Method for detecting two devices of air conditioner, computer readable storage medium and air conditioning system

Abstract

The present application provides a detection method for two air conditioners, a computer-readable storage medium, and an air conditioning system. The method comprises: determining the position information of the initial edge contour of the bell mouth according to the bell mouth images of the two air conditioners; performing symmetry axis fitting on the initial edge contour according to the position information to obtain a symmetry axis segment, wherein the two end points of the symmetry axis segment are the intersection points of the symmetry axis segment and the initial edge contour; extracting multiple edge contour line segments at least located on one side of the symmetry axis segment from the initial edge contour according to the symmetry axis segment; determining the center position of the edge contour of the bell mouth according to the multiple edge contour line segments, and determining the size parameters of the bell mouth according to the multiple edge contour line segments and the center position of the edge contour; determining whether the bell mouth is qualified according to the size parameters.

Description

Technical Field

[0001] The present application relates to the technical field of defect detection, and in particular, to a method for detecting two devices of an air conditioner, a computer-readable storage medium, a computer program product, and an air conditioning system. Background Art

[0002] With the continuous development and progress of science and technology, more and more air-conditioning companies use various modern technologies to realize the automation and intelligence of production. As the basic components of air-conditioning products, the production quality of the two air-conditioning components (evaporator and condenser) has an important impact on the quality of the entire air-conditioning product. Defect detection is the main means to improve the quality of product production. Through the design of the visual inspection system solution, the use of visual inspection related equipment and algorithms can realize the detection of the outer edge diameter of the bell mouth opening after the expansion tube, and judge whether the outer edge diameter of the bell mouth opening is qualified according to the diameter design standard value and the allowable error range. For the bell mouths that are directly connected to the fins at both ends of the side plate side of the two-device components without the side plate sheet metal, the fins directly connected around the copper tube may be uneven and wrinkled, resulting in the image of the bell mouth captured by the line scan camera to have uncertain irregular shapes and shadows of the adhesion copper tube. The shadow will seriously interfere with the existing visual inspection algorithm, resulting in a high false alarm rate of the inspection result. Summary of the invention

[0003] The main purpose of the present application is to provide a detection method for two air conditioners, a computer-readable storage medium, a computer program product and an air conditioning system, so as to at least solve the problem of high false alarm rate in the detection of the bell mouth size of the two air conditioners in the prior art.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a detection method for two air conditioners is provided, comprising: determining the position information of the initial edge contour of the bell mouth according to the bell mouth images of the two air conditioners; performing symmetry axis fitting on the initial edge contour according to the position information to obtain a symmetry axis segment, the two endpoints of the symmetry axis segment being the intersection points of the symmetry axis segment and the initial edge contour; extracting from the initial edge contour a plurality of edge contour line segments located at least on one side of the symmetry axis segment according to the symmetry axis segment; determining the center position of the edge contour of the bell mouth according to the plurality of edge contour line segments, and determining the size parameters of the bell mouth according to the plurality of edge contour line segments and the center position of the edge contour, the size parameters including at least one of the following: the opening diameter and the opening radius of the bell mouth; determining whether the bell mouth is qualified according to the size parameters.

[0005] Optionally, based on the symmetry axis segment, multiple edge contour line segments located at least on one side of the symmetry axis segment are extracted from the initial edge contour, including: starting from the end point of the symmetry axis segment, the initial edge contour is segmented along the clockwise direction and the counterclockwise direction to obtain the multiple edge contour line segments from the initial edge contour.

[0006] Optionally, after extracting a plurality of edge contour line segments located at least on one side of the symmetry axis segment from the initial edge contour according to the symmetry axis segment, and before determining the center position of the edge contour of the bell-mouth according to the plurality of edge contour line segments, the method further includes: performing straight line segment detection on the plurality of edge contour line segments to determine whether the straight line segment exists in the plurality of edge contour line segments by using one of the following: Hough transform method, least squares method, gradient consistency method; if the straight line segment exists in the plurality of edge contour line segments, removing the straight line segment from the plurality of edge contour line segments.

[0007] Optionally, the center position of the edge contour of the bell-mouth is determined based on the multiple edge contour segments, including: performing circle fitting on the multiple edge contour segments to obtain multiple initial circles, and calculating the center position of each initial circle and the radius of each initial circle; according to the center position of each initial circle and the radius of each initial circle, determining that the initial circle that meets predetermined conditions is an intermediate circle, and obtaining multiple intermediate circles, the predetermined conditions include: the radius of the initial circle is less than or equal to half the length of the symmetry axis segment, the center of the initial circle is located within the initial edge contour, and the Euclidean distance between the center of the initial circle and the symmetry axis segment is less than or equal to a predetermined threshold; performing mathematical and statistical analysis on the center position of the multiple intermediate circles to determine the center position of the edge contour.

[0008] Optionally, performing mathematical statistics analysis on the center positions of the plurality of intermediate circles to determine the center position of the edge contour includes: calculating an average value of the center positions of the plurality of intermediate circles to obtain the center position of the edge contour.

[0009] Optionally, the size parameters of the bell mouth are determined according to the multiple edge contour segments and the center position of the edge contour, including: extracting edge points from the edge contour segments corresponding to the multiple middle circles to obtain multiple edge point positions; calculating the Euclidean distances between the multiple edge point positions and the center position of the edge contour, and determining the radius of the bell mouth according to the multiple Euclidean distances.

[0010] Optionally, according to the position information, the initial edge contour is fitted with an axis of symmetry to obtain a symmetry axis segment, including: fitting the position information using the least squares method to obtain the axis of symmetry of the area enclosed by the initial edge contour; according to the position information, determining multiple intersection points between the initial edge contour and the axis of symmetry; determining the one with the largest length among multiple target line segments as the symmetry axis segment, and any two of the intersection points constitute a target line segment.

[0011] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0012] According to another aspect of the present application, a computer program product is provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, any one of the methods described above is implemented.

[0013] According to another aspect of the present application, an air-conditioning system is provided, comprising: two air-conditioning devices, including a bell mouth; a detection device for the two air-conditioning devices, 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 described methods.

[0014] By applying the technical solution of the present application, by determining the symmetry axis segment including the actual edge contour of the bell-mouth and the initial edge contour of the shadow, and extracting the edge contour line segments from the initial edge contour on at least one side of the symmetry axis segment, the line segments constituting the actual edge contour of the bell-mouth can be extracted, and finally these edge contour line segments are used to calculate the size parameters of the bell-mouth, which can ensure that the calculated size parameters of the bell-mouth are close to the actual size parameters of the bell-mouth, achieve the effect of finding the size parameters of the outer edge contour of the bell-mouth under the interference of shadow, reduce the problem of high false alarm rate of bell-mouth size detection caused by shadow interference, and ensure that the accuracy of the bell-mouth detection result is high. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] 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:

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for executing a detection method for two air conditioners provided in an embodiment of the present application is shown;

[0017] Figure 2A schematic flow chart of a method for detecting two devices of an air conditioner provided according to an embodiment of the present application is shown;

[0018] Figure 3 A partial schematic diagram of a side panel of two devices of an air conditioner provided according to an embodiment of the present application is shown;

[0019] Figure 4 A schematic diagram of a partial physical inspection result of a side panel of two air conditioners provided according to an embodiment of the present application is shown;

[0020] Figure 5 A grayscale schematic diagram of a bell mouth of an air conditioner provided according to an embodiment of the present application is shown;

[0021] Figure 6 A schematic diagram of a detection process of two devices of an air conditioner provided according to an embodiment of the present application is shown;

[0022] Figure 7 A schematic diagram of an initial edge profile of a bell mouth provided according to an embodiment of the present application is shown;

[0023] Figure 8 The figure shows a structural block diagram of a detection device for two devices of an air conditioner provided according to an embodiment of the present application.

