Filter screen detection method and device, computer readable storage medium and air conditioning system

Abstract

The application provides a filter screen detection method and device, a computer readable storage medium and an air conditioning system. The detection method comprises: acquiring a target image, which is an image of a filter screen to be detected; extracting a plurality of frame contour lines, which are edges of a frame contour of the filter screen to be detected in the target image; analyzing the target image by using an image warping algorithm to obtain a warping degree of the filter screen to be detected, the warping degree being used to represent a deformation degree of a grid in the filter screen to be detected; and determining that the filter screen to be detected is unqualified in a case where any one of the frame contour lines is not a straight line and / or the warping degree of the filter screen to be detected is greater than a warping degree threshold. Compared with manual measurement of deformation, the image detection greatly improves the efficiency and solves the problem of low efficiency of manual detection of whether an air conditioner filter screen is qualified in the prior art. In addition, manual detection may be inaccurate due to errors, and therefore the image detection can also improve the accuracy of detection.

Description

Technical Field

[0001] This invention relates to the field of air conditioning technology, and more specifically, to a method, apparatus, computer-readable storage medium, and air conditioning system for detecting filters. Background Technology

[0002] Air conditioner filters are crucial components of air conditioners. They absorb dust and purify the air of bacteria while protecting the evaporator. However, if the filter is improperly installed or has inherent quality problems, such as a deformed frame or a broken filter, it will lose its function, allowing dust or other contaminants to enter the evaporator and cause contamination and damage. Therefore, testing air conditioner filters is essential. Filter quality testing can identify improperly installed or defective filters, preventing discomfort and damage to the internal components of the air conditioner caused by substandard filters. Conventional air conditioner filter performance testing is usually done manually, which is time-consuming, inefficient, and lacks accuracy, hindering the development of intelligent testing methods. Summary of the Invention

[0003] The main objective of this application is to provide a method, apparatus, computer-readable storage medium, and air conditioning system for testing air filters, so as to at least solve the problem of low efficiency in the prior art of manually testing whether air conditioning filters are qualified.

[0004] To achieve the above objectives, according to one aspect of this application, a method for detecting a filter is provided, comprising: acquiring a target image, wherein the target image is an image of a filter to be detected; extracting multiple border contour lines, wherein the border contour lines are the edges of the border contours of the filter to be detected in the target image; analyzing the target image using an image distortion algorithm to obtain the distortion degree of the filter to be detected, wherein the distortion degree is used to characterize the degree of deformation of the mesh in the filter to be detected; and determining that the filter to be detected is unqualified if any of the border contour lines is not a straight line and / or the distortion degree of the filter to be detected is greater than a distortion degree threshold.

[0005] Optionally, extracting multiple border contour lines includes: sharpening the image to obtain a first processed image; smoothing the first processed image to obtain a second processed image; and binarizing the second processed image to obtain a contour map of the filter to be detected, wherein the contour map includes multiple border contour lines.

[0006] Optionally, after extracting multiple border contour lines, the method further includes: grouping the multiple border contour lines of the contour map into two border contour line groups, each border contour line group including two non-intersecting border contour lines; calculating the included angle between the two border contour lines in each border contour line group to obtain multiple border angles, each border angle corresponding one-to-one with the border contour line group; and determining that if any border angle is greater than an angle threshold, there exists a border contour line that is not a straight line.

[0007] Optionally, after extracting multiple border contour lines, the method further includes: using the Hough line detection algorithm to detect the contour map to obtain multiple straight lines; if any of the border contour lines is not one of the multiple straight lines, it is determined that there exists a border contour line that is not a straight line.

[0008] Optionally, the target image is analyzed using an image warping algorithm to obtain the warping degree of the filter to be detected, including: warping the target image using the image warping algorithm to obtain a warped image; determining the deformed portion based on the warped image, the deformed portion including multiple grids; calculating the diameter of the circumcircle of each grid in the deformed portion to obtain multiple target diameters; calculating the absolute value of the difference between each target diameter and a standard diameter to obtain multiple warping degrees, the standard diameter being the diameter of the circumcircle of one grid in the undeformed filter; and determining the largest warping degree as the warping degree of the filter to be detected.

[0009] Optionally, the image distortion algorithm is used to distort the target image to obtain a distorted image, including: setting a transformation grid in the target image, wherein the transformation grid is an N*N square grid; distorting the transformation grid to obtain a distorted grid, wherein the distorted grid is an irregularly shaped grid formed by the transformation grid being subjected to an external force; determining a projection matrix based on the distorted grid and the transformation grid, wherein the projection matrix is ​​the transformation matrix of the transformation grid projected from the distorted grid; and projecting the target image based on the projection matrix to obtain the distorted image.

[0010] Optionally, before acquiring the target image, the method further includes: acquiring an installation image, wherein the installation image is an image of the installation position of the filter to be tested in the air conditioner; identifying the filter to be tested based on the installation image to obtain an identification result; and determining that the air conditioner is unqualified if the identification result is that the installation image does not contain an image of the filter to be tested.

[0011] According to another aspect of this application, a filter detection device is provided, comprising: a first acquisition unit for acquiring a target image, the target image being an image of a filter to be detected; a first processing unit for extracting a plurality of border contour lines, the border contour lines being the edges of the border contours of the filter to be detected in the target image; an analysis unit for analyzing the target image using an image distortion algorithm to obtain the distortion degree of the filter to be detected, the distortion degree being used to characterize the degree of deformation of the mesh in the filter to be detected; and a first determination unit for determining that the filter to be detected is unqualified if any one of the border contour lines is not a straight line and / or the distortion degree of the filter to be detected is greater than a distortion degree threshold.

