CN111476065A - Target tracking method and device, computer equipment and storage medium - Google Patents

Abstract

The embodiment of the invention discloses a target tracking method, a target tracking device, computer equipment and a storage medium, wherein the target tracking method comprises the following steps: acquiring a tracking area of a target to be tracked; reducing the pixel value in the tracking area to a preset pixel value, and extracting the characteristics of the target to be tracked from the reduced tracking area; and tracking the characteristics by a preset target tracking algorithm. By reducing the pixel value in the tracking area to the preset pixel value and extracting the target to be tracked from the reduced tracking area, the method extracts the characteristics after reducing the pixel value in the tracking area, can avoid the interference of other factors, accurately and quickly extracts the characteristics of the target to be tracked, and further improves the tracking speed.

Description

Target tracking method, device, computer equipment and storage medium

technical field

Embodiments of the present invention relate to the field of video detection, and in particular, to a target tracking method, device, computer equipment, and storage medium.

Background technique

In recent years, the target tracking algorithm of correlation filtering has been very popular due to its characteristics of real-time tracking, relatively high accuracy, and low hardware requirements. And the target tracking algorithm based on correlation filtering such as KCF has the characteristics of real-time tracking.

However, in some scenarios, the tracking speed of the target tracking algorithm based on correlation filtering is small, which cannot meet the actual requirements, thereby affecting its application range.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a target tracking method, apparatus, computer equipment, and storage medium.

In order to solve the above-mentioned technical problems, a technical solution adopted by the embodiment of the present invention is to provide a target tracking method, comprising the following steps:

Obtain the tracking area of the target to be tracked;

reducing the pixel value in the tracking area to a preset pixel value, and extracting the feature of the target to be tracked from the reduced tracking area;

The features are tracked by a preset target tracking algorithm.

Optionally, the obtaining the tracking area of the target to be tracked includes:

Extract video frames from videos that need to be tracked;

Obtain the frame of the target to be tracked from the video frame;

The movement speed of the target to be tracked in the video frame is acquired, and the tracking area of the target to be tracked is determined according to the movement speed.

Optionally, the determining the tracking area of the target to be tracked according to the motion speed includes:

Determine the speed range that the motion speed of the target to be tracked conforms to;

Find the magnification corresponding to the speed range in the preset information table;

Taking the target to be tracked as the center, the boundary is enlarged according to the magnification factor, and the enlarged area is used as the tracking area.

Optionally, the reducing the pixel value in the tracking area to a preset pixel value includes:

obtain the current pixel value of the tracking area;

determining whether the pixel value is greater than a preset pixel value;

When the pixel value is greater than a preset pixel value, the pixel value of the tracking area is reduced to the preset pixel value.

Optionally, the feature of extracting the target to be tracked from the reduced tracking area includes:

obtaining a horizontal gradient image and a vertical gradient image of the tracking area;

Obtain a gradient magnitude image matrix according to the horizontal gradient image and the vertical gradient image, and calculate the gradient magnitude integral map of each image in the gradient magnitude image matrix;

The gradient magnitude integral map of each image is added to obtain the directional gradient histogram feature of the target to be tracked.

Optionally, the feature is tracked by a preset target tracking algorithm, including:

Using the feature as a tracking target to track in the first video frame group through a correlation filtering algorithm;

Obtain the feature of the target to be tracked from the first frame in the second video frame group;

Tracking is performed in the second video frame group with the acquired feature, wherein the first video frame group is continuous with the second video frame group.

Optionally, after judging whether the pixel value is greater than a preset pixel value, the method further includes;

When the pixel value is smaller than a preset pixel value, the pixel value of the tracking area is retained.

To solve the above technical problems, an embodiment of the present invention also provides a target tracking device, including:

The acquisition module is used to acquire the tracking area of the target to be tracked;

a processing module for reducing the pixel value in the tracking area to a preset pixel value, and extracting the feature of the target to be tracked from the reduced tracking area;

The execution module is used for tracking the feature through a preset target tracking algorithm.

