CN114022367B - Image quality adjusting method and device, electronic equipment and medium - Google Patents

Abstract

The embodiment of the invention provides an image quality adjusting method, an image quality adjusting device, electronic equipment and a readable storage medium, wherein the method comprises the following steps: determining the type of a chip platform currently used for image quality adjustment and determining the image effect parameter information required to be achieved after image adjustment; selecting a target platform tuning flow corresponding to the chip platform type from preset platform tuning flows, and determining shooting reference parameter information corresponding to the chip platform type; and performing image quality tuning according to the target platform tuning flow and the shooting reference parameter information based on the image effect parameter information. According to the embodiment of the invention, a user can obtain a corresponding image quality tuning result according to the information fed back in the cloud debugging system by photographing and uploading without learning any knowledge system for tuning the image quality of the chip platform, so that the problem of high learning cost caused by the differentiation of the chip platform can be greatly reduced, and the image quality tuning efficiency is improved.

Description

Image quality adjusting method and device, electronic equipment and medium

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to an image quality tuning method, an image quality tuning apparatus, an electronic device, and a computer readable storage medium.

Background

The visual technology of the intelligent internet of things industry rapidly develops, and cameras, around-view monitoring and visual equipment can achieve the purposes of high information content and low hardware investment by means of lenses with wide field angles. In 2021, the IOT (Internet of Things ) industry would require hundreds of millions of cameras.

Current camera products still suffer from certain quality problems, including: module problems (distortion, chromatic aberration, blurring, speckles, etc.), sensor problems (noise, color, dead spots, etc.), reduction, mounting accuracy (viewing angle difference, viewing axis deviation, inclination deviation, etc.). The module and sensor problems can be corrected by image quality tuning (Image Quality Tuning) which refers to optimizing the performance of the camera by adjusting system software, hardware and optical parameters according to the application requirements of the camera. However, the tools, procedures, and module groups for adjusting the imaging quality are different for different processing chips, and there is a large difference. For example, there is an independent module 3DNR for denoising under the Hai Si platform, while the high pass platform does not have this module. The difference between the different platforms makes the platforms relatively independent.

When performing Tuning work on mutually independent differential platforms, a worker needs to learn Tuning flows of different platforms, and as potential possibility of Tuning under the platforms is unknown, non-convergence caused by unknown targets can occur in the process of performing Tuning, namely relevant parameters are continuously adjusted, then testing is continuously shot, and finally a subjective and relatively approved result is achieved through multiple iterations to serve as a Tuning optimal state. Namely, the problem of the prior platform differentiation causes high learning cost and large manpower input of the Tuning work.

Disclosure of Invention

In view of the above, embodiments of the present invention have been made to provide an image quality tuning method and corresponding image quality tuning apparatus, an electronic device, and a computer-readable storage medium that overcome or at least partially solve the above problems.

The embodiment of the invention discloses an image quality adjusting and optimizing method which is applied to a cloud debugging system and comprises the following steps:

Determining the type of a chip platform currently used for image quality adjustment and determining the image effect parameter information required to be achieved after image adjustment;

selecting a target platform tuning flow corresponding to the chip platform type from preset platform tuning flows, and determining shooting reference parameter information corresponding to the chip platform type;

and performing image quality tuning according to the target platform tuning flow and the shooting reference parameter information based on the image effect parameter information.

Optionally, the performing image quality tuning according to the target platform tuning flow and the shooting reference parameter information based on the image effect parameter information includes:

determining an imaging device currently used for image quality tuning, and determining a comparison imaging device of the imaging device;

acquiring a shooting image obtained by adopting the comparison imaging equipment to shoot an image according to a shooting flow in the target platform tuning flow and the shooting reference parameter information;

Performing image quality optimization on the shot image to obtain corresponding image quality optimization parameter information; the image quality optimization parameter information can enable the photographed image subjected to image optimization to reach an image effect corresponding to the image effect parameter information;

and compiling parameters of the image quality optimization parameter information based on the chip platform type.

Optionally, the performing image quality adjustment on the captured image to obtain corresponding image quality optimization parameter information includes:

Performing image quality evaluation based on automatic segmentation on the shot image;

and after the evaluation is passed, performing image optimization processing on the shot image based on a preset degradation model to obtain corresponding image quality optimization parameter information.

Optionally, the preset platform tuning flow is generated according to the following manner:

Determining necessary parameter information required to be input for image tuning; the necessary parameter information is determined according to an operation description document of the chip platform; the necessary parameter information comprises at least one of execution sequence of each tuning module, image test card type and shooting notice;

generating an initial platform tuning flow for the chip platform based on the necessary parameter information;

And acquiring image tuning item data corresponding to the chip platform, and adjusting the initial platform tuning flow according to the image tuning item data to generate the corresponding preset platform tuning flow.

Optionally, the adjusting the initial platform tuning procedure according to the image tuning item data includes:

taking the item as a unit from the image tuning item data, taking a newly added module in a platform tuning flow corresponding to each item, taking a shooting chart and shooting conditions as statistical objects, and calculating the distribution probability of each statistical object in all the items respectively;

If the distribution probability is larger than the preset confidence probability, determining the statistical object corresponding to the distribution probability, and updating the adjustment object corresponding to the statistical object in the initial platform tuning flow.

Optionally, the adjusting the initial platform tuning flow according to the image tuning item data further includes:

if the distribution probability is not greater than the preset confidence probability, determining a reference item matched with the current item from a plurality of items of the image tuning item data;

And adjusting the initial platform tuning flow according to the platform tuning flow of the reference item.

Optionally, the determining the shooting reference parameter information corresponding to the chip platform type includes:

determining a digital imaging combination type of the imaging device; the digital imaging combination type is composed of a chip platform type, an image signal processing unit type, an imaging unit type and a lens type;

Judging whether the number of the image tuning items corresponding to the digital imaging combination type is larger than a preset number threshold value, and determining the shooting reference parameter information according to a judging result.

Optionally, the determining the shooting reference parameter information according to the judging result includes:

If the number is larger than the preset number threshold, acquiring a corresponding coding and decoding network model; the encoding and decoding network model is obtained by taking the historical shooting parameter information of the image tuning item as output and taking the historical image effect parameter information of the image tuning item as input for training;

inputting the image effect parameter information into the coding and decoding network model, and outputting the corresponding shooting reference parameter information;

and if the number is not greater than the preset number threshold, taking shooting parameter information in a development code packet corresponding to the digital imaging combination type as the shooting reference parameter information.

Optionally, the determining the alignment imaging device of the imaging device includes:

If the cloud debugging system has the image tuning item with the same digital imaging combination type as the imaging device, the imaging device of the image tuning item is used as candidate comparison imaging device;

If the cloud debugging system does not have the image tuning item with the same digital imaging combination type as the imaging equipment, comparing the resolution of an imaging unit adopted by the current image tuning item with the resolution of an imaging unit adopted by the previous image tuning item, and taking the imaging equipment of the image tuning item with the least difference in resolution as the candidate comparison imaging equipment;

Determining an image quality evaluation result of the candidate comparison imaging device;

And sequencing the evaluation results, calculating the rank of the image quality loss of each candidate comparison imaging device, taking the candidate comparison imaging device with the last rank as the best comparison imaging device, and taking the candidate comparison imaging devices with the middle rank as the reference comparison imaging device.

Optionally, before the image quality evaluation based on automatic segmentation is performed on the captured image, the method further includes:

judging whether shooting non-normative exists in the process of acquiring the shooting image or not;

If yes, executing the operation of feeding back the shooting problem;

And if the image quality evaluation operation does not exist, executing image quality evaluation operation based on automatic segmentation on the shot image.

Optionally, the determining whether there is a shooting non-specification in the process of acquiring the shooting image includes:

carrying out graying treatment on the shooting image to obtain a gray image corresponding to the shooting image;

carrying out wide dynamic stretching on the gray level image to obtain an enhanced gray level image;

Determining an image template, and determining an image area matched with the image template in the enhanced gray-scale image based on a MMSER method;

Based on the image area, it is determined whether there is a shooting irregularity in the process of acquiring the shot image.

Optionally, the performing image quality evaluation based on automatic segmentation on the captured image includes:

Dividing the shot image based on a preset division model to obtain a corresponding division result; the preset segmentation model is obtained by establishing an image group by adopting an objective image card scene, a subjective image scene and a corresponding marker graph and performing segmentation training on the image group;

Correcting an image segmentation area of the shot image according to the segmentation result;

for the same group of shot images, calculating the shot images in the same area based on objective parameters, and comparing the calculation result with the objective parameters of the shot images shot by the corresponding optimal comparison imaging equipment one by one;

And evaluating the image quality according to the comparison result.

Optionally, the image optimization processing of the photographed image based on a preset degradation model includes:

Performing color optimization processing on the shot image;

Carrying out wiener filtering optimization processing on the shot image;

And carrying out noise optimization processing on the shot image.

Optionally, the performing parameter compiling on the image quality optimization parameter information based on the chip platform type includes:

and based on the chip platform type, performing parameter compiling on the image quality optimization parameter information in a column vector mode.