[0012] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0013] According to another aspect of this application, an air conditioning system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any one of the methods described.

[0014] Applying the technical solution of this application, the above-mentioned filter detection method first acquires a target image, which is an image of the filter to be detected; then, multiple border contour lines are extracted, which are the edges of the border contours of the filter to be detected in the target image; subsequently, an image distortion algorithm is used to analyze the target image to obtain the distortion degree of the filter to be detected, which is used to characterize the degree of deformation of the mesh in the filter to be detected; finally, if any of the border contour lines is not a straight line and / or the distortion degree of the filter to be detected is greater than a distortion degree threshold, the filter to be detected is determined to be unqualified. This method determines whether the border of the filter to be detected is deformed by checking whether the border contour lines in the image of the filter to be detected are straight, thereby determining whether the border is qualified; it determines the degree of deformation of the mesh in the filter to be detected by detecting the distortion degree of the filter to be detected, thereby determining whether the mesh is qualified. If the border and / or the mesh is unqualified, the filter to be detected is unqualified. Compared with manual measurement of deformation, image detection is much more efficient, solving the problem of low efficiency in manual detection of air conditioner filter quality in the prior art. In addition, manual inspection may be prone to errors, leading to inaccurate detection. Therefore, image inspection can also improve the accuracy of inspection. Attached Figure Description

[0015] Figure 1A hardware structure block diagram of a mobile terminal performing a filter detection method according to an embodiment of this application is shown;

[0016] Figure 2 A schematic flowchart of a filter detection method according to an embodiment of this application is shown;

[0017] Figure 3 A schematic diagram of a border-deformable filter provided according to an embodiment of this application is shown;

[0018] Figure 4 A schematic diagram of a mesh-deformed filter provided according to an embodiment of this application is shown;

[0019] Figure 5 A schematic diagram of a normal filter provided according to an embodiment of this application is shown;

[0020] Figure 6 A schematic flowchart of another filter detection method provided according to an embodiment of this application is shown;

[0021] Figure 7 A structural block diagram of a filter detection device provided according to an embodiment of this application is shown.

[0022] The above figures include the following reference numerals:

[0023] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0024] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] As described in the background section, the efficiency of manually inspecting air conditioner filters in the prior art is low. To solve this problem, embodiments of this application provide a filter inspection method, apparatus, computer-readable storage medium, and air conditioning system.

[0028] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0029] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a filter detection method according to an embodiment of the present invention. (See diagram for example.) Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0030] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the device information display method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] This embodiment provides a method for detecting a filter that operates on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] Figure 2 This is a flowchart of a filter detection method according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0033] Step S201: Obtain the target image, which is the image of the filter to be detected;

[0034] Specifically, a camera is installed in the air conditioner filter testing room to capture video of the air conditioner filter during the air conditioner testing process, thereby obtaining the captured filter images.

[0035] Step S202: Extract multiple border contour lines, where the border contour lines are the edges of the border contour of the filter to be detected in the target image.

[0036] Specifically, when the filter border experiences compression deformation, during image processing—specifically, when extracting and comparing the filter border outline—the opposite edges of the border may not be straight and may not be parallel, such as... Figure 3 As shown, by extracting multiple border outlines and judging whether they are deformed, it can be determined whether the border of the filter is qualified.

[0037] Step S203: The target image is analyzed using an image warping algorithm to obtain the warping degree of the filter to be detected. The warping degree is used to characterize the degree of deformation of the grid in the filter to be detected.

[0038] Specifically, during the assembly or storage of materials, if the filter mesh is under heat or tension, the mesh will deform due to external factors, resulting in visible fraying, bulging, or collapse of the filter mesh, which can be observed as distortion in the image. Figure 4 As shown, by analyzing the degree of distortion of the grid in the target image through the image distortion algorithm, it can be determined whether the grid of the filter is deformed, resulting in non-compliance.

[0039] Step S204: If any of the above-mentioned border outlines is not a straight line and / or the distortion of the above-mentioned filter screen to be tested is greater than the distortion threshold, the above-mentioned filter screen to be tested is determined to be unqualified.

[0040] Specifically, if any of the above-mentioned border outlines is not a straight line, it indicates that the border of the filter screen is deformed under stress. If the twist degree of the above-mentioned filter screen to be tested is greater than the twist degree threshold, it indicates that the mesh of the filter screen is severely twisted, both of which will lead to the filter screen being unqualified.

[0041] In the above-mentioned filter detection method, firstly, a target image is acquired, which is the image of the filter to be detected; then, multiple border contour lines are extracted, which are the edges of the border contours of the filter to be detected in the target image; next, an image distortion algorithm is used to analyze the target image to obtain the distortion degree of the filter to be detected, which is used to characterize the degree of deformation of the mesh in the filter to be detected; finally, if any of the border contour lines is not a straight line and / or the distortion degree of the filter to be detected is greater than a distortion degree threshold, the filter to be detected is determined to be unqualified. This method determines whether the border of the filter to be detected is deformed by checking whether the border contour lines in the image of the filter to be detected are straight, thereby determining whether the border is qualified; it determines the degree of deformation of the mesh in the filter to be detected by detecting the distortion degree of the filter to be detected, thereby determining whether the mesh is qualified. If the border and / or the mesh is unqualified, the filter to be detected is unqualified. Compared with manual deformation measurement, image detection is much more efficient and solves the problem of low efficiency in manual detection of air conditioner filter quality in the prior art. In addition, manual inspection may be prone to errors, leading to inaccurate detection. Therefore, image inspection can also improve the accuracy of inspection.