[0024] The drawings include the following reference numerals:

[0025] 102, processor; 104, memory; 106, transmission equipment; 108, input and output equipment; 10, fin; 11, copper tube; 12, side panel; 13, sheet metal; 14, shadow. DETAILED DESCRIPTION

[0026] 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.

[0027] 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.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the accompanying 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.

[0029] As introduced in the background technology, there is a technical problem in the prior art that the false alarm rate of the bell mouth size detection of the two air conditioners is high. To solve the above problem, the embodiments of the present application provide a detection method for the two air conditioners, a computer-readable storage medium, a computer program product and an air conditioning system.

[0030] 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.

[0031] 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 for detecting two air conditioners 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 for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0032] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer programs corresponding to the detection method of the two air conditioners in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, the method described 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 may be connected to the mobile terminal via a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The transmission device 106 is used to receive or send data via a network. The specific example 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.

[0033] In this embodiment, a detection method for an air conditioner 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.

[0034] Figure 2 FIG. 1 is a flow chart of a method for detecting two air conditioners according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0035] Step S201, determining the position information of the initial edge contour of the bell mouth according to the bell mouth images of the two air conditioners;

[0036] Specifically, the bell mouth image is acquired by a lens of an image acquisition device facing the bell mouth. The initial edge contour includes a shadow and an edge contour of the bell mouth. The position information of the initial edge contour can specifically be the coordinate information of each point constituting the initial edge contour.

[0037] Step S202, performing symmetry axis fitting on the initial edge contour according to the position information to obtain a symmetry axis segment, wherein two end points of the symmetry axis segment are intersection points of the symmetry axis segment and the initial edge contour;

[0038] Specifically, the initial edge contour is generally an asymmetric figure, the symmetry axis segment is determined by the best symmetry axis obtained by performing symmetry axis fitting on the position information of the initial edge contour, and the symmetry axis segment is the overlapped portion of the best symmetry axis and the area surrounded by the initial edge contour, and is a straight line segment. Along the symmetry axis segment, the initial edge contour is not completely symmetrical, but has a certain degree of symmetry.

[0039] Step S203, extracting from the initial edge contour a plurality of edge contour line segments located at least on one side of the symmetry axis segment according to the symmetry axis segment;

[0040] Specifically, a plurality of the edge contour line segments may be located on the same side of the edge contour line segment, a plurality of the edge contour line segments may also be located on both sides of the symmetry axis segment, and some of the edge contour line segments may also coincide with the endpoints of the symmetry axis segment.

[0041] Step S204, determining the center position of the edge contour of the bell mouth according to the plurality of edge contour line segments, and determining the size parameters of the bell mouth according to the plurality of edge contour line segments and the center position of the edge contour, wherein the size parameters include at least one of the following: an opening diameter and an opening radius of the bell mouth;

[0042] Specifically, the edge profile of the bell mouth is the profile of the outer edge of the opening of the bell mouth.

[0043] Step S205, determining whether the bell mouth is qualified according to the size parameters.

[0044] Specifically, the size parameter is compared with the corresponding size parameter standard range to determine whether the bell mouth is qualified. If the size parameter is within the size parameter standard range, the bell mouth is determined to be qualified; otherwise, the bell mouth is determined to be unqualified.

[0045] Through the embodiment, firstly, according to the bell mouth images of the two air conditioners, the position information of the initial edge contour of the bell mouth is obtained; then, according to the position information, the symmetric axis segment of the initial edge contour is fitted; then, according to the symmetric axis segment, the part of the initial edge contour at least on one side of the symmetric axis segment is extracted to obtain a plurality of edge contour line segments; then, according to the extracted plurality of edge contour line segments, the size parameters such as the opening radius and / or the opening diameter of the bell mouth are determined; finally, according to the size parameters, whether the bell mouth is qualified is determined. The present application determines the symmetric axis segment of the initial edge contour including the actual edge contour and the shadow of the bell mouth, and extracts the edge contour line segments from the initial edge contour on at least one side of the symmetric axis segment, so that the line segments constituting the actual edge contour of the bell mouth can be extracted, and finally, these edge contour line segments are used to calculate the size parameters of the bell mouth, which can ensure that the calculated size parameters of the bell mouth are close to the actual size parameters of the bell mouth, and achieve the effect of finding the size parameters of the outer edge contour of the bell mouth under the interference of shadows, reducing the problem of high false alarm rate of bell mouth size detection caused by shadow interference, and ensuring high accuracy of the bell mouth detection result.

[0046] The inventor of the present application has found that there is a bell-mouth edge contour with shadow interference, that is, the initial edge contour is composed of part of the actual edge contour of the bell-mouth and part of the shadow contour. Since the bell-mouth is an axisymmetric figure, although the initial edge contour is not axisymmetric due to the interference of the shadow, the symmetry axis segment of the initial edge contour obtained by fitting is to make the contour points on both sides as symmetrical as possible, and the actual edge contour portion of the bell-mouth in the initial edge contour is close to the symmetry axis segment. Therefore, at least part of the multiple edge contour line segments extracted from the initial edge contour are line segments of the actual edge contour of the bell-mouth, which can ensure that the size parameters determined based on these line segments are relatively accurate.

[0047] In order to further ensure that the extracted edge contour line segment is relatively accurate, in an embodiment of the present application, the two endpoints of the symmetry axis segment are respectively located in at least one of the edge contour line segments, and part of the edge contour line segments are located on both sides of the two endpoints of the symmetry axis segment.

[0048] One endpoint of the symmetry axis segment may be located in an edge contour segment, including at the endpoint of the edge contour segment, or at a non-endpoint of the edge contour segment; the endpoint of the symmetry axis segment may also be located in two edge contour segments, for example, the endpoints of the two edge contour segments coincide, and the endpoint is located at the coincident endpoint of the two. The same is true for the other endpoint of the symmetry axis segment, which will not be described in detail here.

[0049] In addition, part of the edge contour line segments are located on both sides of one endpoint, and part of the edge contour line segments are located on both sides of the other endpoint, that is, in addition to selecting the edge contour line segments including the two endpoints of the symmetry axis segment, the edge contour line segments are also extracted from the initial edge contours on both sides of the two endpoints of the symmetry axis segment.