Optionally, the obtaining module includes:

The first acquisition sub-module is used to extract video frames from the video that needs to be processed by target tracking;

The second acquisition submodule is used to acquire the frame of the target to be tracked from the video frame;

The third acquisition sub-module is configured to acquire the motion speed of the target to be tracked in the video frame, and determine the tracking area of the target to be tracked according to the motion speed.

Optionally, the third acquisition submodule includes:

a first processing submodule, used to determine a speed range that the motion speed of the target to be tracked conforms to;

a second processing submodule, configured to look up the magnification corresponding to the speed range in a preset information table;

The first execution sub-module is configured to take the target to be tracked as the center, amplify the boundary according to the magnification factor, and use the enlarged area as the tracking area.

Optionally, the processing module includes:

The fourth acquisition sub-module is used to acquire the current pixel value of the tracking area;

a third processing submodule, configured to determine whether the pixel value is greater than a preset pixel value;

The second execution sub-module is configured to reduce the pixel value of the tracking area to the preset pixel value when the pixel value is greater than the preset pixel value.

Optionally, the processing module includes:

The fifth acquisition submodule is used to acquire the horizontal gradient image and the vertical gradient image of the tracking area;

The fourth processing submodule is used to obtain a gradient magnitude image matrix according to the horizontal gradient image and the vertical gradient image, and calculate the gradient magnitude integral map of each image in the gradient magnitude image matrix;

The third execution sub-module is used for adding the gradient magnitude integral map of each image to obtain the directional gradient histogram feature of the target to be tracked.

Optionally, the execution module includes:

The fifth processing submodule is used for tracking in the first video frame group with the feature as a tracking target through a correlation filtering algorithm;

The sixth acquisition submodule is used to acquire the feature of the target to be tracked from the first frame in the second video frame group;

The fourth execution sub-module is used for tracking in the second video frame group with the acquired feature, wherein the first video frame group is continuous with the second video frame group.

Optionally, also include;

The sixth processing submodule is configured to retain the pixel value of the tracking area when the pixel value is smaller than a preset pixel value.

To solve the above technical problem, an embodiment of the present invention further provides a computer device, including a memory and a processor, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, all The processor executes the steps of the target tracking method described above.

In order to solve the above technical problem, an embodiment of the present invention further provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the above-mentioned Describe the steps of the target tracking method.

The beneficial effect of the embodiment of the present invention is: by reducing the pixel value in the tracking area to a preset pixel value, and extracting the target to be tracked from the reduced tracking area, in this method, the pixel value of the tracking area is reduced and then the feature is extracted, which can Avoid the interference of other factors, accurately and quickly extract the characteristics of the target to be tracked, thereby improving the tracking speed.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

FIG. 1 is a schematic flowchart of a basic flow of a target tracking method provided by an embodiment of the present invention;

2 is a schematic diagram of a basic flow of a method for acquiring a tracking area provided by an embodiment of the present invention;

3 is a schematic flow chart of a method for obtaining a tracking area of a target to be tracked by determining a magnification of a boundary according to a motion speed according to an embodiment of the present invention;

4 is a schematic flowchart of a basic flow of a method for reducing pixel values in a tracking area to a preset pixel value according to an embodiment of the present invention;

5 is a schematic flowchart of a basic flow of a method for extracting features of a target to be tracked from a reduced tracking area provided by an embodiment of the present invention;

FIG. 6 is a basic flowchart of a method for tracking a feature by using a preset target tracking algorithm according to an embodiment of the present invention;

FIG. 7 is a basic structural block diagram of a target tracking apparatus provided by an embodiment of the present invention;

FIG. 8 is a basic structural block diagram of a computer device provided by an embodiment of the present invention.