[0042] In an optional implementation, to extract a clear outline, step S202 includes:

[0043] Step S2021: Sharpen the above image to obtain the first processed image;

[0044] Step S2022: Smooth the first processed image to obtain the second processed image;

[0045] Step S2023: The second processed image is binarized to obtain the contour map of the filter to be detected, which includes multiple border contour lines.

[0046] Specifically, the image processing procedure first improves image quality, then selects a threshold to perform binary processing on the image of the installed air conditioner filter, and finally uses contour extraction and edge detection to extract the planar image of the air conditioner filter captured on the production line, obtaining a clear image contour map. That is, the captured image is first sharpened to compensate for the image contour, enhancing the edges and grayscale transitions to make the image clearer. Then, image smoothing can be performed to improve image quality. This involves selecting a threshold → performing image binarization → applying relevant algorithms for contour extraction (e.g., the hollowing-out internal point method) / typical differential operators for edge detection and extraction (Canny operator and Laplacian operator) → a clear image contour map.

[0047] To simplify the judgment process, in an optional implementation, after step S202, the method further includes:

[0048] Step S301: Group the multiple border outlines of the above outline diagram to obtain two border outline groups. Each border outline group includes two non-intersecting border outlines.

[0049] Step S302: Calculate the included angle between the two border outlines of each of the above border outline groups to obtain multiple border included angles, and the above border included angles correspond one-to-one with the above border outline groups.

[0050] Step S303: If any of the above-mentioned border angles is greater than the angle threshold, it is determined that there exists a border outline that is not a straight line.

[0051] Specifically, we can determine whether the left and right, as well as the top and bottom borders, are parallel based on one of the parallelism theorems (corresponding angles are equal, therefore two lines are parallel). Alternatively, if the angle between the lines is greater than a threshold angle, they can be considered non-parallel, for example, greater than 2°. Figure 3As shown, line segment JL is not parallel to KM. If the air conditioner filter is determined to be installed non-parallel, it can be identified as having gaps and thus classified as a defective product. The judgment process is simple and quick.

[0052] To simplify the judgment process, in an optional implementation, after step S202, the method further includes:

[0053] Step S401: The Hough line detection algorithm is used to detect the above contour map to obtain multiple lines;

[0054] Step S402: If any of the above-mentioned border outlines is not one of the plurality of the above-mentioned straight lines, it is determined that there exists a border outline that is not a straight line.

[0055] Specifically, the Hough line detection algorithm is used to directly detect straight lines in the contour map, which can determine whether each border contour line is a straight line. The judgment process is also simple and fast.

[0056] To facilitate the determination of whether the filter mesh is deformed, in one optional embodiment, step S203 includes:

[0057] Step S2031: The above image distortion algorithm is used to distort the target image to obtain a distorted image;

[0058] Step S2032: Determine the deformed portion based on the above distorted image, wherein the deformed portion includes a plurality of the above-mentioned grids;

[0059] Step S2033: Calculate the diameter of the circumcircle of each mesh in the above-mentioned deformed portion to obtain multiple target diameters;

[0060] Step S2034: Calculate the absolute value of the difference between each of the above target diameters and the standard diameter to obtain multiple of the above torsion degrees, where the standard diameter is the diameter of the outer circle of one of the grids in the above filter screen without deformation;

[0061] Step S2035: The maximum of the above-mentioned tortuosity is determined as the tortuosity of the above-mentioned filter screen to be tested.

[0062] Specifically, the cellsize algorithm distorts the air conditioner filter to obtain a distorted image, identifies the distorted portion from the image, and calculates the outer circle diameter z of the distorted filter mesh. Figure 3 As shown, if the value of z is greater than the grid diameter y of a normal, qualified air conditioning filter, such as... Figure 5 As shown, if the acceptable threshold is set to x, the distortion is compared with the maximum value of x. If x < |yz|, it indicates that the distortion is excessive, and the air conditioner filter corresponding to the image is determined to be unqualified; otherwise, it is determined to be qualified.

[0063] To facilitate locating the deformed portion, in an optional implementation, step S2031 includes:

[0064] Step S20311: Set a transformation grid in the target image, wherein the transformation grid is an N*N square grid;

[0065] Step S20312: Twist the above-mentioned transformed mesh to obtain a twisted mesh. The twisted mesh is an irregularly shaped mesh formed by the above-mentioned transformed mesh under external force.

[0066] Step S20313: Determine the projection matrix based on the above-mentioned twisted mesh and the above-mentioned transformed mesh. The projection matrix is ​​the transformation matrix of the above-mentioned transformed mesh obtained by projecting the above-mentioned twisted mesh.

[0067] Step S20314: Project the target image according to the projection matrix to obtain the distorted image.

[0068] Specifically, first, the captured image is set to a grid according to cell size, typically 16*16 or 32*32. Then, a projection transformation is performed on each grid, and finally all the grids are pieced together. In actual programming, a forward transformation can be used to obtain the sampled point set, and then the point set is rasterized again to obtain an image without holes. Then, the distorted parts are found from the image.

[0069] To simplify the detection process, in an optional implementation, before step S201, the method further includes:

[0070] Step S501: Obtain an installation image, which is an image of the installation position of the filter to be tested in the air conditioner;

[0071] Step S502: Identify the filter to be tested based on the installation image to obtain the identification result;

[0072] Step S503: If the above identification result is that the above installation image does not contain the above-mentioned filter to be tested, the above air conditioner is determined to be unqualified.

[0073] Specifically, the filter images acquired after shooting are processed and analyzed using image recognition methods. Whether a filter is installed can be determined by analyzing the captured images, performing image recognition on the images, and using template matching algorithms to identify and analyze the presence of the object. If no filter is identified, the air conditioner is classified as a defective product.

