CN115049662A - Sprayer flow control method based on image processing - Google Patents
Sprayer flow control method based on image processing Download PDFInfo
- Publication number
- CN115049662A CN115049662A CN202210976979.0A CN202210976979A CN115049662A CN 115049662 A CN115049662 A CN 115049662A CN 202210976979 A CN202210976979 A CN 202210976979A CN 115049662 A CN115049662 A CN 115049662A
- Authority
- CN
- China
- Prior art keywords
- image
- dust
- layer
- sprayer
- flow control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 239000000428 dust Substances 0.000 claims abstract description 267
- 238000005507 spraying Methods 0.000 claims abstract description 16
- 230000007613 environmental effect Effects 0.000 claims abstract description 10
- 238000002347 injection Methods 0.000 claims description 25
- 239000007924 injection Substances 0.000 claims description 25
- 150000001875 compounds Chemical class 0.000 claims description 21
- 239000007921 spray Substances 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 239000007788 liquid Substances 0.000 description 4
- 239000002245 particle Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000002834 transmittance Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Application Of Or Painting With Fluid Materials (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a sprayer flow control method based on image processing, which comprises the following steps: acquiring an environmental image to be detected after a building site entrance and exit passes through a vehicle and a dust image in the environmental image, performing image enhancement on the dust image to obtain an enhanced image, and acquiring a definition index of the enhanced image; layering the enhanced image to obtain a plurality of layers of dust areas, and calculating a dust concentration parameter of each layer of dust area; the method comprises the steps of calculating the weight value of the dust concentration parameter of each layer of dust area, calculating the comprehensive dust concentration parameter of the enhanced image, calculating the flow control parameter of the spraying machine according to the comprehensive dust concentration parameter of the enhanced image and the definition index, calculating the target spraying flow value according to the flow control parameter and the spraying flow value under the maximum power of the spraying machine, and adjusting the spraying flow of the spraying machine.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a sprayer flow control method based on image processing.
Background
The sprayer is a machine for dispersing liquid into fog form, and is formed from liquid storage barrel, filter screen, connecting head, suction device (small electric pump), connecting pipe, spray pipe and spray head which are successively connected and communicated, the suction device is electrically connected with battery by means of switch, the battery is mounted in the battery box and mounted in the bottom portion of the liquid storage barrel, and the liquid storage barrel can be made into a recessed groove for holding battery.
The spraying machine is widely applied to general industrial equipment, medical equipment, chemical equipment, agriculture (lawns and gardens), touring vehicles, special vehicles, ships, beverages, vehicle cleaning, carpet cleaning, ground cleaning, water purification and water treatment equipment.
Because the frequent raise dust that makes building site's access & exit of vehicle of building site is many, the suspended particles are great, thereby cause great environmental pollution, the event imports and exports at building site that the vehicle is come in and go out frequent region and carry out the dust fall as dust collecting equipment with the sprayer more, at the dust fall in-process, because, the variation in size through the vehicle, the vehicle is different through the dust concentration who brings, the event utilizes the unchangeable sprayer of injection quantity to carry out the dust fall, dust concentration is hour, can cause the waste of the energy, when dust concentration is big, again, be not enough quick dust fall, the event needs to be according to dust concentration to sprayer flow accurate control.
Although can adopt the dust sensor to detect dust concentration among the prior art, when examining, need arrange a plurality of sensors and just can detect the dust concentration of its detection range to the influence of wind is great, blows the raise dust to the one side that does not have the sensor when wind, just can't detect the concentration of dust, consequently, the dust concentration that utilizes the sensor to detect is inaccurate, and the inaccurate precision that also can influence the control of sprayer flow of dust concentration.
Therefore, it is desirable to provide a method for controlling the flow rate of a spraying machine based on image processing to solve the above problems.
Disclosure of Invention
The invention provides a sprayer flow control method based on image processing, which aims to solve the existing problems.