Detailed ways

In order for those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

In some of the processes described in the description and claims of the present invention and the above-mentioned drawings, various operations are included in a specific order, but it should be clearly understood that these operations may not be in accordance with the order in which they appear herein. For execution or parallel execution, the sequence numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the sequence numbers themselves do not represent any execution order. Additionally, these flows may include more or fewer operations, and these operations may be performed sequentially or in parallel. It should be noted that the descriptions such as "first" and "second" in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit "first" and "second" are different types.

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

Example

Those skilled in the art can understand that the "terminal" and "terminal device" used here include both a wireless signal receiver device that only has a wireless signal receiver without transmission capability, and a device that includes receiving and transmitting hardware. A device having receive and transmit hardware capable of performing two-way communications over a two-way communication link. Such equipment may include: cellular or other communication equipment, which has a single-line display or a multi-line display or a cellular or other communication device without a multi-line display; PCS (Personal Communications Service), which can combine voice, data Processing, fax and/or data communication capabilities; PDA (Personal Digital Assistant), which may include a radio frequency receiver, pager, Internet/Intranet access, web browser, notepad, calendar and/or GPS (Global Positioning System) receiver; conventional laptop and/or palmtop computer or other device having and/or including a conventional laptop and/or palmtop computer or other device with a radio frequency receiver. As used herein, "terminal", "terminal equipment" may be portable, transportable, mounted in a vehicle (air, marine and/or land), or adapted and/or configured to operate locally, and/or In distributed form, run at any other location on Earth and/or in space. The "terminal" and "terminal device" used here can also be a communication terminal, an Internet terminal, and a music/video playing terminal, such as a PDA, a MID (Mobile Internet Device) and/or a music/video playing terminal. It can also be a smart TV, a set-top box and other devices.

The client terminal in this embodiment is the above-mentioned terminal.

Specifically, please refer to FIG. 1 , which is a schematic diagram of a basic flow of the target tracking method according to this embodiment.

As shown in Figure 1, the target tracking method includes the following steps:

S1100, acquiring the tracking area of the target to be tracked;

The tracking area is the area where the target to be tracked determined in the video frame in the video to be subjected to target tracking processing is located. Generally, the tracking area is an area with a preset shape including the tracking target, for example, a rectangular area including the tracking target, a square area, and the like. The video that needs to be processed for target tracking may be the video obtained in the application scenario where the target needs to be monitored. For example, in a security application, people need to be monitored, and a video camera is used to record the video in the application environment. It should be noted that the target to be tracked can be various types of objects, such as people and things, for example, monitoring a confidential environment, and tracking the monitored person in the monitored video.

In this embodiment, when acquiring the tracking area, first extract the video frame from the video, identify the target to be tracked in the video frame through the preset recognition model, and use the area with the preset size ratio where the target is located as the target area.

It should be noted that the recognition model is a model obtained by pre-training the neural network model with sample data. For example, when the target to be tracked is a person, images of various types of people, such as human faces, human body shapes, etc., can be used as sample data, and the neural network model algorithm can be trained through such sample data.

In some embodiments, when determining the tracking area where the target to be tracked is located, the identified target to be tracked is taken as the center, and a shape with a size of a preset proportion including the target is used as the tracking area. The area where the smallest rectangle of the tracked target is located is used as the tracking area or the circumscribed circle of the target to be tracked is used as the tracking area.

S1200, reducing the pixel value in the tracking area to a preset pixel value, and extracting the feature of the target to be tracked from the reduced tracking area;

In this embodiment, the pixel size of the tracking area is acquired, and the pixel size is compared with the preset pixel value. When the pixel size of the tracking area is larger than the preset pixel value, the pixel size of the tracking area is reduced to Default pixel value.

In practical applications, when tracking the target in the video, the application is limited due to the low tracking speed. Therefore, in order to improve the tracking speed, in this embodiment, the pixel value of the tracking area is reduced, and the pixel value of the tracking area is reduced from the reduced tracking area. Extracting the features of the target to track the features can improve the tracking speed. Preferably, the preset pixel value may be 30*30. In other embodiments, an appropriate pixel value may also be set for the speed of the target.