The embodiment of the invention also discloses an image quality adjusting and optimizing device which is applied to the cloud adjusting system and comprises the following components:

the first determining module is used for determining the type of a chip platform currently used for performing image quality adjustment and determining image effect parameter information required to be achieved after the image adjustment;

The second determining module is used for selecting a target platform tuning flow corresponding to the chip platform type from preset platform tuning flows and determining shooting reference parameter information corresponding to the chip platform type;

And the tuning module is used for performing image quality tuning according to the target platform tuning flow and the shooting reference parameter information based on the image effect parameter information.

Optionally, the tuning module includes:

a first determining submodule, configured to determine an imaging device currently used for performing image quality tuning, and determine a comparison imaging device of the imaging device;

The acquisition sub-module is used for acquiring a shooting image obtained by adopting the comparison imaging equipment to perform image shooting according to a shooting flow in the target platform tuning flow and the shooting reference parameter information;

The tuning sub-module is used for performing image quality tuning on the shot image to obtain corresponding image quality optimization parameter information; the image quality optimization parameter information can enable the photographed image subjected to image optimization to reach an image effect corresponding to the image effect parameter information;

And the compiling sub-module is used for carrying out parameter compiling on the image quality optimization parameter information based on the chip platform type.

Optionally, the tuning submodule includes:

the evaluation unit is used for evaluating the image quality of the shot image based on automatic segmentation;

And the tuning unit is used for carrying out image optimization processing on the shot image based on a preset degradation model after the evaluation is passed, so as to obtain the corresponding image quality optimization parameter information.

Optionally, the preset platform tuning flow is generated in the following manner, and the device further includes:

The third determining module is used for determining necessary parameter information required to be input for image tuning; the necessary parameter information is determined according to an operation description document of the chip platform; the necessary parameter information comprises at least one of execution sequence of each tuning module, image test card type and shooting notice;

the generating module is used for generating an initial platform tuning flow aiming at the chip platform based on the necessary parameter information;

The adjusting module is used for acquiring the image tuning item data corresponding to the chip platform and adjusting the initial platform tuning flow according to the image tuning item data so as to generate the corresponding preset platform tuning flow.

Optionally, the adjusting module includes:

the calculation sub-module is used for taking the item as a unit from the image tuning item data, taking the shooting chart and the shooting condition adopted by the newly-added module in the platform tuning flow corresponding to each item as statistical objects, and calculating the distribution probability of each statistical object in all the items respectively;

and the updating sub-module is used for determining the statistical object corresponding to the distribution probability if the distribution probability is larger than the preset confidence probability, and updating the adjustment object corresponding to the statistical object in the initial platform tuning flow.

Optionally, the adjusting module further includes:

A selecting sub-module, configured to determine a reference item matched with a current item from a plurality of items in the image tuning item data if the distribution probability is not greater than the preset confidence probability;

and the adjusting sub-module is used for adjusting the initial platform tuning flow according to the platform tuning flow of the reference item.

Optionally, the second determining module includes:

A second determination sub-module for determining a digital imaging combination type of the imaging device; the digital imaging combination type is composed of a chip platform type, an image signal processing unit type, an imaging unit type and a lens type;

And the judging sub-module is used for judging whether the number of the image tuning items corresponding to the digital imaging combination type is larger than a preset number threshold value or not, and determining the shooting reference parameter information according to a judging result.

Optionally, the judging submodule includes:

the acquisition unit is used for acquiring a corresponding coding and decoding network model if the number is larger than the preset number threshold; the encoding and decoding network model is obtained by taking the historical shooting parameter information of the image tuning item as output and taking the historical image effect parameter information of the image tuning item as input for training;

the input/output unit is used for inputting the image effect parameter information into the coding/decoding network model and outputting the corresponding shooting reference parameter information;

And the first determining unit is used for adopting shooting parameter information in a development code packet corresponding to the digital imaging combination type as the shooting reference parameter information if the number is not greater than the preset number threshold.

Optionally, the first determining sub-module includes:

The second determining unit is used for taking the imaging equipment of the image tuning item as candidate comparison imaging equipment if the cloud debugging system has the image tuning item with the same digital imaging combination type as the imaging equipment;

A third determining unit, configured to, if the cloud debug system does not have an image tuning item of the same type as the digital imaging combination of the imaging device, compare a resolution of an imaging unit adopted by a current image tuning item with a resolution of an imaging unit adopted by a previous image tuning item, and use an imaging device of an image tuning item with a least difference in resolution as the candidate comparison imaging device;

A fourth determining unit, configured to determine an image quality evaluation result of the candidate comparison imaging device;

And a fifth determining unit, configured to sort the evaluation results, calculate a rank of the image quality loss of each candidate comparison imaging device, use the candidate comparison imaging device with the last rank as the best comparison imaging device, and use the candidate comparison imaging device with the middle rank as the reference comparison imaging device.

Optionally, the tuning submodule further includes:

A judging unit configured to judge whether or not there is a shooting irregularity in the process of acquiring the shot image;

the first execution unit is used for executing the operation of feeding back the shooting problem if the shooting problem exists;

And the second execution unit is used for executing image quality evaluation operation based on automatic segmentation on the photographed image if the photographed image does not exist.

Optionally, the judging unit includes:

the gray processing subunit is used for carrying out gray processing on the shot image to obtain a gray image corresponding to the shot image;

The stretching subunit is used for carrying out wide dynamic stretching on the gray level image to obtain an enhanced gray level image;

A determining subunit, configured to determine an image template, and determine an image area matching the image template in the enhanced gray-scale image based on a MMSER method;

And the judging subunit is used for judging whether shooting inaccuracy exists in the process of acquiring the shooting image based on the image area.

Optionally, the evaluation unit includes:

The segmentation subunit is used for segmenting the shooting image based on a preset segmentation model to obtain a corresponding segmentation result; the preset segmentation model is obtained by establishing an image group by adopting an objective image card scene, a subjective image scene and a corresponding marker graph and performing segmentation training on the image group;

A correction subunit, configured to correct an image division area of the captured image according to the division result;

the comparison subunit is used for calculating the shot images in the same area based on objective parameters for the same group of shot images, and comparing the calculation results with the objective parameters of the shot images shot by the corresponding optimal comparison imaging equipment one by one;

And the evaluation subunit is used for evaluating the image quality according to the comparison result.

Optionally, the tuning unit includes:

The first tuning subunit is used for performing color optimization processing on the photographed image;

the second tuning subunit is used for carrying out wiener filtering optimization processing on the shot image;

And the third tuning subunit is used for carrying out noise optimization processing on the shot image.

Optionally, the compiling sub-module includes:

and the compiling unit is used for carrying out parameter compiling on the image quality optimization parameter information in a column vector mode based on the chip platform type.

The embodiment of the invention also discloses an electronic device, which comprises: a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor implements the steps of a method for image quality adjustment as described above.

The embodiment of the invention also discloses a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the steps of the image quality adjusting method when being executed by a processor.

The embodiment of the invention has the following advantages:

In the embodiment of the invention, the cloud debugging system can determine the target platform tuning flow according to the chip platform type, and perform image quality tuning according to the target platform tuning flow. By adopting the method, a user does not need to learn any knowledge system for image quality adjustment and upload the knowledge system according to the feedback information in the cloud debugging system, so that a corresponding image quality adjustment result can be obtained, the problem of high learning cost caused by chip platform differentiation can be greatly reduced, and the image quality adjustment efficiency is improved.

Drawings

Fig. 1 is a flowchart of steps of an image quality tuning method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a cloud debug system according to an embodiment of the present invention;

FIG. 3 is a flowchart illustrating steps of another image quality adjustment method according to an embodiment of the present invention;

FIG. 4 is a subjective scene graph and corresponding label graph;

Fig. 5 is a block diagram of an image quality adjusting apparatus according to an embodiment of the present invention.

Detailed Description

So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings, and some, but not all of which are illustrated in the appended drawings. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the invention, fall within the scope of protection of the invention.

Camera Tuning refers to a process of Tuning the imaging quality of a Camera through a chip platform tool. The Tuning chip platform refers to an integrated circuit set with an independent computing control unit (CPU), supporting system on a chip (SOC) development, and capable of supporting software and hardware expansion (such as graphics card, storage, video acquisition, etc.). The contrast machine is a camera which shoots images and the video quality is considered to reach the standard. A Tuning module refers to a relatively centralized collection of functions in an imaging processing unit (ISP) that support Tuning. An exposure table (ExposureTable) is a table representing the correspondence of the shutter speed and f-number combination of the camera to the actual auto-exposure state.

The visual technology of the intelligent internet of things industry rapidly develops, and the aims of high information content and low hardware investment can be achieved by means of the lens and the camera with wide field angles, the looking-around monitoring and the visual equipment. In 2021, the IOT industry would require hundreds of millions of cameras.