[0074] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the filter detection method of this application will be described in detail below with reference to specific embodiments.

[0075] This embodiment relates to a specific method for detecting filters, such as... Figure 6 As shown, it includes the following steps:

[0076] Step S1: Install a camera to acquire filter images: First, install a camera in the air conditioner filter testing chamber to capture video of the air conditioner filter during the air conditioner testing process and acquire the captured filter images.

[0077] Step S2: Filter performance (defect) inspection:

[0078] S21: Image recognition to determine whether a filter is installed.

[0079] The filter image acquired after step S1 is processed and analyzed using image recognition methods. Whether a filter is installed can be determined by analyzing the captured image, performing image recognition on the image, and using a template matching algorithm to determine the presence of the object. If no filter is identified, the air conditioner is classified as a defective product; if an installed filter is identified, the process proceeds to the next step, S22.

[0080] S22 filter frame performance test

[0081] When the filter frame experiences compression deformation, during image processing—specifically, when extracting and comparing the filter frame outline—it will show that the opposite edges of the frame are not straight and may not be parallel. Therefore, we can determine whether the filter is installed correctly based on this non-parallelism. The image processing procedure is as follows:

[0082] The image processing procedure first improves the image quality, then selects a threshold to perform binary processing on the image of the installed air conditioning filter, and finally uses contour extraction and edge detection to extract the planar image of the air conditioning filter taken by the assembly line to obtain a clear image contour map.

[0083] S221. Image processing improves image quality

[0084] First, sharpen the captured image to compensate for its outline, enhancing edges and areas of grayscale transition to make the image clearer. Then, smooth the image to improve its quality.

[0085] S222. Extract image contour map

[0086] Select a threshold → Binarize the image → Perform contour extraction on the binary image (e.g., the hollowing-out internal point method) / Typical differential operators for edge detection and extraction (Canny operator and Laplacian operator) → Clear image contour map

[0087] S223. Filter qualification is determined by the parallelism of the frame.

[0088] Based on the clear outline obtained in step S222, we can first use an image recognition algorithm to identify the image's borders. Then, we can use one of the parallelism criteria (corresponding angles are equal, two lines are parallel) to determine whether the left, right, top, and bottom borders are parallel, i.e., ... Figure 2 The center line segment JL is not parallel to KM. If it is determined that the air conditioning filter is not installed parallel, it can be considered that there are gaps in the filter installation and it is classified as a defective product. If it is determined that there are no gaps in the air conditioning filter installation, proceed to the next step S23.

[0089] Performance testing of the S23 filter mesh

[0090] Image distortion algorithms were used to analyze the captured filter images. During material assembly or storage, if the filter mesh is heated or stretched, it deforms due to external factors, resulting in visible distortions such as stringing, bulging, or collapse. This distortion can be observed in the images. Figure 2 As shown in region C.

[0091] S231 cellsize algorithm for handling air conditioner filter distortion

[0092] First, set the grid for the captured image according to the cell size, usually 16*16 or 32*32. Then, perform a projection transformation on each grid, and finally piece all the grids together. In actual programming, a forward transformation can be used to obtain the sampled point set, and then the point set can be rasterized again to obtain an image without holes. Then, find the distorted parts in the image and proceed to the next step.

[0093] S232 Twist Degree Used to Determine Filter Performance

[0094] Calculate the diameter of the circumcircle of the distorted portion of the filter mesh as z, such as... Figure 2 As shown, if the value of z is greater than the grid diameter y of a normal qualified air conditioner filter, and if the qualified threshold is set to x, then when x < |yz|, it indicates excessive distortion, and the air conditioner filter corresponding to the image is determined to be unqualified; otherwise, it is determined to be qualified.

[0095] Step S3: Performance testing and evaluation of the filter

[0096] When tests S21, S22, and S23 are all passed, it indicates that the filter meets the production standards, thus completing the performance test of the filter of this invention.

[0097] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0098] This application also provides a filter detection device. It should be noted that the filter detection device of this application can be used to execute the filter detection method provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0099] The following describes the filter detection device provided in the embodiments of this application.

[0100] Figure 7 This is a structural block diagram of a filter detection device according to an embodiment of this application. Figure 7 As shown, the device includes:

[0101] The first acquisition unit 10 is used to acquire a target image, wherein the target image is an image of the filter to be detected.

[0102] Specifically, a camera is installed in the air conditioner filter testing room to capture video of the air conditioner filter during the air conditioner testing process, thereby obtaining the captured filter images.

[0103] The first processing unit 20 is used to extract multiple border contour lines, wherein the border contour lines are the edges of the border contour of the filter to be detected in the target image.

[0104] Specifically, when the filter border experiences compression deformation, during image processing—specifically, when extracting and comparing the filter border outline—the opposite edges of the border may not be straight and may not be parallel, such as... Figure 3 As shown, by extracting multiple border outlines and judging whether they are deformed, it can be determined whether the border of the filter is qualified.

[0105] The analysis unit 30 is used to analyze the target image using an image distortion algorithm to obtain the distortion degree of the filter to be detected. The distortion degree is used to characterize the degree of deformation of the grid in the filter to be detected.

[0106] Specifically, during the assembly or storage of materials, if the filter mesh is under heat or tension, the mesh will deform due to external factors, resulting in visible fraying, bulging, or collapse of the filter mesh, which can be observed as distortion in the image. Figure 4 As shown, by analyzing the degree of distortion of the grid in the target image through the image distortion algorithm, it can be determined whether the grid of the filter is deformed, resulting in non-compliance.