In some embodiments, when extracting the features of the tracking area, the histogram features can be extracted, for example, grayscale processing is performed from the video frame, the grayscale value is divided into 8 intervals from 0-255, and each Pixels, count the number of pixels that fall into each interval, and finally divide the number of pixels in the 8 intervals by the sum of the pixels, and normalize them to obtain the histogram feature.

In some other implementations, local binary pattern features (Local Binary Pattern, LBP) can also be extracted, that is, the center pixel of the image in the tracking area is used as a threshold, and the gray values of 8 adjacent pixels are compared with the center pixel. , if the surrounding pixel value is greater than the central pixel value, the position of the pixel is marked as 1, otherwise it is 0. In this way, an 8-bit binary number can be generated, that is, the LBP feature of the center pixel of the tracking area image is obtained.

S1300. Track the feature by using a preset target tracking algorithm.

The preset target tracking algorithms include: correlation filtering-based tracking algorithms, such as Karaman filter tracking algorithm and particle filter tracking algorithm.

In some embodiments, in order to improve the tracking accuracy, the features can be updated according to the number of video frames, for example, features are extracted from the tracking area every 3-5 frames, and used as the updated features, and passed through The correlation filtering tracking algorithms listed above track the features.

In the above target tracking method, by reducing the pixel value in the tracking area to a preset pixel value, and extracting the target to be tracked from the reduced tracking area, in this method, the pixel value of the tracking area is reduced to extract features, which can avoid other factors. It can accurately and quickly extract the features of the target to be tracked, thereby improving the tracking speed.

In practical applications, when the moving speed of the target in the video is too fast, there will be a situation that the target cannot be tracked in time, that is, the tracking speed is too slow. Therefore, in order to solve this problem, an embodiment of the present invention also provides a method for acquiring a tracking area, as shown in FIG. 2 , which is a schematic flowchart of a basic flow of a method for acquiring a tracking area provided by an embodiment of the present invention.

Specifically, as shown in FIG. 2, step S1100 includes the following steps:

S1110, extracting video frames from the video that needs to be subjected to target tracking processing;

S1120, obtaining the frame of the target to be tracked from the video frame;

The video that needs to be processed by target tracking can be the video obtained in the application scenario where the target needs to be monitored. For example, in a security application, people need to be monitored, and a video camera is used to record the video in the application environment.

In this embodiment, each video frame is sequentially extracted according to the playback order in the acquired video, the target recognition model is used to determine whether there is a target to be tracked in each video frame, and the video frame in which the target to be tracked for the first time is extracted is extracted.

It should be noted that the target recognition model may be a model that has been pre-trained to the convergence of the convolutional neural network algorithm through sample data of the target to be tracked. The target recognition model can also be a feature extraction model. For example, the feature of the target to be tracked is extracted from the video frame, and the feature is compared with the feature extracted from the next video frame. If the comparison is consistent, it is regarded as the target to be tracked. .

In this embodiment, the target recognition model is used to identify the target to be tracked in the video frame, and the coordinates and size of the currently identified frame to be tracked are acquired. The frame of the target to be tracked is a preset boundary of an area that can include the target to be tracked. In this embodiment, the frame is the boundary of the smallest area of the target to be tracked, preferably a rectangle.

S1130: Acquire the motion speed of the target to be tracked in the video frame, and determine the tracking area of the target to be tracked according to the motion speed.

Using preset application software, such as Adobe Premiere Pro Cs, input the video frames into the software to calculate the motion speed of the target to be tracked.

In practical applications, when the moving speed of the target to be tracked is fast, the situation that the tracking speed cannot keep up with the moving speed easily occurs, that is, the problem that the tracking speed is slow. There are multiple magnifications. When the movement speed is fast, set a larger magnification and enlarge the frame to obtain a larger area including the target to be tracked. In this way, the speed of the target to be tracked is faster. , the target can still be tracked in time. When the movement speed is small, setting a small zoom-in speed can also track the target.