Product quality issues greatly restrict camera supply cycles, including: module problems (distortion, chromatic aberration, blurring, speckles, etc.), sensor problems (noise, color, dead spots, etc.), reduction, mounting accuracy (viewing angle difference, viewing axis deviation, inclination deviation, etc.). The module and sensor problems can be corrected by CameraTuning, but the tool, flow and module set for adjusting the imaging quality are different and even have larger difference for different processing chips. For example: an independent module 3DNR for denoising under the hessian platform is present, whereas the high-pass platform is not. The difference between the different platforms makes the platforms relatively independent.

When performing a Tuning work on such a chip platform with independent differentiation, cameraTuning staff needs to learn Tuning flows of different platforms, and because potential possibility of Tuning under the platform is unknown, an unconverged condition caused by unknown target can occur in the Tuning process, namely relevant parameters are continuously adjusted, then testing is continuously shot, and finally a subjective and relatively approved result is achieved through multiple iterations to be used as a Tuning optimal state.

Currently, the difference between different chip platforms is still solved by using a manpower mode, and the process of implementing Tuning between different chip platforms is as follows:

1. platform tool usage learning;

2. experimental attempts by a platform tool;

3. Summarizing and accumulating problems;

4. the actual Tuning task implementation includes:

a) Compiling based on parameters of default imaging quality of the platform; b) Shooting a special scene image based on the compiling result, and exporting data; the compiling result refers to a Tuning parameter containing an adaptive current platform; c) The data is imported into a platform tool to perform initial Tuning; d) Adjusting a Tuning parameter by the subjective and objective quality difference of the image shot by the contrast machine; e) Compiling parameters based on a platform compiler; f) Repeating the steps b) to e) until the subjective quality is considered to be substantially consistent.

5. And the platform compiler compiles the final Tuning parameters to finish Tuning.

As can be seen from the above, for a typical Tuning task, the learning cost of manpower on a platform needs to be measured in months, and the whole operation of shooting, tuning and evaluating processes in the implementation process needs to be measured in months once, so that the labor cost of learning and Tuning is higher if other special scenes exist.

The adaptive Tuning scheme for platform differentiation does not exist, but there are more optimization schemes for Tuning implementation process, such as quality automatic evaluation system and automatic shooting system. Although these schemes can reduce the manpower input of Tuning to improve the efficiency, the improvement of the efficiency has little effect on the learning cost caused by the platform differentiation.

In conclusion, the learning cost caused by platform differentiation is too high, so that the labor input is too large. Since the operation description document of the platform and the platform tool version have insufficient matching degree, experience accumulation is caused, various problems of Tuning cannot be processed, and the processing difficulty of the problems caused by the difference between the platforms is higher. The tool software that the platform provided at present has more problems, and the short time hardly relies on platform manufacturer to solve the problem, greatly influences turn efficiency.

One of the core ideas of the embodiment of the invention is that the cloud debugging system can determine the target platform tuning flow according to the chip platform type and perform image quality tuning according to the target platform tuning flow. By adopting the method, a user does not need to learn any knowledge system for image quality adjustment and upload the knowledge system according to the feedback information in the cloud debugging system, so that a corresponding image quality adjustment result can be obtained, the problem of high learning cost caused by chip platform differentiation can be greatly reduced, and the image quality adjustment efficiency is improved.

Referring to fig. 1, a step flow chart of an image quality tuning method provided by an embodiment of the present invention is shown, and the method is applied to a cloud debugging system, and may specifically include the following steps:

Step 101, determining the type of a chip platform currently used for image quality adjustment and determining the image effect parameter information required to be achieved after the image adjustment.

In the embodiment of the invention, the image quality adjustment aiming at different chip platform types can be performed in the cloud debugging system, namely, the Camera Tuning is performed.

Referring to fig. 2, an architecture diagram of a cloud debug system according to an embodiment of the present invention is shown. The cloud debugging system comprises 6 key functional modules, including a platform differentiation compatible module, an integrated automatic Tuning tool module, an integrated automatic evaluation module, a Tuning data cloud compiling module, a Tuning data cloud storage, management and mining module and a basic interaction and communication module.

The type of the chip platform currently used for image quality adjustment and the image effect parameter information required to be achieved after the image adjustment can be determined. In one example, after a user logs in the cloud debugging system, a chip platform type currently used for image quality tuning may be selected from a plurality of chip platform types provided by the cloud debugging system, and image effect parameter information to be achieved may be input in the cloud debugging system. Wherein the image effect parameter information includes sharpness, noise level, exposure curve, etc. The process of determining the chip platform type and the image effect parameter information can be performed in an interactive, communication module.

Step 102, selecting a target platform tuning flow corresponding to the chip platform type from preset platform tuning flows, and determining shooting reference parameter information corresponding to the chip platform type.

In the embodiment of the invention, the chip platform types and the platform tuning flow are in one-to-one correspondence, and the corresponding relationship between the chip platform types and the platform tuning flow is prestored in the cloud debugging system. In addition, the chip platform types and the shooting reference parameter information are in one-to-one correspondence, and the corresponding relation between the chip platform types and the corresponding shooting reference parameter information is also stored in the cloud debugging system in advance. After the chip platform type is determined, a target platform tuning flow corresponding to the selected chip platform type can be selected from the preset platform tuning flows, and shooting reference parameter information corresponding to the chip platform type is determined. When the cloud debugging system provides the target platform tuning flow, the cloud debugging system can also provide the operation instruction description of the corresponding target platform tuning flow.

And step 103, performing image quality tuning according to the target platform tuning flow and the shooting reference parameter information based on the image effect parameter information.

In the embodiment of the invention, based on the image effect parameter information, image quality adjustment can be performed according to the target platform adjustment flow and shooting reference parameter information.

In summary, in the embodiment of the present invention, the cloud debugging system may determine the target platform tuning flow according to the chip platform type, and perform image quality tuning according to the target platform tuning flow. By adopting the method, a user does not need to learn any knowledge system for image quality adjustment and upload the knowledge system according to the feedback information in the cloud debugging system, so that a corresponding image quality adjustment result can be obtained, the problem of high learning cost caused by chip platform differentiation can be greatly reduced, and the image quality adjustment efficiency is improved.

Referring to fig. 3, a flowchart illustrating steps of another image quality tuning method according to an embodiment of the present invention is applied to a cloud debugging system, and may specifically include the following steps:

step 301, determining the type of the chip platform currently used for image quality adjustment, and determining the image effect parameter information required to be achieved after image adjustment.

In the embodiment of the invention, the image quality adjustment aiming at different chip platform types can be performed in the cloud debugging system, the chip platform type currently used for performing the image quality adjustment can be determined in response to the user operation, and the image effect parameter information required to be achieved after the image adjustment is determined.

Step 302, selecting a target platform tuning flow corresponding to the chip platform type from preset platform tuning flows, and determining the shooting reference parameter information corresponding to the chip platform type.

In the embodiment of the invention, the corresponding relation between the chip platform type and the platform tuning flow is prestored in the cloud debugging system, and the corresponding relation between the chip platform type and the corresponding shooting reference parameter information is also prestored in the cloud debugging system. The target platform tuning flow corresponding to the selected chip platform type can be selected from the preset platform tuning flows, and shooting reference parameter information corresponding to the chip platform type is determined.

In an alternative embodiment, the preset platform tuning flow may be generated as follows:

Determining necessary parameter information required to be input for image tuning; generating an initial platform tuning flow for the chip platform based on the necessary parameter information; and acquiring image tuning item data corresponding to the chip platform, and adjusting the initial platform tuning flow according to the image tuning item data to generate the corresponding preset platform tuning flow.

The necessary parameter information is determined according to an operation description document of the chip platform; the necessary parameter information includes at least one of an execution order of the respective tuning modules, an image test card type, and photographing notice.

In the embodiment of the invention, the corresponding initial platform tuning flow for performing image tuning can be determined based on the operation description documents about the image tuning provided by different chip platforms, wherein the initial platform tuning flow comprises necessary parameter information required to be input for performing the image tuning. In one example, the necessary parameter information may include an execution order of the respective tuning modules, an image test card type, photographing notes, and the like.

The execution sequence of each Tuning module is the calling sequence of a pointer to a Tuning module supporting an ISP on any platform, the different Tuning modules are mutually dependent, and the image quality Tuning is performed according to a certain sequence, otherwise, the Tuning result is divergent, and a good Tuning result cannot be obtained. For example, a general tune sequence is: automatic exposure- > black level- > Shading- > coarse denoising- > Gamma adjustment- > color adjustment- > sharpening adjustment- > other special module adjustment.

The image test card type refers to a photographed image card type, and a typical image card for Tuning includes: gray plate, 24 color card, ISO12233 graphic card, transmission 20 th order, 36 th order graphic card, etc.

The shooting notice may be an imaging notice that needs to be set when shooting a certain image card for a certain module in the shooting sequence in the shooting process, such as an exposure value, an EV value, an aperture value, etc.; the requirements of shooting the picture card, such as the area of the occupied picture, shooting inclination and the like, can also be met; in addition, the color temperature, the light intensity and the like of the shooting light source which need to be noted can be also adopted; finally, the captured image format, the storage method, and the like are also possible.

In the embodiment of the invention, the initial platform tuning flow of the corresponding chip platform can be adjusted by accumulating the project data of the image tuning projects of the same or the same type of chip platform.