The invention relates to a sprayer flow control method based on image processing, which adopts the following technical scheme: the method comprises the following steps:
acquiring an environmental image to be detected after a building site entrance and exit passes through a vehicle, and acquiring a dust image in the environmental image to be detected;
carrying out image enhancement on the dust image to obtain an enhanced image, and obtaining a definition index of the enhanced image;
layering the enhanced image to obtain each layer of dust area formed by pixel points corresponding to each gray value, calculating the density of the pixel points in each layer of dust area, and calculating the dust concentration parameter of each layer of dust area according to the density of the pixel points in each layer of dust area, the number of the pixel points and the total number of the pixel points of the enhanced image;
normalizing the dust concentration parameter corresponding to each layer of dust area, and acquiring the weight value of the dust concentration parameter corresponding to each layer of dust area according to the normalized dust concentration parameter corresponding to each layer of dust area;
calculating a comprehensive dust concentration parameter of the enhanced image according to the dust concentration parameter corresponding to each layer of dust area and the weight value of the concentration parameter;
calculating a flow control parameter of the sprayer according to the definition index of the enhanced image and the comprehensive concentration parameter of the pixel points in the enhanced image, calculating a target injection flow value according to the flow control parameter of the sprayer and the injection flow value under the maximum power of the sprayer, and adjusting the injection flow of the sprayer according to the target injection flow value.
Preferably, the step of acquiring the dust image in the environmental image to be detected includes:
acquiring an environment image when a building site entrance and exit is free of dust and recording the environment image as a first template image;
and acquiring a difference image of the image to be detected and the first template image, wherein the difference image is a dust image in the image of the environment to be detected.
Preferably, the step of obtaining a difference image between the image to be detected and the template image includes:
carrying out difference on an image to be detected and a first template image to obtain a first difference image;
carrying out difference on the first template image and the image to be detected to obtain a second difference image;
and respectively adding the first differential image and the second differential image by taking one half as the weight of the first differential image and the second differential image to obtain a differential image of the image to be detected and the template image.
Preferably, the method further comprises the following steps:
acquiring a second template image only containing a dust area;
calculating structural similarity of the dust area in the differential image and the second template image;
and determining a dust area in the differential image according to the structural similarity, and recording the dust area as a dust image.
Preferably, the step of calculating the density of pixels in each layer of dust region comprises:
calculating Euclidean distances between each pixel point and all other pixel points in each layer of dust area;
calculating the average Euclidean distance of all Euclidean distances corresponding to each layer of dust area;
and taking the average Euclidean distance as the density of the pixel points in the dust region of the layer.
Preferably, the step of calculating the dust concentration parameter for each layer of dust area comprises:
acquiring a gray level histogram of the enhanced image;
acquiring the frequency of each pixel value in the corresponding enhanced image according to the gray level histogram;
and taking the product of the density of the pixel points in each layer of dust area and the frequency of the corresponding pixel values in the layer of dust area as the dust concentration parameter of the corresponding layer of dust area.