An embodiment of the present invention further provides a method for obtaining a tracking area of a target to be tracked by determining the magnification of the boundary according to the moving speed, as shown in FIG. A schematic diagram of the basic flow of the method for obtaining the tracking area of the target to be tracked by multiples.

Specifically, as shown in FIG. 3, step S1130 includes the following steps:

S1131. Determine the speed range that the motion speed of the target to be tracked conforms to;

S1132, looking up the magnification corresponding to the speed range in a preset information table;

In the embodiment of the present invention, a plurality of speed ranges are preset, and after the motion speed is obtained, the motion speed is compared with the preset multiple speed ranges, and a speed range matching the motion speed is obtained. The preset information table records the corresponding relationship between the speed range and the magnification.

For example, the acquired motion speed of the target to be tracked is 1.5, the preset multiple speeds are in the range of 0-1, 1-2, 2-3, the speed range 0-1 in the information table corresponds to 1.5 times, and 1-2 corresponds to 2 times, 2-3 corresponds to 2.5 times. Then, it can be determined that the corresponding speed range is 1-2 through the motion speed of 1.5, and the magnification corresponding to 1-2 is determined to be 2 times through the information table.

It should be noted that the magnification is the magnification of the frame size.

S1133 , taking the target to be tracked as the center, enlarging the boundary according to the magnification factor, and using the enlarged area as the tracking area.

When enlarging the boundary, fix the coordinates of the center of the target to be tracked, enlarge the frame size according to the magnification factor, and use the enlarged area as the tracking area.

An embodiment of the present invention provides a method for reducing pixel values in a tracking area to a preset pixel value. As shown in FIG. 4 , FIG. 4 is a method for reducing pixel values in a tracking area to a predetermined value according to an embodiment of the present invention. A schematic diagram of the basic flow of the method for setting pixel values.

Specifically, as shown in FIG. 4, step S1200 includes the following steps:

S1211, obtaining the current pixel value of the tracking area;

When acquiring the pixel value of the tracking area, a pointer operation method can be used to traverse all the pixel values in the tracking area in a double loop. The implementation code is as follows:

For(int i=0; <rowNumber; i++)//Row loop

{

Uchar*data=outputimager.ptr<uchar>(i);//Get the first address of the i-th line

For(int j=0; j<colNumber; j++>)//column loop

{

//[Start processing each pixel]

Data[j]=data[j]/div*div+div/2;

//[Processing ends]

}//End of line processing

}

S1212, judging whether the pixel value is greater than the preset pixel value;

S1213. When the pixel value is greater than the preset pixel value, reduce the pixel value of the tracking area to the preset pixel value;

After acquiring the pixel value of the tracking area, the acquired pixel value is compared with the preset pixel value. Preferably, the preset pixel value can be set to 30*30. When it is larger than 30*30, reduce the pixel value of the tracking area to 30*30.

S1214. When the pixel value is less than or equal to the preset pixel value, retain the pixel value of the tracking area.

By reducing the pixel value of the tracking area, on the one hand, the interference of other factors in the tracking area can be eliminated, so that the characteristics of the target to be tracked can be obtained, and the accuracy of target tracking can be improved. speed.

An embodiment of the present invention provides a method for extracting features of a target to be tracked from a reduced tracking area. As shown in FIG. 5 , FIG. 5 is a method for extracting a target to be tracked from a reduced tracking area provided by an embodiment of the present invention. Schematic diagram of the basic flow of the method of characterization.

Specifically, as shown in Figure 5, step S1200 includes the following steps:

S1221, acquiring a horizontal gradient image and a vertical gradient image of the tracking area;

First, the images of the tracking area are normalized. That is, convert it into a grayscale image, and use the Gamma correction method to standardize the color space of the image in the tracking area. The purpose is to adjust the contrast of the image, reduce the influence of local shadows and illumination changes in the image, and suppress the interference of noise.