[0050] In actual application, Figure 3 As shown, in the production process of the two-component parts of the air conditioner, the two-component parts after expansion tube forming are composed of fins 10, copper tubes 11 and side plates 12. The side of the side plate 12 is composed of a plurality of rows of cylindrical copper tubes 11 extending through the fins 10 and sheet metal parts 13. The number and specification of the sheet metal parts 13 vary depending on the type of the two-component parts. The opening of the copper tube 11 is a bell mouth, and the opening of the bell mouth is circular. The quality of the bell mouth opening has an important influence on the subsequent copper tube opening welding process quality. Figure 3 As shown in FIG. 1 , since the copper tube 11 at the upper right corner of the first row on the side plate 12 is directly connected to the fin 10 without passing through the sheet metal part 13 of the side plate 12, the exposed fins around the copper tube 11 are uneven and have serious wrinkles, resulting in a large number of irregularly shaped shadows 14 of the copper tubes adhering to the bell mouth in the image of the two device components scanned and photographed by the industrial line scan camera directly in front of the bell mouth, as shown in FIG. Figure 4 As shown, the shadow 14 feature is very similar to the outer edge feature of the bell mouth opening, and the interference of the shadow (noise) cannot be eliminated from the image acquisition or preprocessing layer. When the interference is serious, it will affect the accuracy of the outer diameter detection of the existing visual detection algorithm, causing the algorithm to estimate the outer diameter of the bell mouth too large and be judged as unqualified and offline. Figure 4 As can be seen from the algorithm detection result diagram shown, the 32nd bell mouth in the first row was judged as unqualified due to the interference of the shadow of the fin, which caused the outer diameter detection value to be too large and was taken offline.

[0051] Figure 5 This is the grayscale original image of a device component taken by a line scan camera. Figure 5 It can be seen that there are different degrees of shadow interference at the bell mouths at both ends of each sheet metal part on the side plate. When there is serious shadow interference at the bell mouths of a large number of two-device components directly connected to the fins at both ends of the sheet metal parts, the false alarm rate during the outer diameter detection of the two devices is too high, and a large number of two-device components that need to be processed offline appear, which greatly reduces the effectiveness and efficiency of the two-device component detection.

[0052] In the present application, the bell mouth image may be an image of a bell mouth where the sheet metal part is directly connected to the fin without passing through the side plate, and other bell mouth images except this bell mouth image are detected according to the existing detection method. The bell mouth image may also be an image of any bell mouth.

[0053] Since the size parameter detection of the bell mouth at other positions is less affected by shadows except for the bell mouth where the sheet metal part is directly connected to the fin without passing through the side plate, in order to simplify the detection process, according to an exemplary embodiment, the position information of the initial edge contour of the bell mouth is determined according to the bell mouth images of the two air conditioners, including: when the size parameter of the bell mouth corresponding to the bell mouth image is detected to be greater than the standard range of the size parameter by the existing visual detection algorithm, the position information of the initial edge contour is determined according to the bell mouth image. That is, the method of the present application is only used to re-test the bell mouth whose size parameter is too large, thereby improving the detection efficiency and reducing the false detection rate.

[0054] In other words, in this application, when the two device components arrive at the bell mouth defect detection station via a conveyor belt, the visual inspection system installed at this time will use a line scan camera to capture a picture of all the bell mouths in front of the side panels of the two devices, and then the inspection system will use the existing visual inspection algorithm to detect the circular contour diameter (outer diameter) of the outer edge of the bell mouth opening for each bell mouth image in the captured picture. When a bell mouth is judged to be unqualified due to the outer diameter of the bell mouth of the fin directly connected to the copper tube being too large or too small, the inspection method of this application will be used for re-judgment. In addition, if the outer diameter of the bell mouth opening is still unqualified after re-judgment using the method of this application, it will be processed offline and manually reviewed.

[0055] Step S201, based on the bell-mouth images of the two air conditioners, a specific implementation method for determining the position information of the initial edge contour of the bell-mouth may be: performing a first predetermined processing and a second predetermined processing on the bell-mouth image to standardize the bell-mouth image to obtain a processed image, wherein the first predetermined processing includes but is not limited to: grayscale processing and binarization processing, and the second predetermined processing includes but is not limited to: flipping, rotation, low-pass filtering, median filtering, and opening and closing operations; performing edge extraction on the processed image to obtain the position information of the initial edge contour.

[0056] The edge extraction may adopt any suitable image edge extraction method, which will not be elaborated in this application.

[0057] In order to further improve the accuracy of the size detection of the bell mouths of the two air conditioners, in an optional scheme, based on the symmetry axis segment, a plurality of edge contour line segments located at least on one side of the symmetry axis segment are extracted from the initial edge contour, including: starting from the end point of the symmetry axis segment, the initial edge contour is segmented in the clockwise and counterclockwise directions, that is, the end point of the symmetry axis segment is used as the end point of two adjacent edge contour line segments, so as to obtain a plurality of edge contour line segments from the initial edge contour. In the embodiment, the initial edge contour is segmented in the clockwise and counterclockwise directions starting from the end point of the symmetry axis segment to obtain a plurality of edge contour line segments, which can further avoid missing the line segments constituting the actual edge contour of the bell mouth, thereby further ensuring the accuracy of subsequent size detection.

[0058] Specifically, the number of edge contour line segments to be extracted can be flexibly set according to actual conditions, and the specific value of the connection angle can also be flexibly set according to actual conditions, and this application does not limit this. The plurality of edge contour line segments can be continuous line segments or discontinuous line segments.

[0059] The angles between the two endpoints of the plurality of edge contour line segments and the midpoint of the symmetry axis segment can be the same, and continuous line segment extraction with equal angle steps is performed in two directions starting from the endpoints of the symmetry axis segment, which is easy to implement and can extract as many line segments of the actual edge contour of the bell mouth as possible. Of course, the angles between the two endpoints of the plurality of edge contour line segments and the midpoint of the symmetry axis segment can also be different.

[0060] After extracting multiple edge contour line segments at least located on one side of the symmetry axis segment from the initial edge contour according to the symmetry axis segment, and before determining the center position of the edge contour of the bell mouth according to the multiple edge contour line segments, the method further includes: performing straight line segment detection on the multiple edge contour line segments to determine whether the straight line segment exists in the multiple edge contour line segments; if the straight line segment exists in the multiple edge contour line segments, removing the straight line segment from the multiple edge contour line segments. In the embodiment, since the actual edge contour of the bell mouth is a curve, the line segments that do not conform to the actual edge contour characteristics of the bell mouth are removed from the edge contour line segments by straight line segment detection, thereby reducing the subsequent data processing and calculation amount.

[0061] In addition to the edge contour segment extraction method, in other embodiments, based on the symmetry axis segment, multiple edge contour segments located at least on one side of the symmetry axis segment are extracted from the initial edge contour, including: starting from the end point of the symmetry axis segment, the initial edge contour is segmented in a clockwise direction and a counterclockwise direction to obtain multiple adjacent or non-adjacent preliminary edge contour segments, at least some of the preliminary edge contour segments have different angles between the two end points and the midpoint of the symmetry axis segment; straight line segment detection is performed on the multiple preliminary edge contour segments, and when the straight line segment exists in the multiple preliminary edge contour segments, the straight line segment is eliminated from the multiple preliminary edge contour segments, and the remaining preliminary edge contour segments constitute the edge contour segments.

[0062] For another example, based on the symmetry axis segment, a plurality of edge contour line segments located at least on one side of the symmetry axis segment are extracted from the initial edge contour, including: based on the symmetry axis segment, two contour segments are extracted from the initial edge contour, the endpoints of the symmetry axis segment are located one-to-one in the contour segments, and the two endpoints of the contour segments are located on both sides of the corresponding endpoints of the symmetry axis segment; line segments are randomly selected from the two contour segments as the plurality of edge contour line segments.