Preferably, the formula for calculating the weight value of the dust concentration parameter corresponding to each layer of dust area is as follows:
in the formula (I), the compound is shown in the specification,
is shown as
A weight value of a dust concentration parameter of the layer dust area;
Preferably, the formula for calculating the integrated dust concentration parameter of the enhanced image is:
in the formula (I), the compound is shown in the specification,
a comprehensive dust concentration parameter representing the enhanced image;
Preferably, the formula for calculating the flow control parameter of the sprayer according to the definition index of the enhanced image and the comprehensive concentration parameter of the pixel points in the enhanced image is as follows:
in the formula (I), the compound is shown in the specification,
a flow control parameter indicative of the sprayer;
Preferably, the formula of the target injection flow value is calculated according to the flow control parameter of the spraying machine and the injection flow value at the maximum power of the spraying machine:
in the formula (I), the compound is shown in the specification,
representing objectsAn injection flow value;
The beneficial effects of the invention are: the invention relates to a sprayer flow control method based on image processing, which comprises the steps of processing an environment image of a building site through an image processing technology to obtain a dust image, enhancing the dust image to obtain an enhanced image, layering the enhanced image according to gray values of pixel points to obtain multilayer dust areas, then obtaining concentration parameters of the pixel points in each layer of dust area, determining the weight value of the concentration parameters of the pixel points in each layer of dust area according to the concentration parameters corresponding to each layer of dust area, determining the comprehensive concentration parameters of the enhanced image according to the weight value and the corresponding concentration parameters, determining the flow control parameters of a sprayer by using the comprehensive concentration parameters and the definition index of the enhanced image, determining a target spray flow value according to the flow control parameters of the sprayer and the spray flow value under the maximum power of the sprayer, adjusting the spray flow value of the sprayer according to the target spray flow value, thereby realize the accuracy and control the sprayer flow, and then under the prerequisite of avoiding the water waste, satisfy the dust fall effect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of the general steps of an embodiment of the method for controlling the flow of a sprayer based on image processing.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the embodiment of the method for controlling the flow of the spraying machine based on the image processing, the application scenario of the embodiment is dust fall at the entrance and exit of the building site, because the entrance and exit of the building site are areas where vehicles frequently enter and exit, and when a large soil-pulling vehicle and a material-pulling vehicle can excite large flying dust to affect the environment, a spraying machine needs to be arranged at the entrance and exit, and the spraying machine sprays atomized small water drops to be attached to the surface of suspended dust particles, so that the dust particles sink under the action of gravity, and the purpose of dust removal is achieved, as shown in fig. 1, the method comprises the following steps:
and S1, acquiring an environmental image to be detected after the building site entrance and exit passes through the vehicle, and acquiring a dust image in the environmental image to be detected.
