Detection method, detection device and detection system for leakage of refrigerant of air conditioner

Abstract

The invention provides an air conditioner refrigerant leakage detection method, device and system. The method comprises the steps that an image of a packaging piece of the air conditioner is obtained, a first image is obtained, the first image comprises a hollowed-out area, and the hollowed-out area is an area, used for detecting whether an air conditioner refrigerant leaks or not, of the packaging piece; processing the first image to obtain position information of the hollow area; and according to the position information, the hollowed-out area is detected so as to determine whether the refrigerant leaks or not. According to the method, the problem that the leakage detection process cannot be completed and even leakage detection gun equipment is damaged when the position of the leakage detection area fluctuates due to the fact that the leakage detection area cannot be automatically positioned in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of automatic detection, and in particular to a detection method, a detection device and a detection system for air-conditioning refrigerant leakage. Background Art

[0002] Refrigerant plays a vital role in the refrigeration performance and safety of air-conditioning systems. During the production and maintenance stages of air conditioners, refrigerant leakage problems often occur due to the instability of welding technology or operational errors, which requires leakage detection before the air conditioner is finally shipped out of the factory.

[0003] At present, the existing automatic leakage detection device usually uses infrared positioning technology to determine the position of the packaging box. The block assembly and the detection assembly use the position information to push the leak detection gun to a fixed position for detection according to the lifting and translation mechanism. However, the inventor found that it is impossible to automatically locate the leak detection area, which will result in the leak detection process being unable to be completed or even damage the leak detection gun equipment when the position of the leak detection area fluctuates.

[0004] Therefore, there is an urgent need for a detection method, a detection device and a detection system for air-conditioning refrigerant leakage that can automatically locate the leak detection area. Summary of the invention

[0005] The main purpose of the present application is to provide a method for detecting air-conditioning refrigerant leakage, an air-conditioning refrigerant leakage detection device, a storage medium and an electronic device, so as to at least solve the problem in the prior art that the leak detection area cannot be automatically positioned, which will result in the leak detection process being unable to be completed or even damage the leak detection gun equipment when the position of the leak detection area fluctuates.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for detecting air-conditioning refrigerant leakage is provided, comprising: acquiring an image of a packaging of an air conditioner to obtain a first image, the first image including a hollow area, the hollow area being an area of ​​the packaging for detecting whether the air-conditioning refrigerant is leaking; processing the first image to obtain position information of the hollow area; and detecting the hollow area based on the position information to determine whether there is a refrigerant leakage.

[0007] Optionally, the process of processing the first image includes: binarizing the first image to obtain a grayscale image, calculating the average grayscale value of the grayscale image, removing pixels whose grayscale values ​​are less than the average grayscale value, and obtaining multiple first contour areas; calculating the variance of the grayscale values ​​of multiple first contour areas to obtain a first variance, removing the first contour areas whose first variance is less than a first preset threshold, and obtaining multiple second contour areas; calculating the first distance between all endpoints in each second contour area and endpoints of all other second contour areas, retaining a contour area group whose first distance is less than or equal to a preset distance, wherein the contour area group consists of two second contour areas; fitting the contour area group to obtain a fitting shape, determining that the shape corresponding to the hollow area is the target shape, and calculating the center coordinates of the target shape and the size of the target shape as the position information of the hollow area.

[0008] Optionally, the first distances between all endpoints of each second contour area and endpoints of all other second contour areas are calculated, and a contour area group in which the first distance is less than or equal to a preset distance is retained, including: a search step: selecting any endpoint of the second contour area as a starting point, and searching around the starting point with the preset distance as a search radius; a calculation step: calculating the distance from the starting point to the endpoints of all other second contour areas, screening out the second contour areas to which the endpoints whose distances from the starting point are less than or equal to the search radius belong, and obtaining a target second contour area, wherein the target second contour area and the second contour area where the starting point is located form the contour area group.

[0009] Optionally, calculating the first distances between all endpoints of each second contour area and endpoints of all other second contour areas, retaining the contour area group in which the first distance is less than or equal to the preset distance, and further comprising: repeating the search step and the calculation step in sequence at least once until the distances between all any two endpoints of the second contour areas are calculated to obtain a plurality of the contour area groups.

[0010] Optionally, the contour area group is fitted to obtain a fitting shape, a shape corresponding to the hollow area is determined to be a target shape, and the center coordinates of the target shape and the size of the target shape are calculated as the position information of the hollow area, including: fitting the contour area group to obtain the fitting shape, determining the fitting shape that is the same as the shape of the hollow area as a preliminary shape; calculating the coordinates of the geometric center of the preliminary shape and the average grayscale value of the area where the preliminary shape is located, and determining that the preliminary shape that matches the size information and the average grayscale value of the hollow area is the target shape; and using the center coordinates of the target shape and the size of the target geometric shape as the position information of the hollow area.

[0011] Optionally, the hollow area is detected according to the position information, including: controlling a leak detection gun to move to the hollow area, and aiming at the hollow area to perform refrigerant leakage detection.

[0012] According to another aspect of the present application, a device for detecting refrigerant leakage of an air conditioner is provided, comprising:

[0013] An acquisition unit, configured to acquire an image of a package of the air conditioner to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the package used to detect whether the air conditioner refrigerant is leaking;

[0014] A processing unit, configured to process the first image to obtain position information of the hollowed-out area;

[0015] The detection unit is used to detect the hollow area according to the position information to determine whether there is a refrigerant leakage.

[0016] According to another aspect of the present application, a system for detecting leakage of an air conditioner refrigerant 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 are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the methods for detecting leakage of an air conditioner refrigerant.

[0017] Optionally, the detection system further includes: a light source, wherein during the process of acquiring the first graphic, the light source is located on both sides of the package of the air conditioner, and an angle between the light emitted by the light source and the central axis of the hollow area of ​​the package is an acute angle.