Adjusting the initial platform tuning flow according to the image tuning project data, including:

Taking the item as a unit from the image tuning item data, taking a newly added module in a platform tuning flow corresponding to each item, taking a shooting chart and shooting conditions as statistical objects, and calculating the distribution probability of each statistical object in all the items respectively; if the distribution probability is larger than the preset confidence probability, determining the statistical object corresponding to the distribution probability, and updating the adjustment object corresponding to the statistical object in the initial platform tuning flow. If the distribution probability is not greater than the preset confidence probability, determining a reference item matched with the current item from a plurality of items of the image tuning item data; and adjusting the initial platform tuning flow according to the platform tuning flow of the reference item.

In the embodiment of the present invention, the tuning and adding of the initial platform tuning flow may include: and a new module, a shooting picture card and shooting conditions. Wherein, a module is added in the process of image tuning; shooting picture card, the requirement of shooting picture card adopted by the product/platform for image tuning, such as the requirement of color temperature of shooting picture card; the photographing condition may be an illumination condition, an exposure table recommended to be adopted, or the like.

And counting a newly added module, a shooting picture card and shooting conditions in the platform tuning flow of each item from the accumulated image tuning item data, calculating the distribution probability of the statistical object in all items respectively, and updating the adjustment object corresponding to the statistical object in the initial platform tuning flow corresponding to the chip platform if the distribution probability is greater than the confidence probability (such as 80%). For example, a 20-order transmission gray-scale image card under the color temperature conditions of 1000lux and 5000k cannot be shot in the initial platform tuning flow, but in the actual implementation of data statistics, 80% of the projects adopt the shooting method, and then the addition of a corresponding shooting image card scene can be suggested in the current initial platform tuning flow. In practical application, even if the chip platforms are consistent, when the directions of the applied products are different, for example, the indoor monitoring camera does not need to consider the outdoor special weather condition, but the outdoor monitoring camera with the same model and the same platform is relatively more complicated. Furthermore, the combination of ccd+lens may also cause differences. The difference between the actual flow and the implementation flow just indicates that the provided default flow may be incomplete, so that the image tuning project data can be adopted to automatically strengthen the tuning flow of the initial platform.

For the case that the distribution probability is not greater than the confidence probability, a reference item matched with the current item can be determined from a plurality of items of the image tuning item data, key index differences between the two items are compared, a specific comparison method can adopt Euclidean distance (index item smaller than 3 dimensions) or a correlation coefficient (high-dimensional index item, often a quality curve), if the difference is small, for example, the distance is lower than 0.0001 or the absolute value of the correlation coefficient is higher than 0.8, the initial platform tuning flow can be considered to be adjusted according to the platform tuning flow of the reference item, for example, a corresponding tuning module is added; otherwise, the association degree is considered to be lower, and the adjustment of the initial platform tuning flow is not needed, for example, the tuning module is not needed to be added.

For step 302, the following steps may be performed:

substep S11, a digital imaging combination type of the imaging device is determined.

And a substep S12, wherein it is determined whether the number of the image tuning items corresponding to the digital imaging combination type is greater than a preset number threshold, and the shooting reference parameter information is determined according to the determination result.

In the embodiment of the invention, the shooting reference parameter information corresponding to the type of the chip platform is determined, the digital imaging combination type of the imaging device can be determined first, and the shooting reference parameter information is determined according to the digital imaging combination type. Wherein the photographing reference parameter information may include an exposure table. The digital imaging combination type is composed of a chip platform type, an image signal processing unit type (ISP), an imaging unit type (Sensor), and a lens type.

The cloud debugging system stores the image tuning items which are processed in advance, the number of the image tuning items which are of the same digital imaging combination type as the current image tuning item can be determined, whether the number is larger than a preset number threshold value or not is judged, and shooting reference parameter information of the current image tuning item is determined according to a judging result.

For sub-step S12, the following steps may be performed:

if the number is larger than the preset number threshold, acquiring a corresponding coding and decoding network model; inputting the image effect parameter information into the coding and decoding network model, and outputting the corresponding shooting reference parameter information; and if the number is not greater than the preset number threshold, taking shooting parameter information in a development code packet corresponding to the digital imaging combination type as the shooting reference parameter information.

The encoding and decoding network model is obtained by taking the historical shooting parameter information of the image tuning item as output and taking the historical image effect parameter information of the image tuning item as input for training.

In the embodiment of the invention, for the chip platform and Sensor combination (digital imaging combination): the chip platform, the ISP processor, the Sensor (imaging unit) +the lens can query whether shooting reference parameter information corresponding to the digital imaging combination exists in a database of the cloud debugging system.

If the digital imaging combination type exists, the number of the items with the same digital imaging combination type which are accumulated currently can be determined, when the number of the items is enough (for example, more than 30 items), the historical shooting parameter information which is finished by final Tuning in the accumulated items is taken as output, the historical image effect parameter information is taken as input, a coding and decoding network model can be trained by constructing a coding and decoding network, then the image effect parameter information of the current item is taken as input, and shooting reference parameter information can be obtained by utilizing the coding and decoding model. When the number of accumulated items is insufficient, it can be considered that the current data accumulation is insufficient to provide a quantization condition, using shooting reference parameters in the development code package.

If the code is not present, the code under the chip platform type in the cloud debugging system can be considered to be incomplete, and a notification can be sent to a user to upload a development code package of the type (generally provided by a platform developer).

And compiling the updated shooting reference parameter information through a cloud compiling module in the cloud debugging system to generate a compiling result for shooting. It should be noted that, the cloud compiling module is provided with a plurality of compilers, the compilers correspond to the chip platform types, and the compilers and the camera development code package can be uploaded into the cloud debugging system together.

Step 303, determining an imaging device currently used for image quality tuning, and determining a comparison imaging device of the imaging devices.

In the embodiment of the invention, the imaging equipment currently used for image quality adjustment can be determined, and screening of comparison imaging equipment is performed based on web crawlers and data mining.

For step 303, the following steps may be performed:

and S21, if the cloud debugging system has the image tuning item with the same type as the digital imaging combination type of the imaging equipment, the imaging equipment of the image tuning item is used as candidate comparison imaging equipment.

And S22, if the cloud debugging system does not have the image tuning item with the same digital imaging combination type as the imaging device, comparing the resolution of the imaging unit adopted by the current image tuning item with the resolution of the imaging unit adopted by the previous image tuning item, and taking the imaging device of the image tuning item with the least difference in resolution as the candidate comparison imaging device.

And a substep S23, determining an image quality evaluation result of the candidate comparison imaging device.

And a substep S24, sorting the evaluation results, calculating the rank of the image quality loss of each candidate comparison imaging device, taking the candidate comparison imaging device with the last rank as the best comparison imaging device, and taking the candidate comparison imaging device with the middle rank as the reference comparison imaging device.

When a Tuning item of the same digital imaging combination is stored in the cloud debugging system, the imaging device of the item can be used as a candidate alignment imaging device. Further, in an alternative embodiment, it may be determined that among all tune items having the same digital imaging combination: the final evaluation result of the imaging equipment and the image quality evaluation result of the related comparison imaging equipment are respectively sequenced according to the evaluation results of geometric distortion rate, noise, detail loss, color cast and the like, then the comprehensive ranking of the imaging quality loss of each imaging equipment is calculated, the calculation method is shown as a formula 1, the imaging equipment with the final comprehensive ranking is finally selected as the golden comparison imaging equipment, the ranking is in the middle and is used as a reference comparison imaging equipment, and the screening work of the comparison imaging equipment is completed.

Wherein score represents the composite score; alpha represents the geometric distortion rate; sigma represents noise; η represents detail loss; Δc _mean represents the average color shift.

When the cloud debugging system does not have the same digital imaging combination of the Tuning items, the item closest to the Sensor resolution or the frame rate can be selected from all the items, and the specific method is to calculate the resolution and frame rate difference, and the imaging device involved in the item with the difference of 0 is used as the candidate comparison imaging device. Searching image quality evaluation results of candidate comparison imaging devices, sorting the image quality evaluation results by using evaluation results such as geometric distortion rate, noise, detail loss, average color cast and the like, calculating comprehensive ranking of the imaging quality loss of each imaging device, and finally selecting the imaging device with the last comprehensive ranking as a golden comparison imaging device, namely the shooting device with the highest imaging quality, wherein ranking is in the middle and is used as a benchmark comparison imaging device, namely the shooting device with more average imaging quality, and completing screening work of the comparison imaging device.

In another alternative embodiment, when the storage of the Tuning item for the digital imaging combination in the cloud debugging system is empty, the imaging terminal device consistent with the resolution of the imaging device to be tuned can be searched by the web crawler, including but not limited to a mobile phone, an IOT special device, a customized product and the like, the captured device information is analyzed, the analysis method is to calculate a second order norm according to the sensor information of the current imaging device and the keyword in the captured device information, the attribute value with the same keyword, such as the keyword is the resolution, the resolution of the terminal device is h ₁×w₁, the resolution of the current imaging device to be tuned is h ₂×w₂, and the second order norm with the keyword is the resolution isNeglecting non-numerical attribute calculation, calculating second order norm values and average values of all numerical and keyword matching, carrying out average ascending sorting on the captured terminal equipment and imaging equipment to be turned on based on the average values, and selecting terminal equipment with the top ranking T (T suggestion is more than 4) of the average value and complete attribute information (price, manufacturer, size, specification and the like) as candidate comparison imaging equipment; based on the detailed information of the T type terminal equipment, sorting from small to large according to the mining information quantity, selecting the terminal equipment with the information quantity ranked as the middle position as a reference comparison imaging equipment, and taking the terminal equipment with the largest information quantity as a golden comparison imaging equipment.