Specifically, a high-definition camera is arranged at an entrance and an exit of a building site, the camera is used for collecting an image without raised dust and with good air quality as a first template image, then the camera can automatically identify a vehicle when the vehicle passes through the field of view of the camera, then a to-be-detected environment image with the same field of view is collected after the vehicle passes through the camera, a difference image between the to-be-detected image and the first template image is obtained, the difference image is a dust image in the to-be-detected environment image, the idea of a background difference method is to detect a moving object by comparing a current frame in an image sequence with a background reference model, the detection of dust by using the image difference method is actually to detect pixel points of the image, different areas of the pixel points are obtained by detecting gray level differences of the pixel points in each pixel point and the first template image, and the image difference is a known technology, no further description is given here, and therefore, the step of obtaining the difference image between the image to be detected and the first template image includes: the method comprises the following steps of carrying out difference on an image to be detected and a first template image to obtain a first difference image, wherein an expression of the first difference image is obtained:
in the formula (I), the compound is shown in the specification,
representing coordinates in the template image as
The gray value of the pixel point;
and the template image and the image to be detected are differentiated to obtain an expression of a second differential image:
in the formula (I), the compound is shown in the specification,
representing coordinates in the template image as
The gray value of the pixel point;
because of the influence of image quality and the influence of factors with small difference between the dust pixel points and the background pixel points, the dust area in the image to be detected is determined by only differentiating the image to be detected and the first template image to obtain a first differential image, which is not accurate, so that the two dust areas are obtained by differentiating the image to be detected and the first template image, differentiating the first template image and the image to be detected and obtaining a more accurate dust area, and then setting weights for the two dust areas, so that the first differential image and the second differential image are added by taking half as the weights of the first differential image and the second differential image respectively to obtain the differential image of the image to be detected and the template image, wherein the expression of the differential image of the image to be detected and the template image is obtained:
in the formula (I), the compound is shown in the specification,
representing the coordinate in the first difference image obtained by the difference between the image to be detected and the template image as
The gray value of the pixel point;
0.5 represents the weight of the pixel points in the first differential image and the second differential image;
specifically, the dust region is obtained by an image difference method on the basis of step S1, because the dust is in an unordered escape state, the edge of the dust is irregular, and the degree of the irregularity is large, because pedestrians often pass through the entrance and exit of the building site, a person may appear in the acquired image to be detected, when the image difference calculation is performed on the image to be detected in which the person appears, the person is brought into the range of the dust, so that the judgment on the dust region is affected, therefore, in order to prevent the person appearing in the acquired image to be detected from affecting the acquisition of the dust image, on the basis of step S1, a second template image only including the dust region is further obtained; calculating structural similarity of the dust areas in the differential image and the second template image; determining a dust region in the difference image according to the structural similarity, and marking the dust region as a dust image, wherein a formula for calculating the structural similarity between the difference image and the dust region in the second template image is a prior art formula:
in the formula (I), the compound is shown in the specification,
representing differential images
With the second template image
Structural similarity of dust regions in (a);
when in use
When the difference image is not similar to the second template image in structure
And then, explaining that the differential image is similar to the second template image in structure, wherein the corresponding area in the differential image is a dust area, and the dust area is divided to obtain a gray image only containing the dust area.