[0018] Optionally, the detection system further comprises: a leak detection gun, used for detecting whether there is refrigerant leakage in the hollow area.

[0019] Applying the technical solution of the present application, firstly, an image of the package of the air conditioner is acquired to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the package used to detect whether the air conditioner refrigerant is leaking; the first image is processed to obtain the position information of the hollow area; and the hollow area is detected according to the position information to determine whether there is a refrigerant leak. In this solution, before leak detection, the image of the package is acquired and processed in real time, the position information of the hollow area is extracted, and the position information is transmitted to the leak detection gun, which performs refrigerant leak detection according to the received position information, that is, the solution can automatically locate the leak detection area (hollow area), thereby solving the problem that the prior art cannot automatically locate the leak detection area, which will cause the leak detection process to fail to complete or even damage the leak detection gun equipment when the position of the leak detection area fluctuates. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 A hardware structure block diagram of a mobile terminal for performing a method for detecting air conditioner refrigerant leakage provided in an embodiment of the present application is shown;

[0022] Figure 2 A schematic flow chart of a method for detecting air conditioner refrigerant leakage according to an embodiment of the present application is shown;

[0023] Figure 3 A schematic diagram of a circular hollow area showing a method for detecting air conditioner refrigerant leakage provided in accordance with an embodiment of the present application;

[0024] Figure 4 A schematic diagram of an implementation flow of a method for detecting air conditioner refrigerant leakage provided in accordance with an embodiment of the present application is shown;

[0025] Figure 5 A schematic diagram of a device for detecting refrigerant leakage of an air conditioner provided according to an embodiment of the present application is shown;

[0026] Figure 6 A schematic diagram showing a hollow area on a surface to be detected of a package of an air conditioner according to a method for detecting refrigerant leakage of an air conditioner provided in an embodiment of the present application;

[0027] Figure 7 A front view showing a hollowed-out area and a lighting schematic diagram of a method for detecting refrigerant leakage of an air conditioner provided in an embodiment of the present application is shown;

[0028] Figure 8 A top view of a hollowed-out area and a lighting schematic diagram of a method for detecting refrigerant leakage of an air conditioner provided in an embodiment of the present application is shown;

[0029] Fig. 9 A left view of a hollowed-out area and a lighting schematic diagram of a method for detecting refrigerant leakage of an air conditioner provided in an embodiment of the present application is shown.

[0030] The reference numerals are as follows:

[0031] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device; 10. Hollow area; 20. Scratches; 30. Logo; 40. Printing area; 50. Light source; 51. Light emitting surface of light source; 60. Carton surface. DETAILED DESCRIPTION

[0032] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0033] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] During the research and development process, the inventor discovered that existing automatic leakage detection devices usually use infrared positioning technology to determine the position of the packaging box. The block assembly and the detection assembly use the position information to push the leak detection gun to a fixed position for detection according to the lifting and translation mechanism. This makes it impossible to automatically position the leak detection area, which will result in the leak detection process being unable to be completed or even damage the leak detection gun equipment when the leak detection area fluctuates in position.

[0036] In order to solve the problem that the leak detection area cannot be automatically positioned in the above-mentioned existing solutions, which will result in the leak detection process being unable to be completed or even damage the leak detection gun equipment when the position of the leak detection area fluctuates, the embodiments of the present application provide an air conditioning refrigerant leakage detection method, detection device and detection system.

[0037] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0038] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of an air conditioning refrigerant leakage detection method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0039] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as 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.

[0040] In this embodiment, a method for detecting air conditioning refrigerant leakage running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of 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 can be executed in an order different from that shown here.

[0041] Figure 2 FIG. 1 is a flow chart of a method for detecting air conditioner refrigerant leakage according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0042] Step S201, acquiring an image of a package of an air conditioner to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the package used to detect whether the air conditioner refrigerant is leaking;

[0043] Specifically, the hollow area on the air conditioner packaging is used to detect whether the air conditioner refrigerant is leaking. Refrigerant leakage may cause the air conditioner performance to decline or even damage the equipment. Therefore, such an area is set in the air conditioner packaging design to detect potential leakage problems in time during product transportation or storage to ensure the quality and safety of the air conditioner product. The shape of the area can be circular, rectangular, parallelogram, triangle, etc. For the specific shape, those skilled in the art can set it according to actual conditions.

[0044] Step S202, processing the first image to obtain position information of the hollowed-out area;

[0045] Specifically, by using a series of image processing algorithms to process the image of the air conditioner's packaging, the position information of the hollow area in the image is finally extracted. This position information can be used to determine the position and size of the detection area, thereby helping to accurately detect leaks.

[0046] Step S203: Detect the hollow area according to the position information to determine whether there is any refrigerant leakage.

[0047] Specifically, the process of detecting the hollow area is to conduct specific analysis and monitoring of the area to determine whether there is a refrigerant leak, which usually involves the use of sensors or other detection equipment to detect whether there is a refrigerant leak. Through this step, potential leakage problems can be discovered in time and appropriate measures can be taken to avoid further damage or safety risks.

[0048] In the above embodiment, an image of the air conditioner packaging is first acquired to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the packaging used to detect whether the air conditioner refrigerant is leaking; the first image is processed to obtain position information of the hollow area; and the hollow area is detected based on the position information to determine whether there is a refrigerant leak. In this solution, before leak detection, the image of the packaging is acquired and processed in real time, the position information of the hollow area is extracted, and the position information is transmitted to the leak detection gun, which performs refrigerant leak detection based on the received position information, that is, the solution can automatically locate the leak detection area (hollow area), thereby solving the problem that the prior art cannot automatically locate the leak detection area, which will cause the leak detection process to fail to complete or even damage the leak detection gun equipment when the position of the leak detection area fluctuates.