Calculate the horizontal gradient image and vertical gradient image of the image of the corrected tracking area. And the gradient direction value of each pixel position is calculated through the calculated horizontal gradient image and vertical gradient image, so that not only can the contour, silhouette and texture information be captured, but also the influence of lighting can be further weakened.

Suppose G _x (x, y) is a horizontal gradient image and G _y (x, y) is a vertical gradient image.

Then G _x (x,y)=H(x+1,y)-H(x-1,y);

G _y (x,y)=H(x,y+1)-H(x,y-1);

Among them, G _x (x, y), G _y (x, y), H (x, y) represent the horizontal gradient, vertical gradient and pixel value at the pixel point (x, y) of the input image, respectively.

S1222, obtain a gradient magnitude image matrix according to the horizontal gradient image and the vertical gradient image, and calculate the gradient magnitude integral map of each image in the gradient magnitude image matrix;

Use the cartToPolar function to calculate the angle matrix image angleMat and the gradient magnitude matrix image magnMat corresponding to the above-mentioned horizontal gradient image and vertical gradient image, and normalize the pixel intensity values in the angle matrix image to the intensity range of [0,9) these 9 range, each range represents a bin of the histogram of oriented gradients (HOG). Using the angle as an index, the gradient magnitude image matrix is divided into 9 gradient magnitude image matrices according to 9 directions, and according to the 9 angles, the gradient magnitude image matrix corresponding to each angle is used, and the integral function integral in OpenCv is used. The integral images corresponding to the 9 images are calculated respectively.

S1223: Perform an addition operation on the gradient magnitude integral map of each image to obtain the directional gradient histogram feature of the target to be tracked.

The cachHOGCell function is used to add the gradient magnitude integral map of each image to obtain the directional gradient histogram feature of each image, and the directional gradient histogram feature of each image is finalized to obtain the directional gradient histogram of the target to be tracked. graph features.

An embodiment of the present invention provides a method for tracking features by using a preset target tracking algorithm. As shown in FIG. 6 , FIG. 6 is a method for tracking features by using a preset target tracking algorithm provided by an embodiment of the present invention. Schematic diagram of the basic flow of the method.

Specifically, as shown in FIG. 6, step S1300 includes the following steps:

S1310, using the feature as a tracking target to track in the first video frame group through a correlation filtering algorithm;

The first video frame group is a preset number of video frames extracted from the video to be tracked. First, input the first frame of the first video frame group into the terminal or server, extract features from the area where the target to be tracked is located, and perform training to obtain a correlation filter. After that, for other video frames in the first video frame group, first crop the previously predicted area, perform feature extraction, perform FFT (Fourier) transformation on these features, and then multiply with the correlation filter, and the obtained result is done as IFFT (inverse Fourier) transformation, the area with the largest response point in other video frames in the first video frame group is the position to be tracked.

S1320, obtain the feature of the target to be tracked from the first frame in the second video frame group;

S1330. Use the acquired feature to perform tracking in the second video frame group, where the first video frame group is continuous with the second video frame group.

The second video frame group is continuous with the first video frame group and includes a plurality of video frames, wherein the second video frame group and the first video frame group have the same number of frames. In this embodiment, in order to improve the tracking accuracy, in the tracking process, after the tracking of the first video frame group is completed, the features of the target to be tracked are extracted from the first frame in the second video frame group again, and the The feature retrains the correlation filter to update the correlation filter for predicting the target to be tracked in subsequent video frames.

In some embodiments, a third video frame group, a fourth video frame group, . . . are also included, that is, the feature of the target to be tracked is extracted with a preset number of video frames as a period, and the correlation filter is updated.

In order to solve the above technical problem, the embodiments of the present invention further provide a target tracking device. Please refer to FIG. 7 for details. FIG. 7 is a block diagram of the basic structure of the target tracking apparatus according to this embodiment.