[0063] Optionally, performing straight line segment detection on the plurality of edge contour line segments includes: performing straight line segment detection on the plurality of edge contour line segments by using one of the following methods to determine whether the straight line segment exists in the plurality of edge contour line segments: Hough transform method, least square method, gradient consistency method. Performing straight line segment detection on the plurality of edge contour lines by using any of the methods described above, thereby eliminating the straight line segments therein, further ensures that the amount of subsequent data calculation is small.

[0064] In some other exemplary schemes of the present application, the center position of the edge contour of the bell-mouth is determined based on the multiple edge contour segments, including: performing circle fitting on the multiple edge contour segments to obtain multiple initial circles, and calculating the center position of each initial circle and the radius of each initial circle; determining the initial circle that meets predetermined conditions as an intermediate circle based on the center position of each initial circle and the radius of each initial circle, and obtaining multiple intermediate circles, the predetermined conditions including: the radius of the initial circle is less than or equal to half the length of the symmetry axis segment, the center of the initial circle is located within the initial edge contour, and the Euclidean distance between the center of the initial circle and the symmetry axis segment is less than or equal to a predetermined threshold; performing mathematical and statistical analysis on the center position of the multiple intermediate circles to determine the center position of the edge contour. In the embodiment, the line segments that meet the actual edge contour features of the bell mouth can be further eliminated by screening the predetermined conditions, and the center position of the remaining middle circle can be processed by mathematical statistics analysis to ensure that the center position of the edge contour is relatively accurate and reliable, thereby further realizing the search for the optimal center of the outer edge contour of the bell mouth under shadow interference, further ensuring that the size parameters calculated according to the center position are relatively accurate, further reducing the false detection rate, and further solving the problem of low detection efficiency caused by false detection.

[0065] Specifically, the least squares method, RANSAC (random sampling consensus) algorithm, algebraic distance fitting, geometric distance fitting and gradient method, machine learning model analysis method or other methods can be used to perform circle fitting on the multiple edge contour segments to obtain the multiple initial circles.

[0066] In the actual application process, those skilled in the art can select any appropriate mathematical statistics analysis method to process the center positions of the multiple intermediate circles, such as taking the mode of the center positions of the multiple intermediate circles, taking the average of the center positions of the multiple intermediate circles, taking the median of the center positions of the multiple intermediate circles, etc. In an exemplary embodiment, mathematical statistics analysis is performed on the center positions of the multiple intermediate circles to determine the center position of the edge contour, including: calculating the average of the center positions of the multiple intermediate circles to obtain the center position of the edge contour. This can alleviate the problem of low reliability caused by arbitrarily selecting an intermediate circle as the edge contour.

[0067] On the basis of the embodiment, the size parameters of the bell mouth are determined according to the plurality of edge contour line segments and the center position of the edge contour, including: extracting edge points from the edge contour line segments corresponding to the plurality of middle circles to obtain a plurality of edge point positions; calculating the Euclidean distances between the plurality of edge point positions and the center position of the edge contour, and determining the radius of the bell mouth according to the plurality of Euclidean distances. This embodiment further realizes the search for the optimal radius of the outer edge contour of the bell mouth under the interference of shadows, further ensures that the bell mouth contour determined by the radius and the center position is highly close to the real bell mouth contour, further effectively reduces the detection deviation of the outer diameter of the bell mouth, and greatly improves the accuracy and efficiency of the detection results.

[0068] Specifically, the plurality of edge points may include the endpoints of the edge contour line segments corresponding to the middle circle, or may not include these endpoints. The method of extracting edge points from the edge contour line segments corresponding to the middle circles to obtain the plurality of edge point positions may be: extracting the edge points from the edge contour line segments corresponding to the middle circles according to a predetermined step length; the method of extracting edge points from the edge contour line segments corresponding to the middle circles to obtain the plurality of edge point positions may also be: randomly extracting the plurality of edge points from the edge contour line segments corresponding to the middle circles.

[0069] The specific process of determining the radius of the bell mouth according to the multiple Euclidean distances may include: using mathematical statistics to analyze the multiple Euclidean distances to obtain the radius of the bell mouth. In addition, anomaly detection may be performed on the multiple Euclidean distances to eliminate outliers; and then mathematical statistics analysis may be performed on the multiple Euclidean distances after eliminating outliers to obtain the radius of the bell mouth. The mathematical statistics analysis method includes but is not limited to taking the average, taking the mode, taking the median, etc.

[0070] A person skilled in the art may choose any suitable method to fit the axis of symmetry of a graphic. In some optional schemes, the axis of symmetry is fitted to the initial edge contour according to the position information to obtain an axis of symmetry segment, including: fitting the position information using the least squares method to obtain the axis of symmetry of the area enclosed by the initial edge contour; determining multiple intersection points between the initial edge contour and the axis of symmetry according to the position information; determining the one with the largest length among multiple target line segments as the axis of symmetry segment, and any two of the intersection points constitute a target line segment.

[0071] In addition to the above solution, the position information may also be analyzed by a machine learning model to obtain the axis of symmetry.

[0072] 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 method for detecting two devices of the air conditioner of the present application will be described in detail below in combination with specific embodiments.

[0073] Example 1

[0074] This embodiment relates to a detection process of two devices of an air conditioner, such as Figure 6 As shown, the following steps are included:

[0075] Step S1: Perform edge detection on the bell-mouth image to be processed and extract its edge contour coordinate point set:

[0076] For each bell-shaped image to be processed that is directly connected to the fins on the original images of the two devices, since the images of such bell-shaped images have a large number of irregular shapes and shadow interferences of the adhered copper tubes around the outer edge contour of the bell-shaped opening, and this interference cannot be completely eliminated from the image acquisition or preprocessing layer, edge detection is first performed on the bell-shaped image containing shadow interference, and the edge contour coordinate point set of the bell-shaped image containing shadow interference is extracted;

[0077] Step S2: Determine the optimal symmetry axis of the edge contour area of ​​the bell mouth image:

[0078] Since the outer edge of the bell mouth opening after the copper tube is formed is a standard circle, the circular contour of the original image can be extracted after image processing. The center of the real circular contour of the bell mouth passes through any of its symmetry axes. According to this characteristic, when there is shadow interference around the opening of the bell mouth image, the best symmetry axis of the edge contour area (irregular shape area) of the bell mouth image can be determined according to its edge contour coordinate point set, and the center of the real circular contour of the bell mouth will pass through this symmetry axis or be close to the best symmetry axis.

[0079] Step S3: Determine the best symmetry axis segment formed by the edge contour points of the bell mouth image:

[0080] There are two or more intersection points (edge ​​points) between the best symmetry axis and the edge contour of the extracted bell-mouth image. Every two intersection points can determine a straight line segment. The two end points of the line segment are the edge points on the edge of the bell-mouth image and are also the intersection points. All line segments formed by the intersection point pairs and any two line segments do not overlap are screened out, and the line segment with the longest length is taken as the best symmetry axis segment. If there are only two intersection points, the straight line segment formed by the two intersection points is the best symmetry axis segment.