[0049] In a specific embodiment of the present application, the process of processing the above-mentioned first image includes: binarizing the above-mentioned first image to obtain a grayscale image, calculating the average grayscale value of the above-mentioned grayscale image, removing pixels with grayscale values ​​less than the above-mentioned average grayscale value, and obtaining multiple first contour areas; calculating the variance of the grayscale values ​​of the multiple first contour areas to obtain a first variance, removing the above-mentioned first contour areas whose first variance is less than a first preset threshold, and obtaining multiple second contour areas; calculating the first distance between all endpoints in each of the above-mentioned second contour areas and the endpoints of all other above-mentioned second contour areas, retaining a contour area group whose first distance is less than or equal to the preset distance, and the above-mentioned contour area group is composed of two of the above-mentioned second contour areas; fitting the above-mentioned contour area group to obtain a fitting shape, determining that the shape corresponding to the above-mentioned hollow area is the target shape, and calculating the center coordinates of the above-mentioned target shape and the size of the above-mentioned target shape as the position information of the above-mentioned hollow area.

[0050] Specifically, since the brightness of the printed pattern on the packaging of the air conditioner is relatively low, the first image is binarized. By setting the average grayscale value of the grayscale image as a threshold, the image is converted into a black and white image in which pixel values ​​only include 0 and 255. Among them, the pixels with grayscale values ​​greater than or equal to the threshold are set to white, and the pixels with grayscale values ​​less than the threshold are set to black. In other words, the printed area below the threshold is set to black, and the area above the average value is set to white. The black printed area is removed, that is, part of the printed outline is removed.

[0051] Specifically, mask technology can be used to calculate the grayscale value variance of the remaining contours. This is because the contours of the printed pattern are relatively uniform. Based on the calculated variance, the printed contours similar to the hollow area contours are removed, and what remains is a pattern containing the hollow area contours and other scratched contours.

[0052] More specifically, a mask is a binary image used to indicate the parts that need to be processed and the parts that are ignored. When processing an image, the white area is the part that needs to be processed, and the black area is the part that is ignored. Therefore, a corresponding mask can be made according to the specific position of each contour. The contour position in the mask is set to white, and the other positions are set to black. Each contour in the image can be separated separately for further processing or analysis. The role of the mask is similar to a mask, which can help select the area that needs to be processed more accurately and improve the efficiency and accuracy of the processing.

[0053] Specifically, due to the inconsistent height of the edges of the hollow areas, the captured images may have discontinuities in the edges of the hollow areas. Also, since paper packaging boxes may be scratched, the scratched outlines may interfere with the outlines of the hollow areas, resulting in the possibility of mis-merging. Therefore, it is necessary to remove the scratched outline images.

[0054] Specifically, using the center coordinates of the target shape and the size of the target shape as the position information of the hollowed-out area can ensure that the unknown information of the hollowed-out area is obtained more accurately, thereby more accurately detecting leaks.

[0055] In order to make the determined contour more accurate, and thus the obtained position information more accurate, thereby further ensuring the accuracy of leak detection, in an embodiment of the present application, the first distances between all endpoints of each of the above-mentioned second contour areas and the endpoints of all other above-mentioned second contour areas are calculated, and the contour area group in which the above-mentioned first distance is less than or equal to the preset distance is retained, including: a search step: selecting any endpoint of the above-mentioned second contour area as the starting point, and searching around the above-mentioned starting point with the above-mentioned preset distance as the search radius; a calculation step: calculating the distance from the above-mentioned starting point to the endpoints of all other above-mentioned second contour areas, screening out the above-mentioned second contour areas to which the endpoints whose distance from the above-mentioned starting point is less than or equal to the above-mentioned search radius belong, and obtaining the target second contour area, and the above-mentioned target second contour area and the above-mentioned second contour area where the above-mentioned starting point is located form the above-mentioned contour area group.

[0056] Specifically, taking the shape of the hollow area as a circle as an example, take any point on the hollow area and use the diameter of the hollow area as the search radius. It is certain that other contours on the contour of the hollow area can be searched. Based on this, since they belong to the contours of the real hollow area, the circles they fit respectively are theoretically cocircular, that is, the distance between the centers of the circles will be relatively close or even overlap, allowing some margin. Therefore, the contours that can be searched for each other are fitted with circles respectively, and the scratched contours are removed according to the distance between the centers of the fitted circles, retaining the real contour of the hollow area, such as Figure 3 As shown, a schematic diagram of a circular leak detection area is shown, including a hollow area 10 and a scratch 20. The contours AB, CD, and EF in the second contour area are marked as to be merged. At this time, other contours similar to the hollow area contour may appear, such as contour EF, so the distances between the endpoints of the contours to be merged are calculated, such as AC, AD, AF, AE, CF, etc.

[0057] Specifically, Figure 3 As shown, with point A as the origin and the diameter of the hollow area as the search radius, other contours on the circular hollow area contour can be searched for, and the distance from point A to the other endpoints is calculated and compared with the diameter of the hollow area. The contours whose distance is less than the diameter of the hollow area are divided into a group, such as grouping contour AB and contour CD into a group, and contour CD and contour EF into a group. The contour merging technology is applied to process the contours to be merged in the same group so that they are merged into a complete contour. Based on the shape of the hollow area, the shape of the merged fitted contour is a circle.

[0058] More specifically, when merging two contours, the pixel position information contained in the two contours can be stored in different lists, and then the contours can be merged by merging the two lists. Similarly, if multiple contours need to be merged, the merging of multiple contours can be achieved by merging the corresponding multiple lists. This method can effectively integrate the information of different contours together, thereby realizing the contour merging operation.

[0059] In one embodiment of the present application, the first distances between all endpoints of each of the above-mentioned second contour areas and the endpoints of all other above-mentioned second contour areas are calculated, and the contour area group whose above-mentioned first distance is less than or equal to the preset distance is retained, and it also includes: repeating the above-mentioned search step and the above-mentioned calculation step at least once in sequence until the distances between all arbitrary two endpoints of the above-mentioned second contour areas are calculated, so as to obtain multiple above-mentioned contour area groups.