As shown in FIG. 7 , a target tracking apparatus includes: an acquisition module 2100 , a processing module 2200 and an execution module 2300 . The acquisition module 2100 is used to acquire the tracking area of the target to be tracked; the processing module 2200 is used to reduce the pixel value in the tracking area to a preset pixel value, and extract the target to be tracked from the reduced tracking area The feature; the execution module 2300 is used to track the feature through a preset target tracking algorithm.

The above-mentioned target tracking device reduces the pixel value in the tracking area to a preset pixel value, and extracts the target to be tracked from the reduced tracking area. In this method, the pixel value of the tracking area is reduced to extract features, which can avoid the interference of other factors. , to accurately and quickly extract the features of the target to be tracked, thereby improving the tracking speed.

In some implementations, the acquisition module includes: a first acquisition sub-module for extracting video frames from videos that need to be processed for target tracking; a second acquisition sub-module for acquiring the video frames from the video frames The frame of the target to be tracked; the third acquisition sub-module is configured to acquire the motion speed of the target to be tracked in the video frame, and determine the tracking area of the target to be tracked according to the motion speed.

In some embodiments, the third acquisition sub-module includes: a first processing sub-module for determining a speed range within which the motion speed of the target to be tracked conforms; a second processing sub-module for Find the magnification corresponding to the speed range in the table; the first execution sub-module is used to take the target to be tracked as the center, amplify the boundary according to the magnification, and use the magnified area as the tracking area.

In some embodiments, the processing module includes: a fourth acquisition sub-module for acquiring the current pixel value of the tracking area; a third processing sub-module for judging whether the pixel value is greater than a preset pixel value; The second execution sub-module is configured to reduce the pixel value of the tracking area to the preset pixel value when the pixel value is greater than the preset pixel value.

In some embodiments, the processing module includes: a fifth acquisition sub-module for acquiring a horizontal gradient image and a vertical gradient image of the tracking area; a fourth processing sub-module for acquiring the horizontal gradient image and the The vertical gradient image is described to obtain the gradient magnitude image matrix, and the gradient magnitude integral map of each image in the gradient magnitude image matrix is calculated; the third execution sub-module is used to add the gradient magnitude integral map of each image. The directional gradient histogram feature of the target to be tracked is obtained.

In some embodiments, the execution module includes: a fifth processing sub-module, configured to use the feature as a tracking target to track in the first video frame group through a correlation filtering algorithm; a sixth acquisition sub-module, configured to obtain data from The feature of the target to be tracked is acquired from the first frame in the second video frame group; the fourth execution sub-module is used for tracking in the second video frame group with the acquired feature, wherein the first video The frame group is contiguous with the second video frame group.

In some embodiments, the method further includes: a sixth processing sub-module, configured to retain the pixel value of the tracking area when the pixel value is smaller than a preset pixel value.

To solve the above technical problems, the embodiments of the present invention further provide computer equipment. For details, please refer to FIG. 8 , which is a block diagram of a basic structure of a computer device according to this embodiment.

As shown in FIG. 8 , a schematic diagram of the internal structure of the computer equipment. As shown in FIG. 8, the computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected through a system bus. Wherein, the non-volatile storage medium of the computer device stores an operating system, a database and computer-readable instructions, and the database may store a sequence of control information. When the computer-readable instructions are executed by the processor, the processor can realize a A target tracking method. The processor of the computer equipment is used to provide computing and control capabilities and support the operation of the entire computer equipment. Computer readable instructions may be stored in the memory of the computer device, and when executed by the processor, the computer readable instructions may cause the processor to perform a target tracking method. The network interface of the computer equipment is used for communication with the terminal connection. Those skilled in the art can understand that the structure shown in FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In this embodiment, the processor is used to execute the specific content of the acquisition module 2100 , the processing module 2200 and the execution module 2300 in FIG. 7 , and the memory stores program codes and various types of data required to execute the above modules. The network interface is used for data transmission between user terminals or servers. The memory in this embodiment stores the program codes and data required to execute all the submodules in the target tracking method, and the server can call the program codes and data of the server to execute the functions of all the submodules.