[0081] Step S4: Segment the edge contour of the bell mouth and perform circle fitting on the edge contour curve segments:

[0082] First, taking the two edge contour points at the two ends of the best symmetry axis segment as the starting points, each edge point is segmented with equal angle steps along the edge contour in the clockwise and counterclockwise directions, and the number of segments obtained is equal to the preset value, and the angle formed by the line between the edge points at the two ends of each edge contour segment obtained by segmentation and the center point of the best symmetry axis segment is equal to the preset angle step; secondly, a straight line detection is performed on each edge contour segment obtained after segmentation, and the edge contour segment determined as a straight line segment is removed; finally, a circle fitting is performed on each edge contour curve segment determined as a non-straight line to obtain the center and radius value of the fitted circle;

[0083] Step S5: Obtain a valid fitting circle set:

[0084] A reasonable and effective fitting circle meets the following conditions: the radius of the fitting circle is less than or equal to half the length of the optimal symmetry axis segment, the center of the circle is within the edge contour area of ​​the bell mouth image, and the Euclidean distance from the optimal symmetry axis segment is less than or equal to a preset value; all fitting circles that meet the above conditions are obtained to form a fitting circle set;

[0085] Step S6: Determine the center of the circular contour of the outer edge of the bell mouth opening:

[0086] Theoretically, each fitting circle in the fitting circle set can be used as the circular contour of the outer edge of the bell mouth opening to be extracted, but the reliability of the contour extraction result is low if a fitting circle is arbitrarily selected as the contour. Here, the characteristics of all the fitting circles in the fitting circle set are comprehensively considered. First, the center points of all the fitting circles in the fitting circle set are calculated by arithmetic average method as the center point of the circular contour of the outer edge of the bell mouth opening;

[0087] Step S7: Determine the radius of the circular contour of the outer edge of the bell mouth opening:

[0088] The curve edge contour segments corresponding to all the fitted circles in the fitted circle set are discretely selected according to a preset step length to form a discrete point set, and the average of the Euclidean distances between each discrete point in the discrete point set and the center of the circular contour of the outer edge of the bell mouth opening determined in step S6 is used as the radius of the circular contour of the outer edge of the bell mouth opening;

[0089] Step S8: Result output:

[0090] According to step S6 and step S7, the circular contour of the outer edge of the bell mouth opening can be determined, and the diameter of the contour is the detection result of the bell mouth outer diameter.

[0091] Example 2

[0092] This embodiment relates to a specific detection process of two devices of an air conditioner, including the following steps:

[0093] In this embodiment, according to its implementation scenario, an original image of a certain evaporator to be processed is obtained, and image processing is performed on the original image in the pixel domain coordinate system. The conversion measurement value RM between pixels and actual physical dimensions is: 0.02106149115 (mm / pixel), which means that the real-time physical dimension corresponding to one pixel on the image is 0.02106149115 mm. The relevant preset values ​​and thresholds involved in this embodiment are determined according to the actual debugging results;

[0094] First, the original bell-mouth image is converted into a two-dimensional grayscale image, and then the grayscale original image is standardized through image processing operations such as horizontal flipping, rotation, low-pass filtering, median filtering, opening and closing operations, etc. The edge of each bell-mouth image to be processed on the grayscale original image after the standardized operation is detected, and its edge contour coordinate point set is extracted. Figure 7 This is a schematic diagram of extracting the circular contour of the outer edge of a bell mouth to be processed. Figure 7 It can be seen that the edge contour area of ​​the bell-mouth image with shadow interference extracted by edge detection has no regular shape, and the circular contour of the outer edge of the bell-mouth opening is within this area;

[0095] Secondly, according to Figure 7 The coordinate point set of the edge contour of the bell-mouth image with shadow interference is extracted, and the optimal symmetry axis of the bell-mouth image edge contour area is fitted by the least square method, P 18 P and P9 are the two intersection points (edge ​​contour points) of the optimal symmetry axis and the edge contour of the bell mouth image, then P 18 The straight line segment formed by P and P9 is the best symmetrical axis segment;

[0096] Then, P 18 The edge contour points P and P9 are taken as the starting points. Each edge point is segmented along the edge contour in the clockwise and counterclockwise directions according to the preset angle step of θ. The number of segments obtained in each direction is equal to the preset value N. The total number of segments is 4N. The coordinate point C in the figure is the center point of the optimal symmetric axis segment. 18 As the starting point, take 4 edge segments along the edge contour in the clockwise direction, which are line segments P 18 P1, line segment P1P2, line segment P2P3 and line segment P3P4, the angle formed by the line between the edge points at both ends of each edge segment and point C is equal to θ, that is , , and The value is equal to θ, and four edge segments are taken in the counterclockwise direction according to the above method. Similarly, the starting point P9 is also taken according to P 18The same method is used to perform edge segmentation operations to obtain the corresponding edge segments. Then, the Hough transform method is used to perform straight line detection and judgment on each edge contour segment obtained after segmentation. The contour segments P6P7, P7P8, P8P9, and P9P 10 , P 10 P 11 and P 12 P 13 The edge contour segments that are judged as straight line segments are removed, and each edge contour curve segment that is judged as non-straight line is fitted with a circle using the Hough transform method to obtain the center and radius value of the fitted circle. Point C1 is the contour segment P 18 Point C2 is the center of the fitting circle of contour segment P1P2, point C3 is the center of the fitting circle of contour segment P2P3, point C4 is the center of the fitting circle of contour segment P3P4, and so on. It can be seen from the figure that the fitting circles with centers C6, C12, C15 and C16 do not simultaneously meet the condition that the radius of the fitting circle is less than or equal to half of the length of the optimal symmetry axis segment, and the center is in the edge contour area of ​​the bell-mouth image and the Euclidean distance to the symmetry axis segment is less than or equal to the preset value and is ignored. The fitting circles with centers C1, C2, C3, C4, C17 and C18 constitute a valid fitting circle set;

[0097] Again, calculate the arithmetic mean of the center coordinates of all the fitting circles in the fitting circle set according to the following formula to obtain the coordinates of the center point position: : , .

[0098] in, is the coordinate point of the center of the i-th fitting circle, n is the number of fitting circles, and point A in the figure is the center point of the centers of all fitting circles in the fitting circle set, which is used as the center of the circular contour of the outer edge of the bell mouth opening;

[0099] Finally, all the curve edge contour segments are discretely selected according to the preset step size M, such as Figure 7 As shown, B1, B2 and B3 are edge contour segments P 18 The discrete sampling points of P1, B4, B5, B6 and B7 are the discrete sampling points of the edge contour segment P1P2, and so on. Discrete points are taken for all the remaining edge contour segments to obtain their discrete point set [S={B1, B2, B3, B4, B5, B6, B7, ..., BN}], where N is the number of discrete points. The Euclidean distance between each discrete point in the discrete point set and point A is calculated respectively, and its mean is calculated according to the following formula: ;

[0100] in, is the Euclidean distance between the ith discrete point and point A, N is the number of discrete points, and the mean R is used as the radius of the circular contour of the outer edge of the bell mouth opening. The circular contour of the outer edge of the bell mouth opening can be determined by point A and radius R, and the diameter of the contour is the detection result of the bell mouth outer diameter.