[0060] Specifically, first, the distance between the endpoint of the second contour area and the endpoint of other second contour areas is calculated, and then the contour area group whose first distance is less than or equal to the preset distance is screened out. Next, the search step and the calculation step are repeated in sequence at least once until the distance between the endpoints of all any two second contour areas is calculated to obtain multiple contour area groups. In this way, multiple contour area groups that meet the conditions can be obtained, so that for the contour areas in each contour area group, the distances between their endpoints meet the preset conditions, so that the contour areas can be effectively screened and grouped to meet specific needs and conditions.

[0061] In order to ensure that the obtained position information of the hollow area is more accurate, thereby more accurately detecting leaks, in another embodiment of the present application, the above-mentioned contour area group is fitted to obtain a fitting shape, the shape corresponding to the above-mentioned hollow area is determined to be a target shape, and the center coordinates of the above-mentioned target shape and the size of the above-mentioned target shape are calculated as the position information of the above-mentioned hollow area, including: fitting the above-mentioned contour area group to obtain the above-mentioned fitting shape, determining the above-mentioned fitting shape that is the same as the shape of the above-mentioned hollow area as a preliminary shape; calculating the coordinates of the geometric center of the above-mentioned preliminary shape and the average grayscale value of the area where the above-mentioned preliminary shape is located, determining the above-mentioned preliminary shape that matches the size information and the average grayscale value of the above-mentioned hollow area as the above-mentioned target shape; and using the center coordinates of the above-mentioned target shape and the size of the above-mentioned target geometric shape as the position information of the above-mentioned hollow area.

[0062] Specifically, Figure 3As shown, the contours in each contour area group are fitted with the RANSAC algorithm to calculate the center position and radius of the fitting circle. RANSAC is an iterative method for estimating mathematical model parameters, which can ignore outliers in the data set. The parameter is set to 100 inner points, which means that in each iteration, the randomly selected sample points must contain at least 100 inner points, which will be used to fit the circular model. The fitting distance is set to 5, which means that during the fitting process, if the distance from a data point to the fitting circle is less than 5 units, the point is considered to be an inner point. In this way, the contour pixels are fitted with a circle by the RANSAC method, and the circular model that best conforms to the actual situation can be obtained, which helps to accurately describe the shape of the hollow area contour.

[0063] Specifically, the average gray value of the circumferential area is measured. Because the gray value distribution at the edge of the hollow area should be more uniform and clearly distinguished from the background, those contours with uneven gray value distribution or close to the background can be excluded. In addition, the hollow area has a specific size range, so those circles with too large or too small radius can be excluded. Therefore, by analyzing the gray value and the size of the circle, setting the threshold according to the analysis results of the gray value and the size of the circle, non-target contours can be effectively excluded, such as Figure 3 The circles obtained by fitting the contours CD and EF only retain the center coordinates and radii that meet the characteristics of the hollowed-out area.

[0064] Specifically, if the difference between the size information of the prepared shape and the size information of the hollow area is within a certain range, and the difference between the average grayscale value of the prepared shape and the average grayscale value of the hollow area is within a certain range, then the prepared shape is considered to be the target shape; or if the size information of the prepared shape and the size information of the hollow area are equal, and the average grayscale value of the prepared shape and the average grayscale value of the hollow area are equal, then the prepared shape is considered to be the target shape.

[0065] In another embodiment of the present application, the hollow area is detected based on the position information, including: controlling the leak detection gun to move to the hollow area, and aiming at the hollow area to detect refrigerant leakage.

[0066] Specifically, based on the known position information, the system will control the leak detection gun to move to the hollow area and ensure that it is aimed at the area. Then, the system will perform a refrigerant leak detection to determine whether there is a refrigerant leak.

[0067] In order to improve the response speed and efficiency of leakage events and reduce potential losses and risks, in an embodiment of the present application, the method further includes: issuing an alarm message when the leak detection gun detects refrigerant leakage.

[0068] Specifically, in addition to using a leak detection gun to detect refrigerant leaks, an alarm message will be issued when a refrigerant leak is detected, which means that the system can promptly discover and respond to refrigerant leaks so that necessary measures can be taken in time to prevent further leakage and protect the safety of equipment and the environment. The alarm message can be conveyed to relevant operators through sound, light or other means so that they can take quick action.

[0069] In another embodiment of the present application, the process of acquiring the above-mentioned first image includes: placing the optical axis of the camera perpendicular to the above-mentioned hollow area, photographing the above-mentioned hollow area, and obtaining the above-mentioned first image.

[0070] Specifically, during the imaging process, if the camera optical axis is not perpendicular to the surface of the package to be inspected, perspective distortion will occur, causing the hollow area to deform in the image, which will affect the accuracy of the detection. In order to avoid this situation, a shooting method is adopted in which the camera optical axis is perpendicular to the surface of the package to be inspected, ensuring that the shape of the hollow area is close to the real shape. This shooting method can reduce the error caused by deformation and improve the accuracy and stability of detection.

[0071] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the air-conditioning refrigerant leakage detection method of the present application will be described in detail below in combination with specific embodiments.

[0072] This embodiment relates to a specific method for detecting air conditioner refrigerant leakage, such as Figure 4 As shown, the implementation process of the method for detecting air conditioner refrigerant leakage includes the following steps:

[0073] An image of a package of an air conditioner is acquired.

[0074] The image is binarized and gray-scale analyzed to obtain a plurality of first contour regions.

[0075] The variances of the plurality of first contour regions are analyzed to obtain a plurality of second contour regions.

[0076] An endpoint search logic is applied to each second contour region to obtain a contour region group.

[0077] The contour region groups are merged to obtain a contour set.

[0078] Determine whether the contour collection is empty.

[0079] If the contour set is empty, the position information of all hollowed-out areas is obtained and transmitted to the leak detection gun for detection.