Step 304, obtaining a shooting image obtained by adopting the comparison imaging device to perform image shooting according to the shooting flow in the target platform tuning flow and the shooting reference parameter information.

In the embodiment of the invention, after the comparison imaging device is determined, the comparison imaging device can be adopted to shoot images according to the shooting flow and shooting reference parameter information in the target platform tuning flow.

The user can shoot the image according to the provided comparison imaging device and shooting flow. In an example, the model of the imaging device can be compared in the cloud debugging system, the model selection suggestion of the imaging device can be provided for the user, then the shooting process is provided in an auxiliary mode, a worker is required to shoot according to the shooting process, and the corresponding shooting image and related data are required to be named according to the shooting process. And the cloud debugging system acquires the shooting image uploaded by the user.

And 305, performing image quality optimization on the shot image to obtain corresponding image quality optimization parameter information.

The image quality optimization parameter information can enable the photographed image subjected to the image optimization processing to achieve an image effect corresponding to the image effect parameter information.

In the embodiment of the invention, the image quality of the obtained shooting image is optimized to obtain the image quality optimization parameter information meeting the image effect requirement corresponding to the image effect parameter information.

For step 305, the following steps may be performed:

and a substep S31, performing image quality evaluation based on automatic segmentation on the shot image.

After the photographed image is identified, image quality evaluation can be performed.

In an optional embodiment, the target platform tuning process has constraint conditions on the uploaded captured image, and it is required to determine whether the uploaded captured image belongs to abnormal data, and perform corresponding interactive correction under the condition of the uploaded captured image belonging to the abnormal data.

In one example, a determination may be made as to the naming format of the captured image. The method can check the shot images uploaded according to the shooting flow in a one-to-one correspondence mode according to the data naming rule to determine whether shot image naming inconsistent with the shooting flow requirements exists, if so, the shot images are considered to be nonstandard, and the nonstandard data quantity F can be recorded. In the case where there is no nonstandard captured image, F is 0.

In addition, the content of the photographed image can be determined. Before the image quality evaluation based on automatic segmentation is performed on the photographed image, the method further comprises the following steps:

Judging whether shooting non-normative exists in the process of acquiring the shooting image or not; if yes, executing the operation of feeding back the shooting problem; and if the image quality evaluation operation does not exist, executing image quality evaluation operation based on automatic segmentation on the shot image.

The judging whether the shooting non-normative exists in the process of acquiring the shooting image comprises the following steps:

Carrying out graying treatment on the shooting image to obtain a gray image corresponding to the shooting image; carrying out wide dynamic stretching on the gray level image to obtain an enhanced gray level image; determining an image template, and determining an image area matched with the image template in the enhanced gray-scale image based on a MMSER method; based on the image area, it is determined whether there is a shooting irregularity in the process of acquiring the shot image.

In the embodiment of the invention, the shot image can be subjected to gray-scale processing to obtain the gray-scale image f corresponding to the scene of the shot image; the method for carrying out wide dynamic stretching on the gray-scale image comprises the following specific steps: firstly, counting a normalized gray level histogram of a shot image, then calculating an integral of the statistical histogram to obtain an integral histogram, finding gray level values g _min and g _max of which the integral histogram value is closest to a gray level lower limit (such as an integral value of 0.05) and a gray level upper limit (such as 0.95 for example), and adjusting gray levels f (x, y) at y epsilon [1, h ₂ ] row x epsilon [1, w ₂ ] according to a formula 2 to obtain enhanced gray levels f' (x, y).

Wherein g _min represents the lower limit of the integral histogram value closest to the gray level; g _max represents the upper limit of the integral histogram value closest to the gray scale, and the resolution of the imaging device currently used for image quality tuning is h ₂×w₂,y∈[1,h₂ representing a row; x epsilon [1, w ₂ ] represents a column; the gray scale f (x, y) is the gray scale value at y ε [1, h ₂ ] row, x ε [1, w ₂ ] column; the enhanced gray scale is f' (x, y).

Taking a standard shooting image card image as an image template, and determining an image area S matched with the template in the enhanced gray level image based on MMSER method; assuming that the difference between the image area S and the overall image shooting area S _t＝h₂×w₂ is too large compared with the required difference in the shooting flow, for example, S/S _t is more than 0.2, if the situation of non-standard shooting exists, f=f+1 is considered, and the judgment is completed; otherwise, calculating an external rectangle of the matched image area based on the convex hull coordinates of the matched image area, assuming that the area of the external rectangle is S _q, if the ratio of S/S _q is too small, for example, smaller than 0.9, the condition of non-standard shooting can be considered, and F=F+1, so that the judgment is completed; otherwise, the shooting specification can be considered. Judging whether F is larger than 0, if so, feeding back to the user, and prompting which photographed images have problems and what the specific problems are, such as irregular photographing caused by the fact that the area ratio does not reach the standard.

After determining that the captured image meets the requirements, quality evaluation for the captured image may be performed. For sub-step S31, the following steps may be performed:

Dividing the shot image based on a preset division model to obtain a corresponding division result; correcting an image segmentation area of the shot image according to the segmentation result; for the same group of shot images, calculating the shot images in the same area based on objective parameters, and comparing the calculation result with the objective parameters of the shot images shot by the corresponding optimal comparison imaging equipment one by one; and evaluating the image quality according to the comparison result.

The preset segmentation model is obtained by establishing an image group by adopting an objective image card scene, a subjective image scene and a corresponding mark image and performing segmentation training on the image group.

In the embodiment of the invention, a segmentation model can be established, the shot image is segmented based on the segmentation model, and the segmentation result is corrected. For the shot images of the same group, objective parameter calculation can be carried out on the shot images in the same area, and the objective parameter calculation is used for comparing the shot images with the objective parameter of the shot images shot by the optimal comparison imaging equipment, so that image quality evaluation can be carried out.

The specific modes can be as follows:

1. First, a plurality of sets of objective chart scenes, subjective scene images and corresponding mark patterns are prepared, and referring to fig. 4, the objective chart scenes, the subjective scene images and the corresponding mark patterns are shown (in fig. 4, (a) is a subjective scene image, and (b) is a corresponding mark pattern). Typical graphics cards, such as 24-color cards, SFRPlus graphics cards, dot patterns and the like, must be contained in the objective graphics card scene; the subjective image scene covers different color temperatures and illumination conditions as much as possible, for example, the color temperature range is 2300K-10000K, and the illumination is 51 ux-10000 lux; the size of the mark graph is consistent with that of the original graph, the gray scale value of each pixel represents a classification label at the same position of the original graph, and labels with the same area or attribute are consistent, for example, the gray scale defined by a blue sky in a subjective scene image in the mark graph is 1, and the gray scale defined by a road scene in the mark graph is 2; the image groups consisting of the original image and the corresponding mark image are enough, for example, more than 10000 groups, and the difference between scenes is as large as possible, for example, the image cards, the color temperature and the illumination conditions cannot be completely consistent.

2. The training based on the pixel2pixel segmentation method is carried out on the image group, great difficulty is considered when the training is carried out on the high-resolution image, the current deep learning segmentation method generally uses a downsampling method to process the high-resolution image, and the precision is insufficient, so that when downsampling is carried out on the input image group data, a plurality of groups (such as more than 10 groups) of low-resolution image groups are generated on the high-resolution image group through a random interception method, and the specific method is as follows:

(1) Assuming that the width of the image is W, the height is H, randomly selecting a starting point as a starting point position (x _s,y_s) of the upper left corner of the randomly intercepted image according to a uniformly distributed mode in the integer range of [1, W ] and [1, H ];

(2) Assuming that the width of the training network input layer is w _in and the height is h _in, in Or alternativelyIn the real number domain of (2), the cutting proportion omega of the width or the height is randomly selected according to a uniform distribution mode, calculated according to the width, and then the cutting width is calculatedCorresponding height

(3) Judging whether the cutting width and the cutting height exceed the boundary of the image on the basis of fixed starting points, namely whether x _s+w_c -1 is more than or equal to W or whether y _s+h_c -1 is more than or equal to H is met; if so, the adjustment mode is x _s＝W-w_c +1 or y _s＝H-h_c +1;

(4) Repeating steps (1) to (3) until a sufficient number of sets, such as 10 sets, is met.