[0107] The first determining unit 40 is used to determine that the filter to be tested is unqualified if any of the outline lines of the aforementioned frame are not straight and / or the distortion of the filter to be tested is greater than the distortion threshold.

[0108] Specifically, if any of the above-mentioned border outlines is not a straight line, it indicates that the border of the filter screen is deformed under stress. If the twist degree of the above-mentioned filter screen to be tested is greater than the twist degree threshold, it indicates that the mesh of the filter screen is severely twisted, both of which will lead to the filter screen being unqualified.

[0109] In the aforementioned filter detection device, a first acquisition unit acquires a target image, which is an image of the filter to be detected; a first processing unit extracts multiple border contour lines, which are the edges of the border contours of the filter to be detected in the target image; an analysis unit analyzes the target image using an image distortion algorithm to obtain the distortion degree of the filter to be detected, which is used to characterize the degree of deformation of the mesh in the filter to be detected; a first determination unit determines that the filter to be detected is unqualified if any of the border contour lines is not straight and / or the distortion degree of the filter to be detected is greater than a distortion degree threshold. This device determines whether the border of the filter to be detected is qualified by checking whether the border contour lines in the image of the filter to be detected are straight, thereby determining whether the border is qualified. It also determines whether the mesh in the filter to be detected is qualified by detecting the distortion degree of the filter to be detected, thereby determining whether the mesh is qualified. If the border and / or the mesh is unqualified, the filter to be detected is unqualified. Compared with manual deformation measurement, image detection greatly improves efficiency and solves the problem of low efficiency in manual detection of air conditioner filters in the prior art. In addition, manual inspection may be prone to errors, leading to inaccurate detection. Therefore, image inspection can also improve the accuracy of inspection.

[0110] To extract clear contour lines, in one optional implementation, the first processing unit includes:

[0111] The first processing module is used to sharpen the above image to obtain a first processed image;

[0112] The second processing module is used to smooth the first processed image to obtain the second processed image.

[0113] The third processing module is used to perform binarization processing on the second processed image to obtain the contour map of the filter to be detected, wherein the contour map includes multiple border contour lines.

[0114] Specifically, the image processing procedure first improves image quality, then selects a threshold to perform binary processing on the image of the installed air conditioner filter, and finally uses contour extraction and edge detection to extract the planar image of the air conditioner filter captured on the production line, obtaining a clear image contour map. That is, the captured image is first sharpened to compensate for the image contour, enhancing the edges and grayscale transitions to make the image clearer. Then, image smoothing can be performed to improve image quality. This involves selecting a threshold → performing image binarization → applying relevant algorithms for contour extraction (e.g., the hollowing-out internal point method) / typical differential operators for edge detection and extraction (Canny operator and Laplacian operator) → a clear image contour map.

[0115] To simplify the judgment process, in an optional embodiment, the above-mentioned device further includes:

[0116] The second processing unit is used to group the multiple border outlines of the outline map after extracting multiple border outlines to obtain two border outline groups, and one border outline group includes two non-intersecting border outlines.

[0117] The calculation unit is used to calculate the included angle between the two border outlines of each border outline group to obtain multiple border angles, and the border angles correspond one-to-one with the border outline groups.

[0118] The second determining unit is used to determine that, in any case where the included angle of the aforementioned border is greater than the angle threshold, there exists a border outline that is not a straight line.

[0119] Specifically, we can determine whether the left and right, as well as the top and bottom borders, are parallel based on one of the parallelism theorems (corresponding angles are equal, therefore two lines are parallel). Alternatively, if the angle between the lines is greater than a threshold angle, they can be considered non-parallel, for example, greater than 2°. Figure 3 As shown, line segment JL is not parallel to KM. If the air conditioner filter is determined to be installed non-parallel, it can be identified as having gaps and thus classified as a defective product. The judgment process is simple and quick.

[0120] To simplify the judgment process, in an optional embodiment, the above-mentioned device further includes:

[0121] The third processing unit is used to detect the above contour map using the Hough line detection algorithm after extracting multiple border contour lines, and obtain multiple lines.

[0122] The third determining unit is used to determine that there exists a border outline that is not a straight line when any of the border outlines is not one of the plurality of straight lines.

[0123] Specifically, the Hough line detection algorithm is used to directly detect straight lines in the contour map, which can determine whether each border contour line is a straight line. The judgment process is also simple and fast.

[0124] To facilitate the determination of whether the filter mesh is deformed, in one optional implementation, the analysis unit includes:

[0125] The fourth processing module is used to distort the target image using the image distortion algorithm described above, thereby obtaining a distorted image;

[0126] The first determining module is used to determine the deformed portion based on the above-mentioned distorted image, wherein the deformed portion includes a plurality of the above-mentioned grids;

[0127] The first calculation module is used to calculate the diameter of the circumcircle of each of the aforementioned deformed meshes, thereby obtaining multiple target diameters;

[0128] The second calculation module is used to calculate the absolute value of the difference between each of the above target diameters and the standard diameter to obtain multiple of the above-mentioned torsion degrees, wherein the above-mentioned standard diameter is the diameter of the outer circle of one of the above-mentioned meshes in the filter screen without deformation;

[0129] The second determining module is used to determine the maximum of the above-mentioned tortuosity as the tortuosity of the above-mentioned filter screen to be tested.

[0130] Specifically, the cellsize algorithm distorts the air conditioner filter to obtain a distorted image, identifies the distorted portion from the image, and calculates the outer circle diameter z of the distorted filter mesh. Figure 3 As shown, if the value of z is greater than the grid diameter y of a normal, qualified air conditioning filter, such as... Figure 5 As shown, if the acceptable threshold is set to x, the distortion is compared with the maximum value of x. If x < |yz|, it indicates that the distortion is excessive. The above deformed part includes multiple grids. Then, the air conditioner filter corresponding to the image is determined to be unqualified. Otherwise, it is determined to be qualified.