[0101] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0102] The embodiment of the present application also provides a detection device for two air conditioners. It should be noted that the detection device for two air conditioners in the embodiment of the present application can be used to execute the detection method for two air conditioners provided in the embodiment of the present application. The device is used to implement the embodiments and preferred implementations, 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 devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0103] The following is an introduction to the detection device for the two devices of the air conditioner provided in the embodiment of the present application.

[0104] Figure 8 Schematic diagram of a detection device for two air conditioners according to an embodiment of the present application. Figure 8 As shown, the device comprises:

[0105] A first determining unit 20 is used to determine the position information of the initial edge contour of the bell mouth according to the bell mouth images of the air conditioner;

[0106] Specifically, the bell mouth image is acquired by a lens of an image acquisition device facing the bell mouth. The initial edge contour includes a shadow and an edge contour of the bell mouth. The position information of the initial edge contour can specifically be the coordinate information of each point constituting the initial edge contour.

[0107] A fitting unit 21 is used to perform symmetry axis fitting on the initial edge profile according to the position information to obtain a symmetry axis segment, wherein two end points of the symmetry axis segment are intersection points of the symmetry axis segment and the initial edge profile;

[0108] Specifically, the initial edge contour is generally an asymmetric figure, the symmetry axis segment is determined by the best symmetry axis obtained by performing symmetry axis fitting on the position information of the initial edge contour, and the symmetry axis segment is the overlapped portion of the best symmetry axis and the area surrounded by the initial edge contour, and is a straight line segment. Along the symmetry axis segment, the initial edge contour is not completely symmetrical, but has a certain degree of symmetry.

[0109] An extraction unit 22, configured to extract, from the initial edge contour, a plurality of edge contour line segments located at least on one side of the symmetry axis segment according to the symmetry axis segment;

[0110] Specifically, a plurality of the edge contour line segments may be located on the same side of the edge contour line segment, a plurality of the edge contour line segments may also be located on both sides of the symmetry axis segment, and some of the edge contour line segments may also coincide with the endpoints of the symmetry axis segment.

[0111] A second determining unit 23 is used to determine the center position of the edge contour of the bell mouth according to the plurality of edge contour line segments, and determine the size parameters of the bell mouth according to the plurality of edge contour line segments and the center position of the edge contour, wherein the size parameters include at least one of the following: an opening diameter and an opening radius of the bell mouth;

[0112] Specifically, the edge profile of the bell mouth is the profile of the outer edge of the opening of the bell mouth.

[0113] The third determination unit 24 is used to determine whether the bell mouth is qualified according to the size parameter.

[0114] Specifically, the size parameter is compared with the corresponding size parameter standard range to determine whether the bell mouth is qualified. If the size parameter is within the size parameter standard range, the bell mouth is determined to be qualified; otherwise, the bell mouth is determined to be unqualified.

[0115] According to the embodiment, the first determination unit obtains the position information of the initial edge contour of the bell mouth according to the bell mouth images of the two air conditioners; the fitting unit obtains the symmetric axis segment of the initial edge contour according to the position information; the extraction unit extracts the part of the initial edge contour located at least on one side of the symmetric axis segment according to the symmetric axis segment to obtain multiple edge contour line segments; the second determination unit determines the size parameters of the opening radius and / or opening diameter of the bell mouth according to the extracted multiple edge contour line segments; the third determination unit determines whether the bell mouth is qualified according to the size parameters. The present application determines the symmetric axis segment of the initial edge contour including the actual edge contour and the shadow of the bell mouth, and extracts the edge contour line segments from the initial edge contour on at least one side of the symmetric axis segment, so that the line segments constituting the actual edge contour of the bell mouth can be extracted, and finally the size parameters of the bell mouth are calculated by these edge contour line segments, which can ensure that the calculated size parameters of the bell mouth are close to the actual size parameters of the bell mouth, and achieves the effect of finding the size parameters of the outer edge contour of the bell mouth under the interference of shadows, reduces the problem of high false alarm rate of bell mouth size detection caused by shadow interference, and ensures high accuracy of the bell mouth detection result.

[0116] The detection device for the two air conditioners includes a processor and a memory, and the first determination unit, the fitting unit, the extraction unit, the second determination unit, and the third determination unit are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0117] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be provided, and the problem of high false alarm rate of the bell mouth size detection of the two air conditioners in the prior art can be solved by adjusting the kernel parameters.

[0118] 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.

[0119] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium 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 detection method for the two air conditioners.

[0120] Specifically, the detection method of the two devices of the air conditioner includes:

[0121] Step S201, determining the position information of the initial edge contour of the bell mouth according to the bell mouth images of the two air conditioners;

[0122] Specifically, the bell mouth image is acquired by a lens of an image acquisition device facing the bell mouth. The initial edge contour includes a shadow and an edge contour of the bell mouth. The position information of the initial edge contour can specifically be the coordinate information of each point constituting the initial edge contour.

[0123] Step S202, performing symmetry axis fitting on the initial edge contour according to the position information to obtain a symmetry axis segment, wherein two end points of the symmetry axis segment are intersection points of the symmetry axis segment and the initial edge contour;

[0124] Specifically, the initial edge contour is generally an asymmetric figure, the symmetry axis segment is determined by the best symmetry axis obtained by performing symmetry axis fitting on the position information of the initial edge contour, and the symmetry axis segment is the overlapped portion of the best symmetry axis and the area surrounded by the initial edge contour, and is a straight line segment. Along the symmetry axis segment, the initial edge contour is not completely symmetrical, but has a certain degree of symmetry.

[0125] Step S203, extracting from the initial edge contour a plurality of edge contour line segments located at least on one side of the symmetry axis segment according to the symmetry axis segment;

[0126] Specifically, a plurality of the edge contour line segments may be located on the same side of the edge contour line segment, a plurality of the edge contour line segments may also be located on both sides of the symmetry axis segment, and some of the edge contour line segments may also coincide with the endpoints of the symmetry axis segment.

[0127] Step S204, determining the center position of the edge contour of the bell mouth according to the plurality of edge contour line segments, and determining the size parameters of the bell mouth according to the plurality of edge contour line segments and the center position of the edge contour, wherein the size parameters include at least one of the following: an opening diameter and an opening radius of the bell mouth;

[0128] Specifically, the edge profile of the bell mouth is the profile of the outer edge of the opening of the bell mouth.

[0129] Step S205, determining whether the bell mouth is qualified according to the size parameters.

[0130] Specifically, the size parameter is compared with the corresponding size parameter standard range to determine whether the bell mouth is qualified. If the size parameter is within the size parameter standard range, the bell mouth is determined to be qualified; otherwise, the bell mouth is determined to be unqualified.

[0131] Optionally, based on the symmetry axis segment, multiple edge contour line segments located at least on one side of the symmetry axis segment are extracted from the initial edge contour, including: starting from the end point of the symmetry axis segment, the initial edge contour is segmented along the clockwise direction and the counterclockwise direction to obtain the multiple edge contour line segments from the initial edge contour.

[0132] Optionally, after extracting a plurality of edge contour line segments located at least on one side of the symmetry axis segment from the initial edge contour according to the symmetry axis segment, and before determining the center position of the edge contour of the bell-mouth according to the plurality of edge contour line segments, the method further includes: performing straight line segment detection on the plurality of edge contour line segments to determine whether the straight line segment exists in the plurality of edge contour line segments by using one of the following: Hough transform method, least squares method, gradient consistency method; if the straight line segment exists in the plurality of edge contour line segments, removing the straight line segment from the plurality of edge contour line segments.