3. Training the generated image group to obtain a corresponding segmentation model; generally, in the normal training mode, the loss of training is gradually reduced;

4. under the condition of providing comparison imaging equipment images, segmenting the shot images based on a trained segmentation model, simultaneously comparing partial segmentation results with whole segmentation results, and correcting image region segmentation of the original image by a voting method in the case of repeated positions but containing various classification results;

5. For any group of images, calculating multiple objective parameters of the images in the same area, wherein the objective parameters comprise: frequency domain information entropy, smoothness, noise level, distribution condition in Lab space and the like;

6. And calculating the respective two norms of the statistical result item by item and the objective parameters of the image shot by the corresponding golden comparison imaging device as the quality difference of all items, and then calculating the average value of the quality differences of all items, wherein the smaller the value is, the closer the objective parameter value representing the imaging device which performs image quality adjustment is to the golden comparison imaging device, otherwise, the larger the quality difference is considered.

And S32, after the evaluation is passed, performing image optimization processing on the shot image based on a preset degradation model to obtain corresponding image quality optimization parameter information.

In the embodiment of the invention, after the evaluation is passed, the image quality optimization processing based on the preset degradation model can be performed on the shot image.

For sub-step S32, the following steps may be performed:

Performing color optimization processing on the shot image; carrying out wiener filtering optimization processing on the shot image; and carrying out noise optimization processing on the shot image.

For performing color optimization processing, it may include:

For a captured image, the optical signal L (x, y) at the coordinate location (x, y), x ε [1, H ], y ε [1, W ], the image produced by the imaging device after capturing the signal is f (x, y, c), c ε {1,2,3} (typically the image is divided into R, G, B channels, denoted 1,2, 3). The overall imaging model can be referenced by equation 3:

wherein g (x, y, c) represents the gray value before color adjustment, K (x, y, c) e 0,1 represents the photoelectric conversion coefficient table, instead of gamma or lut conversion, psf is a low-pass filter, represents the detail loss function, T (-) represents the distortion function, n (x, y, c) represents random noise, b represents the fixed bias, and M represents the color conversion matrix.

The T (-) can be solved firstly, specifically, according to shooting requirements, a golden comparison imaging device and a current imaging device shooting geometric distortion evaluation chart card result are provided, an optical distortion equation of a standard chart card is calculated, and geometric distortion removal is completed according to parameters of the equation;

then solving a photoelectric conversion coefficient table, specifically, comparing images of different scenes shot by the imaging equipment and the current imaging equipment through golden, carrying out histogram matching of different channels to obtain an adjustment value corresponding to each gray level, namely, under the condition of providing any gray level, finding the adjustment value through a histogram matching result, inputting gray level T [ L (x, y) ], and finding a matching conversion coefficient matched with the gray level T [ L (x, y, c) ] as K (x, y, c);

The color conversion matrix is solved by carrying out transformation matrix solving on photographed scene images of the golden comparison imaging equipment and the current imaging equipment:

(1) The same scene image shot by the two imaging devices is arranged into a matrix of 3 rows H multiplied by W according to the column direction, the color matrix of the golden comparison imaging device is C _r, the color matrix of the current imaging device is C _t, and an objective function is constructed as shown in formula 4:

wherein R (·) represents the correlation function, λε 0.5, and 1 represents the constraint value.

(2) Respectively solving partial derivatives of the conversion elements m _i (i epsilon [1,9 ]) of the MC _t-C_r, enabling each partial derivative result to be 0, obtaining a 9-element primary equation set, and completing solving to obtain a conversion matrix;

(3) For the matrix which is solved, calculating |R (MC _t,C_t) |, and assuming that R (MC _t,C_t) > lambda is larger than lambda, considering that the solving of the transformation matrix is completed; otherwise, relaxing the formula 4I MC _t-C_r I to MC _t-C_r||≥Δr,Δr＝||MC_r-C_r I; Δr refers to a transform difference constraint;

(4) Repeating (2) - (3) until the conversion matrix solving is completed or a certain iteration number is reached, for example, more than 100 iterations are stopped, and the conversion matrix of the last time is taken as a final result.

For wiener filter optimization, a blind loss function may be employed, including:

By using a blind loss function estimation method, the transfer functions psf of the current imaging equipment systems with different scales (namely different image card distances and special requirement scenes) are estimated, and then the captured image can be sharpened by using wiener filtering.

For performing noise optimization processing, it may include:

Based on a special shooting chart card and based on the principle of wavelet transformation, the noise level of images shot by current imaging equipment and golden comparison imaging equipment under different scenes is calculated, the noise level is assumed to be sigma and sigma _r respectively, and then Gaussian low-pass filters with different scales (generally adopting original size, 1/4 size and 1/16 size charts) are constructed for a certain scale:

(1) Starting noise σ _s =0.5σ, based on a specified noise level interval σ, taking [0.5σ,1.5σ ] as an example, with a fixed step size t (example t=0.05σ);

(2) Constructing a Gaussian low-pass filter with a filtering window of w _lp according to a formula 5, and ensuring that the window is an odd number;

Wherein the filter window size is w _lp, the initial noise sigma _s =0.5σ, the value b ₁ is 0 or 1, Represents rounding to 0 and mod (·) represents the remainder.

(3) Filtering and denoising the current photographed image of the imaging device based on the provided filter to obtain a denoised image f _n, estimating a noise level σ _n of f _n based on wavelet transform, assuming that |σ _n-σ_r | is large, such as: if the value of the I sigma _n-σ_r I is more than 0.1, the filter is considered unsuitable, and meanwhile, the current filtering difference values of the I sigma _n-σ_r I and the sigma _s are recorded, and the step (4) is executed; otherwise, executing the step (5);

(4) Judging whether sigma _s is larger than the upper limit of the interval, such as 1.5sigma, if yes, selecting sigma _s corresponding to |sigma _n-σ_r | with the smallest difference value in all records as an optimal value, and if no, performing step (2);

(5) The current filtering parameter sigma _s and the corresponding filtering window size w _lp are selected as the current optimal denoising filter parameters according to the image effect requirement corresponding to the image effect parameter information.

And 306, compiling parameters of the image quality optimization parameter information based on the chip platform type.

In the embodiment of the invention, after the shot image is subjected to image optimization processing, the image quality optimization parameter information meeting the image effect requirement corresponding to the image effect parameter information can be obtained. The image quality optimization parameter information may include the color conversion matrix, the system transfer function, the optimal denoising filter parameter, and the like. After the image quality optimization parameter information is determined, the image quality optimization parameter information can be compiled based on the chip platform type.

For step 306, the following steps may be performed:

and S41, carrying out parameter compiling on the image quality optimization parameter information in a column vector mode based on the chip platform type.

In the embodiment of the invention, the image quality optimization parameter information can be compiled by adopting a column vector and a self-coding model construction mode. Specifically, the following manner may be adopted:

1. For the image quality optimization parameter information of any chip platform, based on the shooting image data shot according to the requirement and the original compiling parameters accumulated during shooting the image (such as typical configuration parameter adjusted or default value, parameter after curve adjustment or default parameter and the like), the image quality optimization parameter information of different platforms is arranged into column vectors, such as N ₁ related parameters of a module 1, the parameters are arranged according to the column direction, then N ₂ related parameters of a module 2 are arranged behind the data of the module 1, … … until all the parameters of all the modules of the platform are arranged, the definition of the modules belonging to the same chip platform is required to be consistent, and the parameters of each chip platform are generally stored in a development code package; each item of each platform can generate a column vector related to the item, and the column vectors of all the platforms can form a matrix y _out of D rows and P columns under the condition that the column vector length of any platform is D and P items exist under the same platform, and the vector sizes of different platforms are different;

2. Based on the method in the degradation model, searching the T (-) in the same platform and the corresponding item, matching the histogram with the transformation curve, namely the corresponding reference value of K (x, y, c), the color conversion matrix M, the system transfer function psf and the Gaussian low-pass filter lp with the filter window size of w _lp, and arranging all data obtained by the degradation model according to a column vector mode according to the following specific sequence: the T (-) distortion parameters (8 at most) occupy 9 rows and are less than 0, then the gamma/lut curves occupy 3 x 256 lengths, the color conversion matrix occupies 9 rows according to the arrangement of red, green and blue color channels, the data volume of the color conversion matrix is consistent with that of the conversion matrix, the transfer function of the system occupies 121 rows according to the column direction, the transfer function size is less than 0, the filter parameters of different scales (taking 3 scales as an example) are taken, the filter of each scale occupies 121 rows, and the size is less than 0; thus, the Tuning reference vector data of the platform and the project are obtained, and the vector length is 1270 dimension;

3. Vector data in all items of the same platform are ordered according to rows to form input x _in (generally, the input number of each platform is as high as possible, for example, more than 10 groups, when the number is small, a plurality of groups of Tuning parameters and scene results can be considered to be provided at a demand end), and assuming that the dimension of a contracted degradation model is D _e (for example, 1270 dimension) and P items exist under the same platform, the dimension of x _in is D _e rows and P columns;

4. Taking x _in as input and y _out as output, constructing a self-coding model, and performing self-coding training to obtain a self-coding conversion network of a corresponding platform; parameters of platform differentiation can be considered to be eliminated by a unified degradation model, and are adapted by a self-coding network;

5. based on the image quality optimization parameter information, the image quality optimization parameter information is arranged into an input x _sample of a current platform according to the mode of the step 3, output decoding is carried out based on the coding training model of the platform, and the obtained decoding parameter y _sample is the original compiling parameter of the platform.