The computer equipment reduces the pixel value in the tracking area to a preset pixel value, and extracts the target to be tracked from the reduced tracking area. In this method, the pixel value of the tracking area is reduced to extract features, which can avoid the interference of other factors and accurately. , Quickly extract the features of the target to be tracked, thereby improving the tracking speed.

The present invention further provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause one or more processors to execute the target tracking method described in any of the foregoing embodiments A step of.

Those of ordinary skill in the art can understand that the realization of all or part of the processes in the methods of the above embodiments can be accomplished by instructing relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the program is During execution, it may include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM).

It should be understood that although the various steps in the flowchart of the accompanying drawings are sequentially shown in the order indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order and may be performed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution sequence is also It does not have to be performed sequentially, but may be performed alternately or alternately with other steps or at least a portion of sub-steps or stages of other steps.

The above are only some embodiments of the present invention. It should be pointed out that for those skilled in the art, without departing from the principles of the present invention, several improvements and modifications can be made. It should be regarded as the protection scope of the present invention.

Claims (10)

1. a target tracking method, is characterized in that, comprises the following steps: Obtain the tracking area of the target to be tracked; reducing the pixel value in the tracking area to a preset pixel value, and extracting the feature of the target to be tracked from the reduced tracking area; The features are tracked by a preset target tracking algorithm. 2. The target tracking method according to claim 1, wherein the acquiring the tracking area of the target to be tracked comprises: Extract video frames from videos that need to be tracked; Obtain the frame of the target to be tracked from the video frame; The movement speed of the target to be tracked in the video frame is acquired, and the tracking area of the target to be tracked is determined according to the movement speed. 3. The target tracking method according to claim 2, wherein the determining the tracking area of the target to be tracked according to the motion speed comprises: Determine the speed range that the motion speed of the target to be tracked conforms to; Find the magnification corresponding to the speed range in the preset information table; Taking the target to be tracked as the center, the boundary is enlarged according to the magnification factor, and the enlarged area is used as the tracking area. 4. The target tracking method according to claim 1, wherein the reducing the pixel value in the tracking area to a preset pixel value comprises: obtain the current pixel value of the tracking area; determining whether the pixel value is greater than a preset pixel value; When the pixel value is greater than a preset pixel value, the pixel value of the tracking area is reduced to the preset pixel value. 5. The target tracking method according to claim 1, wherein the feature of extracting the target to be tracked from the reduced tracking area comprises: obtaining a horizontal gradient image and a vertical gradient image of the tracking area; Obtain a gradient magnitude image matrix according to the horizontal gradient image and the vertical gradient image, and calculate the gradient magnitude integral map of each image in the gradient magnitude image matrix; The gradient magnitude integral map of each image is added to obtain the directional gradient histogram feature of the target to be tracked. 6. The target tracking method according to claim 1, wherein, the feature is tracked by a preset target tracking algorithm, comprising: Using the feature as a tracking target to track in the first video frame group through a correlation filtering algorithm; Obtain the feature of the target to be tracked from the first frame in the second video frame group; Tracking is performed in the second video frame group with the acquired feature, wherein the first video frame group is continuous with the second video frame group. 7. The target tracking method according to claim 1, wherein after judging whether the pixel value is greater than a preset pixel value, the method further comprises: When the pixel value is smaller than a preset pixel value, the pixel value of the tracking area is retained. 8. A target tracking device, comprising: The acquisition module is used to acquire the tracking area of the target to be tracked; a processing module for reducing the pixel value in the tracking area to a preset pixel value, and extracting the feature of the target to be tracked from the reduced tracking area; The execution module is used for tracking the feature through a preset target tracking algorithm. 9. A computer device comprising a memory and a processor, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the processor is caused to perform as claimed in claims 1 to 7 The steps of the target tracking method of any one of claims. 10. A storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform any one of claims 1 to 7 The steps of the target tracking method.

Images