[0133] Optionally, the center position of the edge contour of the bell-mouth is determined based on the multiple edge contour segments, including: performing circle fitting on the multiple edge contour segments to obtain multiple initial circles, and calculating the center position of each initial circle and the radius of each initial circle; according to the center position of each initial circle and the radius of each initial circle, determining that the initial circle that meets predetermined conditions is an intermediate circle, and obtaining multiple intermediate circles, the predetermined conditions include: the radius of the initial circle is less than or equal to half the length of the symmetry axis segment, the center of the initial circle is located within the initial edge contour, and the Euclidean distance between the center of the initial circle and the symmetry axis segment is less than or equal to a predetermined threshold; performing mathematical and statistical analysis on the center position of the multiple intermediate circles to determine the center position of the edge contour.

[0134] Optionally, performing mathematical statistics analysis on the center positions of the plurality of intermediate circles to determine the center position of the edge contour includes: calculating an average value of the center positions of the plurality of intermediate circles to obtain the center position of the edge contour.

[0135] Optionally, the size parameters of the bell mouth are determined according to the multiple edge contour segments and the center position of the edge contour, including: extracting edge points from the edge contour segments corresponding to the multiple middle circles to obtain multiple edge point positions; calculating the Euclidean distances between the multiple edge point positions and the center position of the edge contour, and determining the radius of the bell mouth according to the multiple Euclidean distances.

[0136] Optionally, according to the position information, the initial edge contour is fitted with an axis of symmetry to obtain a symmetry axis segment, including: fitting the position information using the least squares method to obtain the axis of symmetry of the area enclosed by the initial edge contour; according to the position information, determining multiple intersection points between the initial edge contour and the axis of symmetry; determining the one with the largest length among multiple target line segments as the symmetry axis segment, and any two of the intersection points constitute a target line segment.

[0137] An embodiment of the present invention provides a processor, which is used to run a program, wherein the detection method of the two air conditioners is executed when the program is running.

[0138] Specifically, the detection method of the two devices of the air conditioner includes:

[0139] Step S201, determining the position information of the initial edge contour of the bell mouth according to the bell mouth images of the two air conditioners;

[0140] Step S202, performing symmetry axis fitting on the initial edge contour according to the position information to obtain a symmetry axis segment, wherein two end points of the symmetry axis segment are intersection points of the symmetry axis segment and the initial edge contour;

[0141] Step S203, extracting from the initial edge contour a plurality of edge contour line segments located at least on one side of the symmetry axis segment according to the symmetry axis segment;

[0142] Step S204, determining the center position of the edge contour of the bell mouth according to the plurality of edge contour line segments, and determining the size parameters of the bell mouth according to the plurality of edge contour line segments and the center position of the edge contour, wherein the size parameters include at least one of the following: an opening diameter and an opening radius of the bell mouth;

[0143] Step S205, determining whether the bell mouth is qualified according to the size parameters.

[0144] 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:

[0145] Step S201, determining the position information of the initial edge contour of the bell mouth according to the bell mouth images of the two air conditioners;

[0146] Step S202, performing symmetry axis fitting on the initial edge contour according to the position information to obtain a symmetry axis segment, wherein two end points of the symmetry axis segment are intersection points of the symmetry axis segment and the initial edge contour;

[0147] Step S203, extracting from the initial edge contour a plurality of edge contour line segments located at least on one side of the symmetry axis segment according to the symmetry axis segment;

[0148] Step S204, determining the center position of the edge contour of the bell mouth according to the plurality of edge contour line segments, and determining the size parameters of the bell mouth according to the plurality of edge contour line segments and the center position of the edge contour, wherein the size parameters include at least one of the following: an opening diameter and an opening radius of the bell mouth;

[0149] Step S205, determining whether the bell mouth is qualified according to the size parameters.

[0150] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0151] Optionally, based on the symmetry axis segment, multiple edge contour line segments located at least on one side of the symmetry axis segment are extracted from the initial edge contour, including: starting from the end point of the symmetry axis segment, the initial edge contour is segmented along the clockwise direction and the counterclockwise direction to obtain the multiple edge contour line segments from the initial edge contour.

[0152] Optionally, after extracting a plurality of edge contour line segments located at least on one side of the symmetry axis segment from the initial edge contour according to the symmetry axis segment, and before determining the center position of the edge contour of the bell-mouth according to the plurality of edge contour line segments, the method further includes: performing straight line segment detection on the plurality of edge contour line segments to determine whether the straight line segment exists in the plurality of edge contour line segments by using one of the following: Hough transform method, least squares method, gradient consistency method; if the straight line segment exists in the plurality of edge contour line segments, removing the straight line segment from the plurality of edge contour line segments.

[0153] Optionally, the center position of the edge contour of the bell-mouth is determined based on the multiple edge contour segments, including: performing circle fitting on the multiple edge contour segments to obtain multiple initial circles, and calculating the center position of each initial circle and the radius of each initial circle; according to the center position of each initial circle and the radius of each initial circle, determining that the initial circle that meets predetermined conditions is an intermediate circle, and obtaining multiple intermediate circles, the predetermined conditions include: the radius of the initial circle is less than or equal to half the length of the symmetry axis segment, the center of the initial circle is located within the initial edge contour, and the Euclidean distance between the center of the initial circle and the symmetry axis segment is less than or equal to a predetermined threshold; performing mathematical and statistical analysis on the center position of the multiple intermediate circles to determine the center position of the edge contour.

[0154] Optionally, performing mathematical statistics analysis on the center positions of the plurality of intermediate circles to determine the center position of the edge contour includes: calculating an average value of the center positions of the plurality of intermediate circles to obtain the center position of the edge contour.

[0155] Optionally, the size parameters of the bell mouth are determined according to the multiple edge contour segments and the center position of the edge contour, including: extracting edge points from the edge contour segments corresponding to the multiple middle circles to obtain multiple edge point positions; calculating the Euclidean distances between the multiple edge point positions and the center position of the edge contour, and determining the radius of the bell mouth according to the multiple Euclidean distances.

[0156] Optionally, according to the position information, the initial edge contour is fitted with an axis of symmetry to obtain a symmetry axis segment, including: fitting the position information using the least squares method to obtain the axis of symmetry of the area enclosed by the initial edge contour; according to the position information, determining multiple intersection points between the initial edge contour and the axis of symmetry; determining the one with the largest length among multiple target line segments as the symmetry axis segment, and any two of the intersection points constitute a target line segment.

[0157] The present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement at least the following method steps:

[0158] Step S201, determining the position information of the initial edge contour of the bell mouth according to the bell mouth images of the two air conditioners;

[0159] Step S202, performing symmetry axis fitting on the initial edge contour according to the position information to obtain a symmetry axis segment, wherein two end points of the symmetry axis segment are intersection points of the symmetry axis segment and the initial edge contour;

[0160] Step S203, extracting from the initial edge contour a plurality of edge contour line segments located at least on one side of the symmetry axis segment according to the symmetry axis segment;

[0161] Step S204, determining the center position of the edge contour of the bell mouth according to the plurality of edge contour line segments, and determining the size parameters of the bell mouth according to the plurality of edge contour line segments and the center position of the edge contour, wherein the size parameters include at least one of the following: an opening diameter and an opening radius of the bell mouth;

[0162] Step S205, determining whether the bell mouth is qualified according to the size parameters.