6. Based on y _sample and the arrangement mode of the step 1, modifying the compiling parameters of the corresponding platform, and simultaneously calling compilers of different platform+sensor combinations (digital imaging combinations) to complete parameter compiling;

7. The user subjectively judges whether fine adjustment is needed or not by actually shooting the image: if fine adjustment is needed, replacing the related shooting scene images of the imaging equipment with subjective approval result images by adjusting and comparing the shooting scene images, and re-executing the steps of image quality evaluation and image optimization processing until subjective approval; and if fine adjustment is not needed, completing the image quality adjustment of the cloud.

In summary, in the embodiment of the present invention, the cloud debugging system may determine the target platform tuning flow according to the chip platform type, and perform image quality tuning according to the target platform tuning flow. By adopting the method, a user does not need to learn any knowledge system for image quality adjustment and upload the knowledge system according to the feedback information in the cloud debugging system, so that a corresponding image quality adjustment result can be obtained, the problem of high learning cost caused by chip platform differentiation can be greatly reduced, and the image quality adjustment efficiency is improved. In the process of image quality Tuning by the cloud debugging system, a user does not need to learn any knowledge system of the chip platform Tuning, and only needs to upload a picture according to the requirements of the platform Tuning flow, so that a Tuning result can be obtained, and then the Tuning of the result is completed by changing subjective trends. According to the scheme, through constructing an evaluation, tuning and shooting integrated system, learning cost caused by platform differentiation can be eliminated by means of a unified degradation model, and Tuning efficiency is improved. According to the scheme, through a mode of quantitatively accumulating the Tuning project data, based on the mining and crawler technology, various statistical data which cannot be provided by a chip platform side can be provided, so that the Tuning process is more reasonable, and the Tuning process can be dependent on a law. Because the chip platform mostly adopts the AI mode, after accumulating a certain amount of project data, shooting inspection, tuning and evaluation can be completed without depending on a platform Tuning tool, and the stability and referenceability of Tuning are greatly improved.

It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.

Referring to fig. 5, a block diagram of an image quality tuning device according to an embodiment of the present invention is shown, and the block diagram is applied to a cloud tuning system, and may specifically include the following modules:

a first determining module 501, configured to determine a type of a chip platform currently used for performing image quality adjustment, and determine image effect parameter information required to be achieved after image adjustment;

The second determining module 502 is configured to select a target platform tuning flow corresponding to the chip platform type from preset platform tuning flows, and determine the shooting reference parameter information corresponding to the chip platform type;

And the tuning module 503 is configured to perform image quality tuning according to the target platform tuning flow and the shooting reference parameter information based on the image effect parameter information.

In an embodiment of the present invention, the tuning module includes:

a first determining submodule, configured to determine an imaging device currently used for performing image quality tuning, and determine a comparison imaging device of the imaging device;

The acquisition sub-module is used for acquiring a shooting image obtained by adopting the comparison imaging equipment to perform image shooting according to a shooting flow in the target platform tuning flow and the shooting reference parameter information;

The tuning sub-module is used for performing image quality tuning on the shot image to obtain corresponding image quality optimization parameter information; the image quality optimization parameter information can enable the photographed image subjected to image optimization to reach an image effect corresponding to the image effect parameter information;

And the compiling sub-module is used for carrying out parameter compiling on the image quality optimization parameter information based on the chip platform type.

In an embodiment of the present invention, the tuning submodule includes:

the evaluation unit is used for evaluating the image quality of the shot image based on automatic segmentation;

And the tuning unit is used for carrying out image optimization processing on the shot image based on a preset degradation model after the evaluation is passed, so as to obtain the corresponding image quality optimization parameter information.

In the embodiment of the present invention, the preset platform tuning flow is generated in the following manner, and the device further includes:

The third determining module is used for determining necessary parameter information required to be input for image tuning; the necessary parameter information is determined according to an operation description document of the chip platform; the necessary parameter information comprises at least one of execution sequence of each tuning module, image test card type and shooting notice;

the generating module is used for generating an initial platform tuning flow aiming at the chip platform based on the necessary parameter information;

The adjusting module is used for acquiring the image tuning item data corresponding to the chip platform and adjusting the initial platform tuning flow according to the image tuning item data so as to generate the corresponding preset platform tuning flow.

In an embodiment of the present invention, the adjustment module includes:

the calculation sub-module is used for taking the item as a unit from the image tuning item data, taking the shooting chart and the shooting condition adopted by the newly-added module in the platform tuning flow corresponding to each item as statistical objects, and calculating the distribution probability of each statistical object in all the items respectively;

and the updating sub-module is used for determining the statistical object corresponding to the distribution probability if the distribution probability is larger than the preset confidence probability, and updating the adjustment object corresponding to the statistical object in the initial platform tuning flow.

In an embodiment of the present invention, the adjusting module further includes:

A selecting sub-module, configured to determine a reference item matched with a current item from a plurality of items in the image tuning item data if the distribution probability is not greater than the preset confidence probability;

and the adjusting sub-module is used for adjusting the initial platform tuning flow according to the platform tuning flow of the reference item.

In an embodiment of the present invention, the second determining module includes:

A second determination sub-module for determining a digital imaging combination type of the imaging device; the digital imaging combination type is composed of a chip platform type, an image signal processing unit type, an imaging unit type and a lens type;

And the judging sub-module is used for judging whether the number of the image tuning items corresponding to the digital imaging combination type is larger than a preset number threshold value or not, and determining the shooting reference parameter information according to a judging result.

In an embodiment of the present invention, the judging submodule includes:

the acquisition unit is used for acquiring a corresponding coding and decoding network model if the number is larger than the preset number threshold; the encoding and decoding network model is obtained by taking the historical shooting parameter information of the image tuning item as output and taking the historical image effect parameter information of the image tuning item as input for training;

the input/output unit is used for inputting the image effect parameter information into the coding/decoding network model and outputting the corresponding shooting reference parameter information;

And the first determining unit is used for adopting shooting parameter information in a development code packet corresponding to the digital imaging combination type as the shooting reference parameter information if the number is not greater than the preset number threshold.

In an embodiment of the present invention, the first determining sub-module includes:

The second determining unit is used for taking the imaging equipment of the image tuning item as candidate comparison imaging equipment if the cloud debugging system has the image tuning item with the same digital imaging combination type as the imaging equipment;

A third determining unit, configured to, if the cloud debug system does not have an image tuning item of the same type as the digital imaging combination of the imaging device, compare a resolution of an imaging unit adopted by a current image tuning item with a resolution of an imaging unit adopted by a previous image tuning item, and use an imaging device of an image tuning item with a least difference in resolution as the candidate comparison imaging device;

A fourth determining unit, configured to determine an image quality evaluation result of the candidate comparison imaging device;

And a fifth determining unit, configured to sort the evaluation results, calculate a rank of the image quality loss of each candidate comparison imaging device, use the candidate comparison imaging device with the last rank as the best comparison imaging device, and use the candidate comparison imaging device with the middle rank as the reference comparison imaging device.

In an embodiment of the present invention, the tuning submodule further includes:

A judging unit configured to judge whether or not there is a shooting irregularity in the process of acquiring the shot image;

the first execution unit is used for executing the operation of feeding back the shooting problem if the shooting problem exists;

And the second execution unit is used for executing image quality evaluation operation based on automatic segmentation on the photographed image if the photographed image does not exist.

In an embodiment of the present invention, the determining unit includes:

the gray processing subunit is used for carrying out gray processing on the shot image to obtain a gray image corresponding to the shot image;

The stretching subunit is used for carrying out wide dynamic stretching on the gray level image to obtain an enhanced gray level image;

A determining subunit, configured to determine an image template, and determine an image area matching the image template in the enhanced gray-scale image based on a MMSER method;

And the judging subunit is used for judging whether shooting inaccuracy exists in the process of acquiring the shooting image based on the image area.

In an embodiment of the present invention, the evaluation unit includes:

The segmentation subunit is used for segmenting the shooting image based on a preset segmentation model to obtain a corresponding segmentation result; the preset segmentation model is obtained by establishing an image group by adopting an objective image card scene, a subjective image scene and a corresponding marker graph and performing segmentation training on the image group;

A correction subunit, configured to correct an image division area of the captured image according to the division result;

the comparison subunit is used for calculating the shot images in the same area based on objective parameters for the same group of shot images, and comparing the calculation results with the objective parameters of the shot images shot by the corresponding optimal comparison imaging equipment one by one;

And the evaluation subunit is used for evaluating the image quality according to the comparison result.

In an embodiment of the present invention, the tuning unit includes:

The first tuning subunit is used for performing color optimization processing on the photographed image;

the second tuning subunit is used for carrying out wiener filtering optimization processing on the shot image;

And the third tuning subunit is used for carrying out noise optimization processing on the shot image.

In an embodiment of the present invention, the compiling sub-module includes:

and the compiling unit is used for carrying out parameter compiling on the image quality optimization parameter information in a column vector mode based on the chip platform type.