[0131] To facilitate locating the deformed portion, in one optional implementation, the fourth processing module includes:

[0132] The first processing submodule is used to set a transformation grid in the target image, wherein the transformation grid is an N*N square grid;

[0133] The second processing submodule is used to distort the above-mentioned transformed mesh to obtain a distorted mesh, wherein the distorted mesh is an irregularly shaped mesh formed by the above-mentioned transformed mesh under external force;

[0134] The determination submodule is used to determine the projection matrix based on the above-mentioned twisted mesh and the above-mentioned transformed mesh, wherein the projection matrix is ​​the transformation matrix of the above-mentioned transformed mesh obtained by projecting the above-mentioned twisted mesh;

[0135] The third processing submodule is used to project the target image according to the projection matrix to obtain the distorted image.

[0136] Specifically, first, the captured image is set to a grid according to cell size, typically 16*16 or 32*32. Then, a projection transformation is performed on each grid, and finally all the grids are pieced together. In actual programming, a forward transformation can be used to obtain the sampled point set, and then the point set is rasterized again to obtain an image without holes. Then, the distorted parts are found from the image.

[0137] To simplify the detection process, in an optional embodiment, the above-mentioned device further includes:

[0138] The second acquisition unit is used to acquire an installation image before acquiring the target image, wherein the installation image is an image of the installation position of the filter to be detected in the air conditioner;

[0139] The identification unit is used to identify the filter to be detected based on the installation image and obtain the identification result.

[0140] The fourth determining unit is used to determine that the air conditioner is unqualified if the above identification result is that the above installation image does not contain the above-mentioned filter to be tested.

[0141] Specifically, the filter images acquired after shooting are processed and analyzed using image recognition methods. Whether a filter is installed can be determined by analyzing the captured images, performing image recognition on the images, and using template matching algorithms to identify and analyze the presence of the object. If no filter is identified, the air conditioner is classified as a defective product.

[0142] The aforementioned filter detection device includes a processor and a memory. The first acquisition unit, first processing unit, analysis unit, and first determination unit are all stored as program units in the memory, and the processor executes the program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the modules may be located in different processors in any combination.

[0143] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the low efficiency of manual inspection of air conditioner filters in existing technologies.

[0144] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0145] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the filter detection method.

[0146] Specifically, the testing methods for filters include:

[0147] Step S201: Obtain the target image, which is the image of the filter to be detected;

[0148] Specifically, a camera is installed in the air conditioner filter testing room to capture video of the air conditioner filter during the air conditioner testing process, thereby obtaining the captured filter images.

[0149] Step S202: Extract multiple border contour lines, where the border contour lines are the edges of the border contour of the filter to be detected in the target image.

[0150] Specifically, when the filter border experiences compression deformation, during image processing—specifically, when extracting and comparing the filter border outline—the opposite edges of the border may not be straight and may not be parallel, such as... Figure 3 As shown, by extracting multiple border outlines and judging whether they are deformed, it can be determined whether the border of the filter is qualified.

[0151] Step S203: The target image is analyzed using an image warping algorithm to obtain the warping degree of the filter to be detected. The warping degree is used to characterize the degree of deformation of the grid in the filter to be detected.

[0152] Specifically, during the assembly or storage of materials, if the filter mesh is under heat or tension, the mesh will deform due to external factors, resulting in visible fraying, bulging, or collapse of the filter mesh, which can be observed as distortion in the image. Figure 4 As shown, by analyzing the degree of distortion of the grid in the target image through the image distortion algorithm, it can be determined whether the grid of the filter is deformed, resulting in non-compliance.

[0153] Step S204: If any of the above-mentioned border outlines is not a straight line and / or the distortion of the above-mentioned filter screen to be tested is greater than the distortion threshold, the above-mentioned filter screen to be tested is determined to be unqualified.

[0154] Specifically, if any of the above-mentioned border outlines is not a straight line, it indicates that the border of the filter screen is deformed under stress. If the twist degree of the above-mentioned filter screen to be tested is greater than the twist degree threshold, it indicates that the mesh of the filter screen is severely twisted, both of which will lead to the filter screen being unqualified.

[0155] This invention provides a processor for running a program, wherein the program executes the filter detection method.

[0156] Specifically, the testing methods for filters include:

[0157] Step S201: Obtain the target image, which is the image of the filter to be detected;

[0158] Specifically, a camera is installed in the air conditioner filter testing room to capture video of the air conditioner filter during the air conditioner testing process, thereby obtaining the captured filter images.

[0159] Step S202: Extract multiple border contour lines, where the border contour lines are the edges of the border contour of the filter to be detected in the target image.

[0160] Specifically, when the filter border experiences compression deformation, during image processing—specifically, when extracting and comparing the filter border outline—the opposite edges of the border may not be straight and may not be parallel, such as... Figure 3 As shown, by extracting multiple border outlines and judging whether they are deformed, it can be determined whether the border of the filter is qualified.

[0161] Step S203: The target image is analyzed using an image warping algorithm to obtain the warping degree of the filter to be detected. The warping degree is used to characterize the degree of deformation of the grid in the filter to be detected.

[0162] Specifically, during the assembly or storage of materials, if the filter mesh is under heat or tension, the mesh will deform due to external factors, resulting in visible fraying, bulging, or collapse of the filter mesh, which can be observed as distortion in the image. Figure 4 As shown, by analyzing the degree of distortion of the grid in the target image through the image distortion algorithm, it can be determined whether the grid of the filter is deformed, resulting in non-compliance.