And S2, carrying out image enhancement on the dust image to obtain an enhanced image, and acquiring the definition index of the enhanced image.
Specifically, the range of the change of the gray level value of the dust is small, so that the obtained dust image needs to be enhanced, some dust pixel points with small concentration in the gray level image can be lost due to the particularity of the dust image in the image enhancement process, but the dust concentration calculation of an area with high dust concentration is not influenced, specifically, the image is enhanced by histogram equalization to obtain an enhanced image, and the histogram equalization is adoptedFor the prior art, it is not repeated here, and in order to measure the enhancement effect of the image quality of the enhanced image, the sharpness index is used to measure the enhancement effect of the enhanced image, if the enhanced image is
A size of
Then the expression of the sharpness index is:
in the formula (I), the compound is shown in the specification,
expressing the definition index of the enhanced image, wherein the definition index calculation formula is a prior art formula;
S3, the larger the dust concentration is, the smaller the transmittance of the background is, and the larger the concentration is, the larger the gray value of the gray image is; the smaller the dust concentration is, the larger the transmittance of the background is, the smaller the gray value of the gray image is in the region with the smaller concentration is, so that the dust concentration is described according to the gray change of the image and the density of pixels corresponding to the same gray value, namely, the enhanced image is layered to obtain each layer of dust region formed by the pixels corresponding to each gray value, the density of the pixels in each layer of dust region is calculated, and the dust concentration parameter of each layer of dust region is calculated according to the density of the pixels in each layer of dust region, the number of the pixels and the total number of the pixels of the enhanced image.
When the enhanced image is layered to obtain each layer of dust area formed by pixel points corresponding to each gray value: because the dust is in a three-dimensional space, the collected dust image is a two-dimensional image, so that when the dust image is analyzed, the dust in the enhanced image corresponding to the dust image can be regarded as a process of overlapping layer by layer, layering is carried out according to the gray value, and the dust concentration in different areas can be well shown through the image, so that the enhanced image is layered according to the gray value of the pixel points in the enhanced image, specifically, the pixel points with the same gray size in the enhanced image are classified into the same class through a clustering algorithm, and the same class of pixel points form a layer of corresponding dust area, thereby obtaining a multilayer dust area;
specifically, when calculating the density of pixel in every layer of dust region, at first we describe the element density with the distance between the pixel in a certain layer of dust region, the grey scale value of all pixel in same layer of dust region is the same, distance between the pixel in same layer of dust region is more near, then it is denser to explain the pixel of this kind of grey scale value, then the pixel density of dust in this layer of dust region is big more, and when the regional number of piles of dust is many more, then the pile volume of pixel is more, concentration is big more, calculate the density step of pixel in every layer of dust region includes: calculating Euclidean distances between each pixel point and all other pixel points in each layer of dust area; calculating the average Euclidean distance of all Euclidean distances corresponding to each layer of dust area; taking the average Euclidean distance as the density of the pixels in the layer of dust area, wherein the formula for calculating the Euclidean distance between each pixel in each layer of dust area and all other pixels is as follows:
in the formula (I), the compound is shown in the specification,
is shown as
Pixels in the dust region
Euclidean distances from other pixel points;
（
) Is shown as
Pixels in the dust region
The coordinates of (a);
（
) Is shown as
Coordinates of other pixel points in the layer dust area;
wherein, the formula for calculating the average Euclidean distance of all Euclidean distances corresponding to each layer of dust area is as follows:
in the formula (I), the compound is shown in the specification,
is shown as
Taking the average Euclidean distance corresponding to each layer of dust area as the density of the pixels of the layer of dust area, namely the density of the dust pixels;
specifically, the step of calculating the dust concentration parameter of each layer of dust area includes: acquiring a gray level histogram of the enhanced image;
acquiring the frequency of each pixel value in the corresponding enhanced image according to the gray level histogram; taking the product of the density of the pixel points in each layer of dust area and the frequency of the corresponding pixel value in the layer of dust area as the dust concentration parameter of the corresponding layer of dust area, in this embodiment, the formula for calculating the dust concentration parameter of each layer of dust area is:
in the formula (I), the compound is shown in the specification,
is shown as
Dust-layer area pairThe corresponding mean euclidean distance;
S4, because the dust area with the maximum concentration has the largest influence on the environment, when the flow of the spraying machine is controlled according to the dust concentration, the attention of the dust area with the maximum concentration should be larger, so that the dust concentration parameter corresponding to each layer of dust area is normalized, and the weight value of the dust concentration parameter corresponding to each layer of dust area is obtained according to the normalized dust concentration parameter corresponding to each layer of dust area;
calculating a formula of dust concentration parameters corresponding to each layer of normalized dust area:
in the formula (I), the compound is shown in the specification,
is shown as
Dust concentration parameters of the layer dust area are normalized;
wherein, the formula of the weighted value of the dust concentration parameter of each layer of dust area is calculated as follows:
in the formula (I), the compound is shown in the specification,
is shown as
A weight value of a dust concentration parameter of the layer dust area;
S5, calculating a comprehensive dust concentration parameter of the enhanced image according to the dust concentration parameter corresponding to each layer of dust area and the weight value of the concentration parameter, specifically, calculating a formula of the comprehensive dust concentration parameter of the enhanced image:
in the formula (I), the compound is shown in the specification,
a comprehensive dust concentration parameter representing the enhanced image;
S6, calculating a flow control parameter of the sprayer according to the definition index of the enhanced image and the comprehensive concentration parameter of the pixel points in the enhanced image, calculating a target injection flow value according to the flow control parameter of the sprayer and the injection flow value under the maximum power of the sprayer, adjusting the injection flow of the sprayer according to the target injection flow value, and specifically adjusting the current injection flow value of the sprayer to the target injection flow value according to the flow difference between the target injection flow value and the current injection flow value.