[0080] If the contour set is not empty, take a contour from the contour set and delete it.

[0081] Perform shape fitting on the selected contour.

[0082] Determine whether it can fit into the target shape.

[0083] If the target shape cannot be fitted, the position information of the hollowed-out area is set to a null value.

[0084] The location information of the hollowed-out area is stored, and the process jumps to the execution step of "determining whether the contour set is empty".

[0085] If it can be fitted into the target shape, it is determined whether the size of the fitted shape meets the requirements.

[0086] If the size of the fitted shape does not meet the requirements, the position information of the hollowed-out area is set to a null value, and the process jumps to the step "storing the position information of the hollowed-out area, and jumping to the step "judging whether the contour set is empty"".

[0087] If the size of the fitted shape meets the requirements, it is determined whether the average grayscale value of the pixels around the fitted shape meets the requirements.

[0088] If the average grayscale value of the pixels around the fitted shape does not meet the requirements, the position information of the hollowed-out area is set to a null value, and the process jumps to the step "Store the position information of the hollowed-out area, and jumps to the step "Determine whether the contour set is empty"".

[0089] If the average grayscale value of the pixels around the fitted shape meets the requirements, the hollow area will be marked in the figure.

[0090] Use the center coordinates and size of the fitted shape as the position information of the hollowed-out area, jump to the step "Store the position information of the hollowed-out area, and jump to the execution step "Determine whether the contour set is empty"".

[0091] In the above embodiment, an image processing algorithm is used to process the image of the air conditioner packaging, extract the position information of the hollow area, and transmit the position information to the leak detection gun. The leak detection gun performs refrigerant leakage detection based on the received position information, thereby realizing automatic positioning of the leak detection area.

[0092] The embodiment of the present application also provides a detection device for air conditioning refrigerant leakage. It should be noted that the detection device for air conditioning refrigerant leakage of the embodiment of the present application can be used to execute the detection method for air conditioning refrigerant leakage provided by the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0093] The following is an introduction to the air conditioning refrigerant leakage detection device provided in the embodiment of the present application.

[0094] Figure 5 Schematic diagram of a device for detecting air conditioner refrigerant leakage according to an embodiment of the present application. Figure 5 As shown, the device comprises:

[0095] The acquisition unit 100 is used to acquire an image of a package of the air conditioner to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the package used to detect whether the air conditioner refrigerant is leaking;

[0096] Specifically, the hollow area on the air conditioner packaging is used to detect whether the air conditioner refrigerant is leaking. Refrigerant leakage may cause the air conditioner performance to decline or even damage the equipment. Therefore, such an area is set up in the air conditioner packaging design to detect potential leakage problems in time during product transportation or storage to ensure the quality and safety of the air conditioner products.

[0097] The processing unit 200 is used to process the first image to obtain the position information of the hollowed-out area;

[0098] Specifically, by using a series of image processing algorithms to process the image of the air conditioner's packaging, the position information of the hollow area in the image is finally extracted. This position information can be used to determine the position and size of the detection area, thereby helping to accurately detect leaks.

[0099] The detection unit 300 is used to detect the hollow area according to the position information to determine whether there is any refrigerant leakage.

[0100] Specifically, the process of detecting the hollow area is to conduct specific analysis and monitoring of the area to determine whether there is a refrigerant leak, which usually involves the use of sensors or other detection equipment to detect whether there is a refrigerant leak. Through this step, potential leakage problems can be discovered in time and appropriate measures can be taken to avoid further damage or safety risks.

[0101] In the above embodiment, an image of the air conditioner packaging is first acquired to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the packaging used to detect whether the air conditioner refrigerant is leaking; the first image is processed to obtain position information of the hollow area; and the hollow area is detected based on the position information to determine whether there is a refrigerant leak. In this solution, before leak detection, the image of the packaging is acquired and processed in real time, the position information of the hollow area is extracted, and the position information is transmitted to the leak detection gun, which performs refrigerant leak detection based on the received position information, that is, the solution can automatically locate the leak detection area (hollow area), thereby solving the problem that the prior art cannot automatically locate the leak detection area, which will cause the leak detection process to fail to complete or even damage the leak detection gun equipment when the position of the leak detection area fluctuates.

[0102] In a specific embodiment of the present application, the processing unit includes:

[0103] A first calculation module is used to perform binarization processing on the first image to obtain a grayscale image, calculate an average grayscale value of the grayscale image, remove pixels with grayscale values ​​less than the average grayscale value, and obtain a plurality of first contour areas;

[0104] A second calculation module is used to calculate the variance of the grayscale values ​​of the plurality of first contour regions to obtain a first variance, and remove the first contour regions whose first variance is less than a first preset threshold to obtain a plurality of second contour regions;

[0105] a third calculation module, configured to calculate first distances between all endpoints in each of the second contour regions and endpoints of all other second contour regions, and retain a contour region group whose first distance is less than or equal to a preset distance, wherein the contour region group is composed of two of the second contour regions;

[0106] The fitting module is used to fit the above-mentioned contour area group to obtain a fitting shape, determine the shape corresponding to the above-mentioned hollow area as the target shape, and calculate the center coordinates of the above-mentioned target shape and the size of the above-mentioned target shape as the position information of the above-mentioned hollow area.

[0107] Specifically, since the brightness of the printed pattern on the packaging of the air conditioner is relatively low, the first image is binarized. By setting the average grayscale value of the grayscale image as a threshold, the image is converted into a black and white image in which pixel values ​​only include 0 and 255. Among them, the pixels with grayscale values ​​greater than or equal to the threshold are set to white, and the pixels with grayscale values ​​less than the threshold are set to black. In other words, the printed area below the threshold is set to black, and the area above the average value is set to white. The black printed area is removed, that is, part of the printed outline is removed.