[0163] Step S204: If any of the above-mentioned border outlines is not a straight line and / or the distortion of the above-mentioned filter screen to be tested is greater than the distortion threshold, the above-mentioned filter screen to be tested is determined to be unqualified.

[0164] Specifically, if any of the above-mentioned border outlines is not a straight line, it indicates that the border of the filter screen is deformed under stress. If the twist degree of the above-mentioned filter screen to be tested is greater than the twist degree threshold, it indicates that the mesh of the filter screen is severely twisted, both of which will lead to the filter screen being unqualified.

[0165] This invention provides an air conditioning system, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0166] Step S201: Obtain the target image, which is the image of the filter to be detected;

[0167] Specifically, a camera is installed in the air conditioner filter testing room to capture video of the air conditioner filter during the air conditioner testing process, thereby obtaining the captured filter images.

[0168] Step S202: Extract multiple border contour lines, where the border contour lines are the edges of the border contour of the filter to be detected in the target image.

[0169] Specifically, when the filter border experiences compression deformation, during image processing—specifically, when extracting and comparing the filter border outline—the opposite edges of the border may not be straight and may not be parallel, such as... Figure 3 As shown, by extracting multiple border outlines and judging whether they are deformed, it can be determined whether the border of the filter is qualified.

[0170] Step S203: The target image is analyzed using an image warping algorithm to obtain the warping degree of the filter to be detected. The warping degree is used to characterize the degree of deformation of the grid in the filter to be detected.

[0171] Specifically, during the assembly or storage of materials, if the filter mesh is under heat or tension, the mesh will deform due to external factors, resulting in visible fraying, bulging, or collapse of the filter mesh, which can be observed as distortion in the image. Figure 4 As shown, by analyzing the degree of distortion of the grid in the target image through the image distortion algorithm, it can be determined whether the grid of the filter is deformed, resulting in non-compliance.

[0172] Step S204: If any of the above-mentioned border outlines is not a straight line and / or the distortion of the above-mentioned filter screen to be tested is greater than the distortion threshold, the above-mentioned filter screen to be tested is determined to be unqualified.

[0173] Specifically, if any of the above-mentioned border outlines is not a straight line, it indicates that the border of the filter screen is deformed under stress. If the twist degree of the above-mentioned filter screen to be tested is greater than the twist degree threshold, it indicates that the mesh of the filter screen is severely twisted, both of which will lead to the filter screen being unqualified.

[0174] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0175] Step S201: Obtain the target image, which is the image of the filter to be detected;

[0176] Specifically, a camera is installed in the air conditioner filter testing room to capture video of the air conditioner filter during the air conditioner testing process, thereby obtaining the captured filter images.

[0177] Step S202: Extract multiple border contour lines, where the border contour lines are the edges of the border contour of the filter to be detected in the target image.

[0178] Specifically, when the filter border experiences compression deformation, during image processing—specifically, when extracting and comparing the filter border outline—the opposite edges of the border may not be straight and may not be parallel, such as... Figure 3 As shown, by extracting multiple border outlines and judging whether they are deformed, it can be determined whether the border of the filter is qualified.

[0179] Step S203: The target image is analyzed using an image warping algorithm to obtain the warping degree of the filter to be detected. The warping degree is used to characterize the degree of deformation of the grid in the filter to be detected.

[0180] Specifically, during the assembly or storage of materials, if the filter mesh is under heat or tension, the mesh will deform due to external factors, resulting in visible fraying, bulging, or collapse of the filter mesh, which can be observed as distortion in the image. Figure 4 As shown, by analyzing the degree of distortion of the grid in the target image through the image distortion algorithm, it can be determined whether the grid of the filter is deformed, resulting in non-compliance.

[0181] Step S204: If any of the above-mentioned border outlines is not a straight line and / or the distortion of the above-mentioned filter screen to be tested is greater than the distortion threshold, the above-mentioned filter screen to be tested is determined to be unqualified.

[0182] Specifically, if any of the above-mentioned border outlines is not a straight line, it indicates that the border of the filter screen is deformed under stress. If the twist degree of the above-mentioned filter screen to be tested is greater than the twist degree threshold, it indicates that the mesh of the filter screen is severely twisted, both of which will lead to the filter screen being unqualified.

[0183] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0184] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0185] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0186] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0187] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0188] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0189] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0190] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0191] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0192] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0193] 1) In the filter detection method of this application, firstly, a target image is acquired, which is the image of the filter to be detected; then, multiple border contour lines are extracted, which are the edges of the border contours of the filter to be detected in the target image; subsequently, an image distortion algorithm is used to analyze the target image to obtain the distortion degree of the filter to be detected, which is used to characterize the degree of deformation of the mesh in the filter to be detected; finally, if any of the border contour lines is not a straight line and / or the distortion degree of the filter to be detected is greater than the distortion degree threshold, the filter to be detected is determined to be unqualified. This method determines whether the border of the filter to be detected is deformed by checking whether the border contour lines in the image of the filter to be detected are straight, thereby determining whether the border is qualified; it determines the degree of deformation of the mesh in the filter to be detected by detecting the distortion degree of the filter to be detected, thereby determining whether the mesh is qualified. If the border and / or the mesh is unqualified, the filter to be detected is unqualified. Compared with manual measurement of deformation, image detection is much more efficient and solves the problem of low efficiency in manual detection of air conditioner filter quality in the prior art. In addition, manual inspection may be prone to errors, leading to inaccurate detection. Therefore, image inspection can also improve the accuracy of inspection.