Specifically, a formula for calculating the flow control parameter of the sprayer according to the definition index of the enhanced image and the comprehensive concentration parameter of the pixel points in the enhanced image is as follows:
in the formula (I), the compound is shown in the specification,
a flow control parameter indicative of the sprayer;
in this embodiment, a hand-propelled high-power sprayer is taken as an example, the sprayer adopts a four-stroke engine, the pressure is 0-30BAR, the flow rate is 12L/min, the range is greater than 15m, five spray heads are provided, the average spray particle size is 60-100um, and the sprayer can be used for columnar, cloud and fan-shaped spraying, wherein a formula of a target spray flow value is calculated according to a flow control parameter of the sprayer and a spray flow value under the maximum power of the sprayer:
in the formula (I), the compound is shown in the specification,
indicating a target injection flow rate value;
In summary, the present invention provides an image processing-based sprayer flow control method, which includes processing an environment image of a building site by an image processing technology to obtain a dust image, enhancing the dust image to obtain an enhanced image, layering the enhanced image according to gray values of pixel points to obtain a multi-layer dust area, then obtaining concentration parameters of the pixel points in each layer of the dust area, determining a weight value of the concentration parameters of the pixel points in each layer of the dust area according to the concentration parameters corresponding to each layer of the dust area, determining an enhanced image comprehensive concentration parameter according to the weight value and the corresponding concentration parameter, thereby determining a flow control parameter of a sprayer by using the comprehensive concentration parameter and a sharpness index of the enhanced image, determining a target spray flow value according to the flow control parameter of the sprayer and a spray value at the maximum power of the sprayer, adjusting the spray flow value of the sprayer according to the target spray flow value, thereby realize the accuracy and control the sprayer flow, and then under the prerequisite of avoiding the water waste, satisfy the dust fall effect.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. The spraying machine flow control method based on image processing is characterized by comprising the following steps:
acquiring an environmental image to be detected after a building site entrance and exit passes through a vehicle, and acquiring a dust image in the environmental image to be detected;
carrying out image enhancement on the dust image to obtain an enhanced image, and obtaining a definition index of the enhanced image;
layering the enhanced image to obtain each layer of dust area formed by pixel points corresponding to each gray value, calculating the density of the pixel points in each layer of dust area, and calculating the dust concentration parameter of each layer of dust area according to the density of the pixel points in each layer of dust area, the number of the pixel points and the total number of the pixel points of the enhanced image;
normalizing the dust concentration parameter corresponding to each layer of dust area, and acquiring the weight value of the dust concentration parameter corresponding to each layer of dust area according to the normalized dust concentration parameter corresponding to each layer of dust area;
calculating a comprehensive dust concentration parameter of the enhanced image according to the dust concentration parameter corresponding to each layer of dust area and the weight value of the concentration parameter;
calculating a flow control parameter of the sprayer according to the definition index of the enhanced image and the comprehensive concentration parameter of the pixel points in the enhanced image, calculating a target injection flow value according to the flow control parameter of the sprayer and the injection flow value under the maximum power of the sprayer, and adjusting the injection flow of the sprayer according to the target injection flow value.
2. The image processing-based sprayer flow control method according to claim 1, wherein the step of acquiring the dust image in the environmental image to be detected comprises:
acquiring an environment image when a building site entrance and exit is free of dust and recording the environment image as a first template image;
and acquiring a difference image of the image to be detected and the first template image, wherein the difference image is a dust image in the image of the environment to be detected.
3. The image processing-based sprayer flow control method according to claim 2, wherein the step of obtaining a difference image between the image to be detected and the template image comprises:
carrying out difference on an image to be detected and a first template image to obtain a first difference image;
carrying out difference on the first template image and the image to be detected to obtain a second difference image;
and respectively adding the first differential image and the second differential image by taking one half as the weight of the first differential image and the second differential image to obtain a differential image of the image to be detected and the template image.
4. The image processing-based sprayer flow control method according to claim 2, further comprising:
acquiring a second template image only containing a dust area;
calculating structural similarity of the dust areas in the differential image and the second template image;
and determining a dust area in the differential image according to the structural similarity, and recording the dust area as a dust image.
5. The image processing-based sprayer flow control method according to claim 1, wherein the step of calculating the density of pixel points in each dust region comprises:
calculating Euclidean distances between each pixel point and all other pixel points in each layer of dust area;
calculating the average Euclidean distance of all Euclidean distances corresponding to each layer of dust area;
and taking the average Euclidean distance as the density of the pixel points in the dust region of the layer.
6. The image processing-based sprayer flow control method according to claim 1, wherein the step of calculating the dust concentration parameter for each layer of dust area comprises:
acquiring a gray level histogram of the enhanced image;
acquiring the frequency of each pixel value in the corresponding enhanced image according to the gray level histogram;
and taking the product of the density of the pixel points in each layer of dust area and the frequency of the corresponding pixel values in the layer of dust area as a dust concentration parameter of the corresponding layer of dust area.