[0163] Optionally, based on the symmetry axis segment, multiple edge contour line segments located at least on one side of the symmetry axis segment are extracted from the initial edge contour, including: starting from the end point of the symmetry axis segment, the initial edge contour is segmented along the clockwise direction and the counterclockwise direction to obtain the multiple edge contour line segments from the initial edge contour.

[0164] Optionally, after extracting a plurality of edge contour line segments located at least on one side of the symmetry axis segment from the initial edge contour according to the symmetry axis segment, and before determining the center position of the edge contour of the bell-mouth according to the plurality of edge contour line segments, the method further includes: performing straight line segment detection on the plurality of edge contour line segments to determine whether the straight line segment exists in the plurality of edge contour line segments by using one of the following: Hough transform method, least squares method, gradient consistency method; if the straight line segment exists in the plurality of edge contour line segments, removing the straight line segment from the plurality of edge contour line segments.

[0165] Optionally, the center position of the edge contour of the bell-mouth is determined based on the multiple edge contour segments, including: performing circle fitting on the multiple edge contour segments to obtain multiple initial circles, and calculating the center position of each initial circle and the radius of each initial circle; according to the center position of each initial circle and the radius of each initial circle, determining that the initial circle that meets predetermined conditions is an intermediate circle, and obtaining multiple intermediate circles, the predetermined conditions include: the radius of the initial circle is less than or equal to half the length of the symmetry axis segment, the center of the initial circle is located within the initial edge contour, and the Euclidean distance between the center of the initial circle and the symmetry axis segment is less than or equal to a predetermined threshold; performing mathematical and statistical analysis on the center position of the multiple intermediate circles to determine the center position of the edge contour.

[0166] Optionally, performing mathematical statistics analysis on the center positions of the plurality of intermediate circles to determine the center position of the edge contour includes: calculating an average value of the center positions of the plurality of intermediate circles to obtain the center position of the edge contour.

[0167] Optionally, the size parameters of the bell mouth are determined according to the multiple edge contour segments and the center position of the edge contour, including: extracting edge points from the edge contour segments corresponding to the multiple middle circles to obtain multiple edge point positions; calculating the Euclidean distances between the multiple edge point positions and the center position of the edge contour, and determining the radius of the bell mouth according to the multiple Euclidean distances.

[0168] Optionally, according to the position information, the initial edge contour is fitted with an axis of symmetry to obtain a symmetry axis segment, including: fitting the position information using the least squares method to obtain the axis of symmetry of the area enclosed by the initial edge contour; according to the position information, determining multiple intersection points between the initial edge contour and the axis of symmetry; determining the one with the largest length among multiple target line segments as the symmetry axis segment, and any two of the intersection points constitute a target line segment.

[0169] An embodiment of the present application also provides an air-conditioning system, comprising: two air-conditioning devices, including a bell mouth; a detection device for the two air-conditioning devices, 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 described methods.

[0170] Obviously, those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose 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 herein, 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.

[0171] 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 combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0172] 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 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0173] 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.

[0174] 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.

[0175] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0176] 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.

[0177] 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, magnetic tape disk storage 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.

[0178] 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.

[0179] 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 two devices of an air conditioner, characterized in that: include: Determine the position information of the initial edge contour of the bell mouth according to the bell mouth images of the two air conditioners; According to the position information, a symmetry axis fitting is performed on the initial edge contour to obtain a symmetry axis segment, wherein two end points of the symmetry axis segment are intersection points of the symmetry axis segment and the initial edge contour; According to the symmetry axis segment, extracting from the initial edge contour a plurality of edge contour line segments located at least on one side of the symmetry axis segment; Determine the center position of the edge contour of the bell mouth according to the plurality of edge contour line segments, and determine the size parameters of the bell mouth according to the plurality of edge contour line segments and the center position of the edge contour, wherein the size parameters include at least one of the following: the opening diameter and the opening radius of the bell mouth; According to the size parameters, determine whether the bell mouth is qualified. After extracting a plurality of edge contour line segments at least located on one side of the symmetry axis segment from the initial edge contour according to the symmetry axis segment, and before determining the center position of the edge contour of the bell mouth according to the plurality of edge contour line segments, the method further includes: Performing straight line segment detection on the plurality of edge contour line segments to determine whether the straight line segment exists in the plurality of edge contour line segments; In the case that the straight line segment exists in the plurality of edge contour line segments, the straight line segment is removed from the plurality of edge contour line segments.

2. The method according to claim 1, characterized in that According to the symmetry axis segment, a plurality of edge contour line segments located at least on one side of the symmetry axis segment are extracted from the initial edge contour, including: The initial edge contour is segmented in a clockwise direction and a counterclockwise direction starting from the end point of the symmetry axis segment, so as to obtain a plurality of edge contour line segments from the initial edge contour.

3. The method according to claim 1, characterized in that Determining the center position of the edge contour of the bell mouth according to the plurality of edge contour line segments includes: Performing circle fitting on the plurality of edge contour line segments to obtain a plurality of initial circles, and calculating the center position and radius of each of the initial circles; According to the center position and radius of each of the initial circles, determine that the initial circle that meets a predetermined condition is an intermediate circle, and obtain multiple intermediate circles, wherein the predetermined condition includes: the radius of the initial circle is less than or equal to half of the length of the symmetry axis segment, the center of the initial circle is located within the initial edge contour, and the Euclidean distance between the center of the initial circle and the symmetry axis segment is less than or equal to a predetermined threshold; Mathematical statistics are performed on the center positions of the plurality of intermediate circles to determine the center position of the edge contour.

4. The method according to claim 3, characterized in that: Performing mathematical statistical analysis on the center positions of the plurality of intermediate circles to determine the center position of the edge contour includes: The average value of the center positions of the plurality of intermediate circles is calculated to obtain the center position of the edge contour.

5. The method according to claim 3, characterized in that: Determining the size parameters of the bell mouth according to the plurality of edge contour line segments and the center position of the edge contour includes: Extract edge points from the edge contour line segments corresponding to the plurality of middle circles to obtain a plurality of edge point positions; The Euclidean distances between the positions of the plurality of edge points and the center position of the edge contour are calculated, and the radius of the bell mouth is determined according to the plurality of Euclidean distances.

6. The method according to any one of claims 1 to 5, characterized in that According to the position information, the initial edge profile is subjected to symmetry axis fitting to obtain a symmetry axis segment, including: Fitting the position information using the least square method to obtain the symmetry axis of the area surrounded by the initial edge contour; Determining a plurality of intersection points between the initial edge contour and the symmetry axis according to the position information; The longest one among the plurality of target line segments is determined to be the symmetry axis segment, and any two intersection points constitute a target line segment.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium 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 method according to any one of claims 1 to 6.

8. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An air conditioning system, characterized in that: include: Two air conditioners, including bell mouth; The detection device for the air conditioner comprises 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 claims 1 to 6.

Images