[0194] 2) In the filter detection device of this application, the first acquisition unit acquires a target image, which is an image of the filter to be detected; the first processing unit extracts multiple border contour lines, which are the edges of the border contour of the filter to be detected in the target image; the analysis unit analyzes the target image using an image distortion algorithm to obtain the distortion degree of the filter to be detected, which is used to characterize the degree of deformation of the mesh in the filter to be detected; the first determination unit determines that the filter to be detected is unqualified if any of the border contour lines is not straight and / or the distortion degree of the filter to be detected is greater than the distortion degree threshold. This device determines whether the border of the filter to be detected is deformed by checking whether the border contour lines in the image of the filter to be detected are straight, thereby determining whether the border is qualified. It determines the degree of deformation of the mesh in the filter to be detected by detecting the distortion degree of the filter to be detected, thereby determining whether the mesh is qualified. If the border and / or the mesh is unqualified, the filter to be detected is unqualified. Compared with manual measurement of deformation, image detection greatly improves efficiency and solves the problem of low efficiency in manual detection of air conditioner filter quality in the prior art. In addition, manual inspection may be prone to errors, leading to inaccurate detection. Therefore, image inspection can also improve the accuracy of inspection.

[0195] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for detecting a filter screen, characterized in that, include: Acquire a target image, which is the image of the filter to be detected; Extract multiple border contour lines, where the border contour lines are the edges of the border contour of the filter to be detected in the target image; The target image is analyzed using an image warping algorithm to obtain the warping degree of the filter to be detected. The warping degree is used to characterize the degree of deformation of the grid in the filter to be detected. If any of the stated border outlines is not a straight line and / or the distortion of the filter to be tested exceeds a distortion threshold, the filter to be tested is determined to be unqualified. The image distortion algorithm is used to analyze the target image to obtain the distortion degree of the filter to be detected. This includes: distorting the target image using the image distortion algorithm to obtain a distorted image; determining the deformed portion based on the distorted image, the deformed portion including multiple grids; calculating the diameter of the circumcircle of each grid in the deformed portion to obtain multiple target diameters; calculating the absolute value of the difference between each target diameter and a standard diameter to obtain multiple distortion degrees, the standard diameter being the diameter of the circumcircle of one grid in the undeformed filter; and determining the largest distortion degree as the distortion degree of the filter to be detected.

2. The method according to claim 1, characterized in that, Extract multiple border outlines, including: The image is sharpened to obtain a first processed image; The first processed image is smoothed to obtain the second processed image; The second processed image is binarized to obtain the contour map of the filter to be detected, the contour map including multiple border contour lines.

3. The method according to claim 2, characterized in that, After extracting multiple border outlines, the method further includes: The multiple border outlines of the outline map are grouped to obtain two border outline groups, and each border outline group includes two non-intersecting border outlines. Calculate the included angle between the two border outlines of each border outline group to obtain multiple border angles, and the border angles correspond one-to-one with the border outline groups. If any of the included angles of the borders is greater than an angle threshold, it is determined that there exists a border outline that is not a straight line.

4. The method according to claim 2, characterized in that, After extracting multiple border outlines, the method further includes: The Hough line detection algorithm is used to detect the contour map, resulting in multiple straight lines; If any of the border outlines is not one of the plurality of straight lines, it is determined that there exists a border outline that is not a straight line.

5. The method according to claim 1, characterized in that, The image distortion algorithm described above is used to distort the target image to obtain a distorted image, including: A transformation grid is set in the target image, and the transformation grid is an N*N square grid; The transformed mesh is twisted to obtain a twisted mesh, which is an irregularly shaped mesh formed by the transformation mesh under external force; The projection matrix is ​​determined based on the twisted mesh and the transformed mesh, wherein the projection matrix is ​​the transformation matrix obtained by projecting the twisted mesh onto the transformed mesh; The distorted image is obtained by projecting the target image according to the projection matrix.

6. The method according to any one of claims 1 to 5, characterized in that, Before acquiring the target image, the method further includes: Acquire an installation image, which is an image of the installation position of the filter to be tested in the air conditioner; The filter to be detected is identified based on the installation image, and the identification result is obtained; If the identification result is that the installation image does not contain the filter to be tested, the air conditioner is determined to be defective.

7. A filter screen detection device, characterized in that, include: The first acquisition unit is used to acquire a target image, wherein the target image is an image of the filter to be detected; The first processing unit is used to extract multiple border contour lines, wherein the border contour lines are the edges of the border contour of the filter to be detected in the target image. The analysis unit is used to analyze the target image using an image distortion algorithm to obtain the distortion degree of the filter to be detected, wherein the distortion degree is used to characterize the degree of deformation of the grid in the filter to be detected; The first determining unit is configured to determine that the filter to be tested is unqualified if any of the outline lines of the frame is not a straight line and / or the distortion of the filter to be tested is greater than a distortion threshold. The analysis unit includes: a first processing module, used to distort the target image using the image distortion algorithm to obtain a distorted image; a first determining module, used to determine the deformed portion based on the distorted image, the deformed portion including multiple grids; a first calculation module, used to calculate the diameter of the circumcircle of each grid in the deformed portion to obtain multiple target diameters; a second calculation module, used to calculate the absolute value of the difference between each target diameter and a standard diameter to obtain multiple degrees of distortion, the standard diameter being the diameter of the circumcircle of one grid in the undeformed filter; and a second determining module, used to determine the largest degree of distortion as the degree of distortion of the filter to be detected.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 6.

9. An air conditioning system, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising methods for performing any one of claims 1 to 6.

Images