7. The image processing-based sprayer flow control method according to claim 1, wherein the calculation formula of the weight value of the dust concentration parameter corresponding to each layer of dust area is as follows:
in the formula (I), the compound is shown in the specification,
is shown as
A weight value of a dust concentration parameter of the layer dust area;
8. The image processing-based sprayer flow control method according to claim 1, wherein the formula for calculating the comprehensive dust concentration parameter of the enhanced image is as follows:
in the formula (I), the compound is shown in the specification,
integration of presentation enhancement imagesA dust concentration parameter;
9. The image processing-based sprayer flow control method according to claim 1, wherein a formula for calculating the flow control parameter of the sprayer according to the sharpness index of the enhanced image and the comprehensive concentration parameter of the pixel points therein is as follows:
in the formula (I), the compound is shown in the specification,
a flow control parameter indicative of the sprayer;
10. The image processing-based sprayer flow control method according to claim 1, wherein the formula for calculating the target spray flow value is based on the flow control parameter of the sprayer and the spray flow value at the maximum power of the sprayer:
in the formula (I), the compound is shown in the specification,
representing a target injection flow value of the sprayer;
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210976979.0A CN115049662B (en) | 2022-08-16 | 2022-08-16 | Sprayer flow control method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210976979.0A CN115049662B (en) | 2022-08-16 | 2022-08-16 | Sprayer flow control method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115049662A true CN115049662A (en) | 2022-09-13 |
| CN115049662B CN115049662B (en) | 2022-11-08 |
Family
ID=83167626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210976979.0A Active CN115049662B (en) | 2022-08-16 | 2022-08-16 | Sprayer flow control method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115049662B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115439494A (en) * | 2022-11-08 | 2022-12-06 | 山东大拇指喷雾设备有限公司 | Spray image processing method for quality inspection of sprayer |
| CN116309437A (en) * | 2023-03-15 | 2023-06-23 | 中国铁塔股份有限公司河北省分公司 | Dust detection method, device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160089783A1 (en) * | 2014-09-30 | 2016-03-31 | Lg Electronics Inc. | Robot cleaner and control method thereof |
| US20170144097A1 (en) * | 2015-11-25 | 2017-05-25 | Xiaomi Inc. | Methods and apparatuses for detecting parameter for air purifier |
| CN107870141A (en) * | 2017-09-15 | 2018-04-03 | 孔华 | A kind of method of indoor high-acruracy survey dust concentration |
| CN108961200A (en) * | 2017-05-17 | 2018-12-07 | 深圳怡化电脑股份有限公司 | A kind of dust detection method and device |
| US20180365805A1 (en) * | 2017-06-16 | 2018-12-20 | The Boeing Company | Apparatus, system, and method for enhancing an image |
| CN110197465A (en) * | 2019-05-28 | 2019-09-03 | 深圳供电规划设计院有限公司 | A kind of foggy image enhancing algorithm |
| CN110544261A (en) * | 2019-09-04 | 2019-12-06 | 东北大学 | Blast furnace tuyere coal injection state detection method based on image processing |
| CN110852997A (en) * | 2019-10-24 | 2020-02-28 | 普联技术有限公司 | Dynamic image definition detection method and device, electronic equipment and storage medium |
| CN113327206A (en) * | 2021-06-03 | 2021-08-31 | 江苏电百达智能科技有限公司 | Image fuzzy processing method of intelligent power transmission line inspection system based on artificial intelligence |
-
2022
- 2022-08-16 CN CN202210976979.0A patent/CN115049662B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160089783A1 (en) * | 2014-09-30 | 2016-03-31 | Lg Electronics Inc. | Robot cleaner and control method thereof |
| US20170144097A1 (en) * | 2015-11-25 | 2017-05-25 | Xiaomi Inc. | Methods and apparatuses for detecting parameter for air purifier |