In summary, in the embodiment of the present invention, the cloud debugging system may determine the target platform tuning flow according to the chip platform type, and perform image quality tuning according to the target platform tuning flow. By adopting the method, a user does not need to learn any knowledge system for image quality adjustment and upload the knowledge system according to the feedback information in the cloud debugging system, so that a corresponding image quality adjustment result can be obtained, the problem of high learning cost caused by chip platform differentiation can be greatly reduced, and the image quality adjustment efficiency is improved.

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

The embodiment of the invention also provides electronic equipment, which comprises: the image quality adjusting method comprises a processor, a memory and a computer program which is stored in the memory and can run on the processor, wherein the computer program realizes the processes of the image quality adjusting method embodiment when being executed by the processor, and can achieve the same technical effects, and the repetition is avoided, so that the description is omitted.

The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the processes of the above-mentioned embodiment of the image quality adjusting method, and can achieve the same technical effects, so that repetition is avoided, and no further description is given here.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.

It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or terminal device that comprises the element.

The foregoing has outlined a detailed description of the principles and embodiments of the present invention in which specific examples are provided, the above examples being provided to facilitate the understanding of the method and core concepts of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims (16)

1. An image quality tuning method, characterized by being applied to a cloud debugging system, the method comprising:

Determining the type of a chip platform currently used for image quality adjustment and determining the image effect parameter information required to be achieved after image adjustment;

selecting a target platform tuning flow corresponding to the chip platform type from preset platform tuning flows, and determining shooting reference parameter information corresponding to the chip platform type;

Based on the image effect parameter information, performing image quality tuning according to the target platform tuning flow and the shooting reference parameter information;

the image quality adjustment based on the image effect parameter information according to the target platform adjustment flow and the shooting reference parameter information comprises the following steps:

determining an imaging device currently used for image quality tuning, and determining a comparison imaging device of the imaging device;

acquiring a shooting image obtained by adopting the comparison imaging equipment to shoot an image according to a shooting flow in the target platform tuning flow and the shooting reference parameter information;

Performing image quality optimization on the shot image to obtain corresponding image quality optimization parameter information; the image quality optimization parameter information can enable the photographed image subjected to image optimization to reach an image effect corresponding to the image effect parameter information;

and compiling parameters of the image quality optimization parameter information based on the chip platform type.

2. The method according to claim 1, wherein the performing image quality optimization on the captured image to obtain corresponding image quality optimization parameter information includes:

Performing image quality evaluation based on automatic segmentation on the shot image;

and after the evaluation is passed, performing image optimization processing on the shot image based on a preset degradation model to obtain corresponding image quality optimization parameter information.

3. The method of claim 1, wherein the preset platform tuning flow is generated as follows:

Determining necessary parameter information required to be input for image tuning; the necessary parameter information is determined according to an operation description document of the chip platform; the necessary parameter information comprises at least one of execution sequence of each tuning module, image test card type and shooting notice;

generating an initial platform tuning flow for the chip platform based on the necessary parameter information;

And acquiring image tuning item data corresponding to the chip platform, and adjusting the initial platform tuning flow according to the image tuning item data to generate the corresponding preset platform tuning flow.

4. A method according to claim 3, wherein said adjusting the initial platform tuning flow according to the image tuning item data comprises:

taking the item as a unit from the image tuning item data, taking a newly added module in a platform tuning flow corresponding to each item, taking a shooting chart and shooting conditions as statistical objects, and calculating the distribution probability of each statistical object in all the items respectively;

If the distribution probability is larger than the preset confidence probability, determining the statistical object corresponding to the distribution probability, and updating the adjustment object corresponding to the statistical object in the initial platform tuning flow.

5. The method of claim 4, wherein said adjusting the initial platform tuning flow according to the image tuning item data further comprises:

if the distribution probability is not greater than the preset confidence probability, determining a reference item matched with the current item from a plurality of items of the image tuning item data;

And adjusting the initial platform tuning flow according to the platform tuning flow of the reference item.

6. The method of claim 1, wherein the determining the photographing reference parameter information corresponding to the chip platform type comprises:

determining a digital imaging combination type of the imaging device; the digital imaging combination type is composed of a chip platform type, an image signal processing unit type, an imaging unit type and a lens type;

Judging whether the number of the image tuning items corresponding to the digital imaging combination type is larger than a preset number threshold value, and determining the shooting reference parameter information according to a judging result.

7. The method of claim 6, wherein determining the photographing reference parameter information according to the determination result comprises:

If the number is larger than the preset number threshold, acquiring a corresponding coding and decoding network model; the encoding and decoding network model is obtained by taking the historical shooting parameter information of the image tuning item as output and taking the historical image effect parameter information of the image tuning item as input for training;

inputting the image effect parameter information into the coding and decoding network model, and outputting the corresponding shooting reference parameter information;

and if the number is not greater than the preset number threshold, taking shooting parameter information in a development code packet corresponding to the digital imaging combination type as the shooting reference parameter information.

8. The method of claim 1, wherein the determining an aligned imaging device of the imaging device comprises:

If the cloud debugging system has the image tuning item with the same digital imaging combination type as the imaging device, the imaging device of the image tuning item is used as candidate comparison imaging device;

If the cloud debugging system does not have the image tuning item with the same digital imaging combination type as the imaging equipment, comparing the resolution of an imaging unit adopted by the current image tuning item with the resolution of an imaging unit adopted by the previous image tuning item, and taking the imaging equipment of the image tuning item with the least difference in resolution as the candidate comparison imaging equipment;

Determining an image quality evaluation result of the candidate comparison imaging device;

And sequencing the evaluation results, calculating the rank of the image quality loss of each candidate comparison imaging device, taking the candidate comparison imaging device with the last rank as the best comparison imaging device, and taking the candidate comparison imaging devices with the middle rank as the reference comparison imaging device.

9. The method according to claim 2, further comprising, before the automatically segmented image quality evaluation of the captured image:

judging whether shooting non-normative exists in the process of acquiring the shooting image or not;

If yes, executing the operation of feeding back the shooting problem;

And if the image quality evaluation operation does not exist, executing image quality evaluation operation based on automatic segmentation on the shot image.

10. The method of claim 9, wherein the determining whether there is a shooting irregularity in the process of acquiring the captured image comprises:

carrying out graying treatment on the shooting image to obtain a gray image corresponding to the shooting image;

carrying out wide dynamic stretching on the gray level image to obtain an enhanced gray level image;

Determining an image template, and determining an image area matched with the image template in the enhanced gray-scale image based on a MMSER method;

Based on the image area, it is determined whether there is a shooting irregularity in the process of acquiring the shot image.

11. The method of claim 2, wherein the automatically segmented image quality evaluation of the captured image comprises:

Dividing the shot image based on a preset division model to obtain a corresponding division result; the preset segmentation model is obtained by establishing an image group by adopting an objective image card scene, a subjective image scene and a corresponding marker graph and performing segmentation training on the image group;

Correcting an image segmentation area of the shot image according to the segmentation result;

for the same group of shot images, calculating the shot images in the same area based on objective parameters, and comparing the calculation result with the objective parameters of the shot images shot by the corresponding optimal comparison imaging equipment one by one;

And evaluating the image quality according to the comparison result.

12. The method according to claim 2, wherein the performing image optimization processing on the captured image based on a preset degradation model includes:

Performing color optimization processing on the shot image;

Carrying out wiener filtering optimization processing on the shot image;

And carrying out noise optimization processing on the shot image.

13. The method according to claim 1, wherein the parameter compiling the image quality optimization parameter information based on the chip platform type comprises:

and based on the chip platform type, performing parameter compiling on the image quality optimization parameter information in a column vector mode.

14. An image quality tuning apparatus, characterized by being applied to a cloud debugging system, comprising:

the first determining module is used for determining the type of a chip platform currently used for performing image quality adjustment and determining image effect parameter information required to be achieved after the image adjustment;

The second determining module is used for selecting a target platform tuning flow corresponding to the chip platform type from preset platform tuning flows and determining shooting reference parameter information corresponding to the chip platform type;

the tuning module is used for performing image quality tuning according to the target platform tuning flow and the shooting reference parameter information based on the image effect parameter information;

wherein, the tuning module includes:

a first determining submodule, configured to determine an imaging device currently used for performing image quality tuning, and determine a comparison imaging device of the imaging device;

The acquisition sub-module is used for acquiring a shooting image obtained by adopting the comparison imaging equipment to perform image shooting according to a shooting flow in the target platform tuning flow and the shooting reference parameter information;

The tuning sub-module is used for performing image quality tuning on the shot image to obtain corresponding image quality optimization parameter information; the image quality optimization parameter information can enable the photographed image subjected to image optimization to reach an image effect corresponding to the image effect parameter information;

And the compiling sub-module is used for carrying out parameter compiling on the image quality optimization parameter information based on the chip platform type.

15. An electronic device, comprising: a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor carries out the steps of an image quality tuning method according to any one of claims 1-13.

16. A computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of a method for image quality adjustment according to any one of claims 1-13.