[0108] Specifically, the mask technology is used to calculate the gray value variance of the remaining contour. This is because the contour of the printed pattern is relatively uniform. According to the calculated variance, the printed contour similar to the hollow area contour is removed, and what remains is the pattern containing the hollow area contour and other scratched contours.

[0109] More specifically, a mask is a binary image used to indicate the parts that need to be processed and the parts that are ignored. When processing an image, the white area is the part that needs to be processed, and the black area is the part that is ignored. Therefore, a corresponding mask can be made according to the specific position of each contour. The contour position in the mask is set to white, and the other positions are set to black. Each contour in the image can be separated separately for further processing or analysis. The role of the mask is similar to a mask, which can help select the area that needs to be processed more accurately and improve the efficiency and accuracy of the processing.

[0110] Specifically, due to the inconsistent height of the edges of the hollow areas, the captured images may have discontinuities in the edges of the hollow areas. Also, since paper packaging boxes may be scratched, the scratched outlines may interfere with the outlines of the hollow areas, resulting in the possibility of mis-merging. Therefore, it is necessary to remove the scratched outline images.

[0111] In one embodiment of the present application, the third calculation module includes:

[0112] A search submodule is used to select any endpoint of the second contour area as a starting point, use the preset distance as a search radius, and search around the starting point;

[0113] A calculation submodule is used to calculate the distance from the above-mentioned starting point to the endpoints of all other above-mentioned second contour areas, screen out the above-mentioned second contour areas to which the endpoints whose distance from the above-mentioned starting point is less than or equal to the above-mentioned search radius belong, and obtain the target second contour area. The above-mentioned target second contour area and the above-mentioned second contour area where the above-mentioned starting point is located form the above-mentioned contour area group.

[0114] Specifically, taking the shape of the hollow area as a circle as an example, take any point on the hollow area and use the diameter of the hollow area as the search radius. It is certain that other contours on the contour of the hollow area can be searched. Based on this, since they belong to the contours of the real hollow area, the circles they fit respectively are theoretically cocircular, that is, the distance between the centers of the circles will be relatively close or even overlap, allowing some margin. Therefore, the contours that can be searched for each other are fitted with circles respectively, and the scratched contours are removed according to the distance between the centers of the fitted circles, retaining the real contour of the hollow area.

[0115] Specifically, taking any point on the hollow area as the origin and the diameter of the hollow area as the search radius, other contours on the circular hollow area contour can be searched for, and the distance from the origin to the other endpoints is calculated and compared with the diameter of the hollow area. The contours whose distance is less than the diameter of the hollow area are grouped together, and the contour merging technology is applied to process the contours to be merged in the same group so that they are merged into a complete contour. Based on the shape of the hollow area, the shape of the merged and fitted contour is a circle.

[0116] More specifically, when merging two contours, the pixel position information contained in the two contours can be stored in different lists, and then the contours can be merged by merging the two lists. Similarly, if multiple contours need to be merged, the merging of multiple contours can be achieved by merging the corresponding multiple lists. This method can effectively integrate the information of different contours together, thereby realizing the contour merging operation.

[0117] In one embodiment of the present application, the third calculation module further includes:

[0118] The repeating submodule is used to repeatedly execute the above-mentioned search step and the above-mentioned calculation step at least once in sequence until the distances between all the endpoints of any two of the above-mentioned second contour areas are calculated to obtain a plurality of the above-mentioned contour area groups.

[0119] Specifically, the distance between the endpoint of the second contour area and the endpoint of other second contour areas is calculated, and then the contour area group whose first distance is less than or equal to the preset distance is screened out. Next, the search step and the calculation step are repeated in sequence at least once until the distance between the endpoints of all any two second contour areas is calculated to obtain multiple contour area groups. In this way, multiple contour area groups that meet the conditions can be obtained, so that for the contour areas in each contour area group, the distances between their endpoints meet the preset conditions, so that the contour areas can be effectively screened and grouped to meet specific needs and conditions.

[0120] In another embodiment of the present application, the fitting module includes:

[0121] A fitting submodule, used for fitting the above-mentioned contour area group to obtain the above-mentioned fitting shape, and determining the above-mentioned fitting shape which is the same as the shape of the above-mentioned hollow area as the preliminary shape;

[0122] A calculation submodule, used to calculate the coordinates of the geometric center of the above-mentioned preparation shape and the average grayscale value of the area where the above-mentioned preparation shape is located, and determine that the above-mentioned preparation shape matching the size information and the average grayscale value of the above-mentioned hollow area is the above-mentioned target shape;

[0123] The determination submodule is used to use the center coordinates of the target shape and the size of the target geometric shape as the position information of the hollow area.

[0124] Specifically, the RANSAC algorithm is used to perform circular fitting on the contours in each contour area group to calculate the center position and radius of the fitting circle. RANSAC is an iterative method for estimating mathematical model parameters, which can ignore outliers in the data set. The parameter is set to 100 inner points, which means that in each iteration, the randomly selected sample points must contain at least 100 inner points, which will be used to fit the circular model. The fitting distance is set to 5, which means that during the fitting process, if the distance from a data point to the fitting circle is less than 5 units, the point is considered to be an inner point. In this way, the RANSAC method is used to fit the contour pixels to a circle, and the most realistic circular model can be obtained, which helps to accurately describe the shape of the hollow area contour.

[0125] Specifically, the average gray value of the circumference area is measured. Because the gray value distribution at the edge of the hollow area should be more uniform and clearly distinguished from the background, those contours with uneven gray value distribution or close to the background can be excluded. The hollow area has a specific size range, so those circles with too large or too small radius can be excluded. Therefore, by analyzing the gray value and the size of the circle, and setting the threshold according to the analysis results of the gray value and the size of the circle, non-target contours can be effectively excluded, and only those circle center coordinates and radii that meet the characteristics of the hollow area are retained.

[0126] In another embodiment of the present application, the detection unit includes:

[0127] The detection module is used to control the leak detection gun to move to the above-mentioned hollow area and aim at the above-mentioned hollow area to perform refrigerant leakage detection.

[0128] Specifically, based on the known location information, the system will control the leak detection gun to move to the hollow area and ensure that it is aimed at the area. The system will perform a refrigerant leak detection to determine whether there is a refrigerant leak.

[0129] In order to improve the response speed and efficiency of leakage events and reduce potential losses and risks, in an embodiment of the present application, the above-mentioned device also includes: an alarm unit, which is used to issue an alarm message when the above-mentioned leak detection gun detects refrigerant leakage.

[0130] Specifically, in addition to using a leak detection gun to detect refrigerant leaks, an alarm message will be issued when a refrigerant leak is detected, which means that the system can promptly discover and respond to refrigerant leaks so that necessary measures can be taken in time to prevent further leakage and protect the safety of equipment and the environment. The alarm message can be conveyed to relevant operators through sound, light or other means so that they can take quick action.

[0131] In another embodiment of the present application, the acquisition unit includes:

[0132] The shooting module is used to make the optical axis of the camera perpendicular to the hollow area, shoot the hollow area, and obtain the first image.

[0133] Specifically, during the imaging process, if the camera optical axis is not perpendicular to the surface of the package to be inspected, perspective distortion will occur, causing the hollow area to deform in the image, which will affect the accuracy of the detection. In order to avoid this situation, a shooting method is adopted in which the camera optical axis is perpendicular to the surface of the package to be inspected, ensuring that the shape of the hollow area is close to the real shape. This shooting method can reduce the error caused by deformation and improve the accuracy and stability of detection.

[0134] An embodiment of the present invention provides a system for detecting refrigerant leakage of an air conditioner, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the above-mentioned methods for detecting refrigerant leakage of an air conditioner.

[0135] In the above embodiment, firstly, an image of the package of the air conditioner is acquired to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the package used to detect whether the air conditioner refrigerant is leaking; the first image is processed to obtain the position information of the hollow area; and the hollow area is detected according to the position information to determine whether there is a refrigerant leak. In this scheme, before leak detection, the image of the package is acquired in real time and processed, the position information of the hollow area is extracted, and the position information is transmitted to the leak detection gun, and the leak detection gun performs refrigerant leakage detection according to the received position information, that is, the scheme can automatically locate the leak detection area (hollow area), thereby solving the problem that the prior art cannot automatically locate the leak detection area, which will cause the leak detection process to fail to complete or even damage the leak detection gun equipment when the position of the leak detection area fluctuates. In one embodiment of the present application, the detection system further includes: a light source, in the process of acquiring the first graphic, the light source is located on both sides of the package of the air conditioner, and the angle between the light emitted by the light source and the central axis of the hollow area of ​​the package is an acute angle.

[0136] Specifically, the top of the hollow area on the surface to be tested of the package of the air conditioner is not opened, and the schematic diagram of the hollow area on the surface to be tested of the package of the air conditioner is as follows: Figure 6As shown, the surface of the package to be inspected, that is, the carton surface 60, has a printed area 40, a logo 30, etc. in addition to the hollow area 10. In addition, the package is made of easily deformable paper material, so that the hollow area and the non-hollow area are located on different planes, resulting in the edge of the hollow area being uneven compared to the plane of the package. However, when the hollow area is observed in a direction perpendicular to the plane of the hollow area, the unevenness of the edge of the hollow area is not easy to be observed. The light source emitting surface 51 is as shown in FIG. Figure 6 As shown, in order to make the image contour features of the hollow area clearer, based on the uneven characteristics of the hollow area edge, avoid the lighting direction of the light source 50 being perpendicular to the plane of the hollow area. The front view of the hollow area and the lighting schematic diagram is shown in Figure 7 As shown, specifically, two symmetrical strip light sources 50 are used for illumination, so that the light source is parallel to the surface of the package to be inspected, that is, the carton surface 60, and cannot be located directly above the hollow area 10. The best way is that the light source is perpendicular to the top plane of the hollow area. The top view of the hollow area and the lighting schematic diagram is shown in Figure 8 As shown, the light source 50 can be placed against the carton panel, and the light source cannot be placed in the front area of ​​the hollow area 10, because if the light source is placed in the front area of ​​the hollow area, no matter how the light source shines, it is difficult to form a good light and shadow at the boundary of the hollow area, which affects the detection of the edge of the hollow area contour. In addition, the light source can be placed in other positions, and the angle α between the light direction and the central axis can be kept as an acute angle. The left view of the hollow area and the lighting schematic diagram is shown in FIG. Fig. 9 As shown, the light source 50 is placed flush with the carton surface 60. In actual operation, the light source can also be placed flush with the carton panel, as long as the angle between the light and the central axis is an acute angle. This can significantly improve the contrast between the edge of the hollow area 10 and the surface to be inspected of the package.

[0137] In one embodiment of the present application, the detection system further includes: a leak detection gun for detecting whether there is refrigerant leakage in the hollow area.

[0138] Specifically, the purpose of a leak detector gun is to detect if there is a refrigerant leak in the hollow area, and it usually works by sensing specific signals produced by a refrigerant leak, such as smell, sound or pressure change. Leak detector guns can usually be electronic, using sensors to detect leaks, or chemical, using special reagents to detect the presence of refrigerant.

[0139] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0140] The above-mentioned air conditioner refrigerant leakage detection device includes a processor and a memory, and the above-mentioned acquisition unit, processing unit, detection unit, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions. The above-mentioned modules are all located in the same processor; or, the above-mentioned modules are located in different processors in any combination.

[0141] The memory may include non-permanent memory in a computer-readable medium, 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.

[0142] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the air-conditioning refrigerant leakage detection method.

[0143] Specifically, the method for detecting air conditioner refrigerant leakage includes:

[0144] Step S201, acquiring an image of a package of an air conditioner to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the package used to detect whether the air conditioner refrigerant is leaking;

[0145] Step S202, processing the first image to obtain position information of the hollowed-out area;

[0146] Step S203: Detect the hollow area according to the position information to determine whether there is any refrigerant leakage.

[0147] An embodiment of the present invention provides a device, the device including a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0148] Step S201, acquiring an image of a package of an air conditioner to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the package used to detect whether the air conditioner refrigerant is leaking;

[0149] Step S202, processing the first image to obtain position information of the hollowed-out area;

[0150] Step S203: Detect the hollow area according to the position information to determine whether there is any refrigerant leakage.

[0151] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0152] Step S201, acquiring an image of a package of an air conditioner to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the package used to detect whether the air conditioner refrigerant is leaking;

[0153] Step S202, processing the first image to obtain position information of the hollowed-out area;

[0154] Step S203: Detect the hollow area according to the position information to determine whether there is any refrigerant leakage.

[0155] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0156] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0157] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0158] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0159] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0160] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0161] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0162] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0163] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0164] In the above embodiment, an image of the air conditioner packaging is first acquired to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the packaging used to detect whether the air conditioner refrigerant is leaking; the first image is processed to obtain position information of the hollow area; and the hollow area is detected based on the position information to determine whether there is a refrigerant leak. In this solution, before leak detection, the image of the packaging is acquired and processed in real time, the position information of the hollow area is extracted, and the position information is transmitted to the leak detection gun, which performs refrigerant leak detection based on the received position information, that is, the solution can automatically locate the leak detection area (hollow area), thereby solving the problem that the prior art cannot automatically locate the leak detection area, which will cause the leak detection process to fail to complete or even damage the leak detection gun equipment when the position of the leak detection area fluctuates.

[0165] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting air conditioning refrigerant leakage, characterized in that: include: Acquire an image of a package of the air conditioner to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the package used to detect whether the air conditioner refrigerant is leaking; Processing the first image to obtain position information of the hollowed-out area; The hollow area is inspected according to the position information to determine whether there is a refrigerant leakage.

2. The detection method according to claim 1, characterized in that: The process of processing the first image includes: Binarizing the first image to obtain a grayscale image, calculating an average grayscale value of the grayscale image, removing pixels whose grayscale values ​​are less than the average grayscale value, and obtaining a plurality of first contour regions; Calculating the variance of the grayscale values ​​of the plurality of first contour regions to obtain a first variance, and removing the first contour regions whose first variance is less than a first preset threshold to obtain a plurality of second contour regions; Calculating first distances between all endpoints in each of the second contour areas and endpoints of all other second contour areas, and retaining a contour area group whose first distance is less than or equal to a preset distance, wherein the contour area group is composed of two second contour areas; The contour region group is fitted to obtain a fitting shape, a shape corresponding to the hollow region is determined as a target shape, and the center coordinates of the target shape and the size of the target shape are calculated as position information of the hollow region.

3. The detection method according to claim 2, characterized in that: Calculating first distances between all endpoints of each second contour region and endpoints of all other second contour regions, and retaining a contour region group whose first distance is less than or equal to a preset distance, comprises: Searching step: selecting any endpoint of the second contour area as a starting point, using the preset distance as a search radius, and searching around the starting point; Calculation steps: calculate the distance from the starting point to the endpoints of all other second contour areas, filter out the second contour areas to which the endpoints whose distance from the starting point is less than or equal to the search radius belong, and obtain the target second contour area. The target second contour area and the second contour area where the starting point is located form the contour area group.

4. The detection method according to claim 3, characterized in that: Calculating first distances between all endpoints of each second contour region and endpoints of all other second contour regions, and retaining a contour region group whose first distance is less than or equal to a preset distance, further comprising: The searching step and the calculating step are sequentially and repeatedly performed at least once until the distances between all any two endpoints of the second contour areas are calculated, thereby obtaining a plurality of the contour area groups.

5. The detection method according to claim 2, characterized in that: Fitting the contour region group to obtain a fitting shape, determining a shape corresponding to the hollow region as a target shape, and calculating the center coordinates of the target shape and the size of the target shape as position information of the hollow region, including: Fitting the contour area group to obtain the fitting shape, and determining the fitting shape that is the same as the shape of the hollow area as the preliminary shape; Calculating the coordinates of the geometric center of the preliminary shape and the average grayscale value of the area where the preliminary shape is located, and determining that the preliminary shape matching the size information and the average grayscale value of the hollowed-out area is the target shape; The center coordinates of the target shape and the size of the target shape are used as the position information of the hollow area.

6. The detection method according to claim 1, characterized in that: Detecting the hollowed-out area according to the position information includes: The leak detection gun is controlled to move to the hollow area and is aimed at the hollow area to perform refrigerant leakage detection.

7. A device for detecting refrigerant leakage of an air conditioner, characterized in that: include: An acquisition unit, configured to acquire an image of a package of the air conditioner to obtain a first image, wherein the first image includes a hollow area, and the hollow area is an area of ​​the package used to detect whether the air conditioner refrigerant is leaking; A processing unit, configured to process the first image to obtain position information of the hollowed-out area; The detection unit is used to detect the hollow area according to the position information to determine whether there is a refrigerant leakage.

8. A detection system for air conditioning refrigerant leakage, 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 are configured to be executed by the one or more processors, and the one or more programs include a method for detecting air conditioner refrigerant leakage according to any one of claims 1 to 6.

9. The detection system according to claim 8, characterized in that: The detection system also includes: Light source, in the process of acquiring the first image, the light source is located on both sides of the package of the air conditioner, the angle between the light emitted by the light source and the central axis of the hollow area of ​​the package is an acute angle, and the light source has no positive projection on the hollow area.

10. The detection system according to claim 8, characterized in that: The detection system also includes: The leak detection gun is used to detect whether there is refrigerant leakage in the hollow area.

Images