| CN108961200A (en) * | 2017-05-17 | 2018-12-07 | 深圳怡化电脑股份有限公司 | A kind of dust detection method and device |
| US20180365805A1 (en) * | 2017-06-16 | 2018-12-20 | The Boeing Company | Apparatus, system, and method for enhancing an image |
| CN107870141A (en) * | 2017-09-15 | 2018-04-03 | 孔华 | A kind of method of indoor high-acruracy survey dust concentration |
| CN110197465A (en) * | 2019-05-28 | 2019-09-03 | 深圳供电规划设计院有限公司 | A kind of foggy image enhancing algorithm |
| CN110544261A (en) * | 2019-09-04 | 2019-12-06 | 东北大学 | Blast furnace tuyere coal injection state detection method based on image processing |
| CN110852997A (en) * | 2019-10-24 | 2020-02-28 | 普联技术有限公司 | Dynamic image definition detection method and device, electronic equipment and storage medium |
| CN113327206A (en) * | 2021-06-03 | 2021-08-31 | 江苏电百达智能科技有限公司 | Image fuzzy processing method of intelligent power transmission line inspection system based on artificial intelligence |
Non-Patent Citations (2)
| Title |
|---|
| HICHAM TRIBAK 等: ""Dust Soiling Concentration Measurement on Solar Panels based on Image Entropy"", 《IEEE》 * |
| 薛倩等: "基于视频的飞机货舱烟雾识别去干扰方法研究", 《计算机仿真》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115439494A (en) * | 2022-11-08 | 2022-12-06 | 山东大拇指喷雾设备有限公司 | Spray image processing method for quality inspection of sprayer |
| CN116309437A (en) * | 2023-03-15 | 2023-06-23 | 中国铁塔股份有限公司河北省分公司 | Dust detection method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115049662B (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113255481B (en) | Crowd state detection method based on unmanned patrol car | |
| CN109024417B (en) | Intelligent road sweeper and road pollutant identification method and control method thereof | |
| CN115049662B (en) | Sprayer flow control method based on image processing | |
| CN109460709A (en) | The method of RTG dysopia analyte detection based on the fusion of RGB and D information | |
| CN104183127B (en) | Traffic surveillance video detection method and device | |
| CN109100741A (en) | A kind of object detection method based on 3D laser radar and image data | |
| CN104408724B (en) | Froth flotation level monitoring and operating mode's switch method and system based on depth information | |
| CN104112269B (en) | A kind of solar battery laser groove parameter detection method and system based on machine vision | |
| CN106530281B (en) | Unmanned plane image fuzzy Judgment method and system based on edge feature | |
| CN108596058A (en) | Running disorder object distance measuring method based on computer vision | |
| CN108960198A (en) | A kind of road traffic sign detection and recognition methods based on residual error SSD model | |
| CN105844621A (en) | Method for detecting quality of printed matter | |
| CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
| CN110111331A (en) | Honeycomb paper core defect inspection method based on machine vision | |
| CN104299247B (en) | A kind of video target tracking method based on adaptive measuring matrix | |
| CN107133973A (en) | A kind of ship detecting method in bridge collision prevention system | |
| CN107392929B (en) | Intelligent target detection and size measurement method based on human eye vision model | |
| CN109815856A (en) | Status indication method, system and the computer readable storage medium of target vehicle | |
| CN114764871B (en) | Urban building attribute extraction method based on airborne laser point cloud | |
| CN104899866A (en) | Intelligent infrared small target detection method | |
| CN105719283A (en) | Road surface crack image detection method based on Hessian matrix multi-scale filtering | |
| CN110633671A (en) | Bus passenger flow real-time statistical method based on depth image | |
| CN107480585A (en) | Object detection method based on DPM algorithms | |
| CN106127145A (en) | Pupil diameter and tracking | |
| CN113012195A (en) | Method for estimating river surface flow velocity based on optical flow calculation and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |