Method for detecting missing connecting plates in a chain and electronic device

Abstract

The embodiments of the present disclosure disclose a method for detecting missing connecting plates in a chain and an electronic device. The method comprises the following: capturing an original chain image of a chain to be detected and determining a single-line detection area image between the respective chain pins according to a type of chain to be detected and the original chain image; extracting gaps in the single-line detection area image and determining a corresponding gap width for each gap for any single-line detection area image; and determining the line width of the single-line detection area image and detecting, according to the line width, the gap width, and the type of chain to be detected, whether connecting plates are missing in a line corresponding to the single-line detection area image.Based on this, the present disclosure can automatically recognize the respective lines in the chain one after the other and, using the line width and gap width, determine more intuitively whether connecting plates are missing in the respective lines, thereby avoiding the problems of missed detection that occur during manual inspection. This leads to higher detection efficiency and accuracy.

Description

Cross-reference to related registrations

[0001] The present disclosure claims priority from the Chinese patent application filed on July 28, 2023, with the Chinese State Intellectual Property Office under application number 2023109356186 and entitled “Method for detecting missing connecting plates in a chain and electronic device”, the entire contents of which are hereby incorporated into the present disclosure by reference. Technical field

[0002] Embodiments of the present disclosure relate to the technical field of chain testing and in particular to a method and an electronic device for detecting missing connecting plates in a chain. State of the art

[0003] The chain is a crucial component in an automotive transmission, and its quality plays a vital role in the transmission's performance and normal operation. Therefore, chains must undergo quality inspection before leaving the factory, particularly regarding the potential absence of connecting plates.

[0004] Currently, quality control of chains is usually performed manually. However, a chain typically contains hundreds of chain pins, and each pin has multiple connecting plates. Due to the sheer number of pins, manual inspection carries the risk of missing a defect, a risk that increases further on assembly lines. Description of the invention

[0005] The embodiments of the present disclosure provide a method and an electronic device for detecting missing connecting plates (tab plates) in a chain in order to avoid a lack of detection.

[0006] In some embodiments, the present disclosure provides a method for detecting missing connecting plates in a chain, wherein the method may comprise the following: Capturing an original chain image of a chain to be detected and determining a single-row detection area image between the chain pins according to a type of chain to be detected and the original chain image; Extracting gaps in the single-row recognition area image and determining a corresponding gap width for each gap for any single-row recognition area image; and Determining the line width of the single-line recognition area image and recognizing, according to the line width, the gap width, and the type of chain to be recognized, whether connecting plates are missing in a line corresponding to the single-line recognition area image.

[0007] In some other embodiments, the present disclosure also provides an electronic device which may include the following: one or more processors; a storage device for storing one or more programs, and wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method for detecting missing connecting plates in a chain according to any embodiment of the present disclosure.

[0008] The technical solution of the embodiments of the present disclosure comprises capturing an original chain image of a chain to be detected and determining a single-line detection area image between the chain pins according to a type of chain to be detected and the original chain image; extracting gaps in the single-line detection area image and determining a respective corresponding gap width for each gap for any single-line detection area image; and determining a line width of the single-line detection area image and detecting, according to the line width, the gap width, and the type of chain to be detected, whether connecting plates are missing in a line corresponding to the single-line detection area image.Based on this, the present disclosure can automatically detect the respective lines in the chain one after the other and, using the line width and gap width, determine more intuitively whether connecting plates are missing in the respective lines, thereby avoiding the problems of missed detection that occur during manual inspection. This leads to higher detection efficiency and accuracy.

[0009] Furthermore, according to the present disclosure, a first chain pin is determined in the original chain pattern based on the type of chain to be detected and the original chain pattern. After obtaining the original chain pattern, the first chain pin can be identified in the original chain pattern, provided the type of chain to be detected is known. Based on this method, the operator can mount the chain arbitrarily on the test fixture without having to manually determine the first chain pin and place it in a fixed position, thereby improving assembly efficiency during testing and further increasing detection efficiency. Brief description of the drawings Fig. Figure 1 is a schematic flowchart of a method provided in some embodiments of the present disclosure for detecting missing connecting plates in a chain; Fig. Figure 2 is a schematic diagram of a single-line area image provided in some embodiments of the present disclosure; Fig. Figure 3 is a schematic diagram of an enclosing image of a single-line main body provided in some embodiments of the present disclosure; Fig. Figure 4 is a schematic structural diagram of a device provided in some other embodiments of the present disclosure for detecting missing connecting plates in a chain; and Fig. Figure 5 is a schematic structure diagram of an electronic device provided in some further embodiments of the present disclosure. Description of the embodiments

[0010] The present disclosure is further explained in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described here serve only to illustrate the present disclosure and do not constitute a limitation of the present disclosure. Furthermore, it should be noted that, for the sake of simplicity, the accompanying drawings depict only some structures related to the present disclosure, but not all structures.

[0011] Fig. Figure 1 is a schematic flowchart of the method provided in some embodiments of the present disclosure for detecting missing connecting plates in a chain. The present embodiment is applicable to a scenario of detecting missing connecting plates in a chain; the method can be carried out by a device for detecting missing connecting plates in a chain; and the device can be implemented in the form of hardware and / or software and can generally be integrated into an electronic device such as a computer with data processing capabilities. Specifically, the method comprises the following steps: Step 101: Capturing an original chain image of a chain to be detected and determining a single-row detection area image between the chain pins according to a type of chain to be detected and the original chain image.

[0012] In this step, the chain to be detected is rotated using the associated hardware device. During rotation, the image information of the chain is captured line by line until the number of captured lines reaches a preset threshold to obtain the original chain image. This preset threshold is greater than the number of pixel lines corresponding to the size of the chain to be detected.

[0013] The image information can be captured using a line scan camera. Since the line scan camera typically has only one line of light-sensitive units, only one line can usually be captured during the acquisition process, and the number of capture lines in this step is the number of capture lines of the line scan camera.

[0014] Furthermore, the number of pixel lines corresponding to the size of the chain to be detected refers to the number of lines that the line scan camera must capture to detect the entire chain. The specific setting for the number of pixel lines corresponding to the size of the chain to be detected can be adjusted to different values ​​depending on the type of chain.

[0015] In a specific embodiment, the preset threshold can be determined according to the number of pixel rows corresponding to the size of the chain to be detected. For example, if the number of pixel rows corresponding to the size of the chain to be detected is 12,000, the preset threshold can be set to 12,200; that is, the preset threshold simply needs to be greater than the number of pixel rows corresponding to the size of the chain to be detected. Based on this setting, it can be ensured that all elements of the chain to be detected are captured, thus avoiding partial omissions.

[0016] Since the display length of the currently captured image is limited by the display device, the capture process can be performed multiple times, with each capture occurring continuously and without interruption. The repeatedly captured images are then combined in the capture sequence to obtain the original chain image.

[0017] Furthermore, each chain has a corresponding identification code to differentiate the results between the respective chains. The identification code can be affixed to the chain as a two-dimensional code or etched directly onto it. Before capturing the original chain image, the identification code of the chain to be recognized is obtained by scanning the two-dimensional code. Alternatively, the identification code can also be affixed or etched directly onto the chain. The identification code is recognized by an image capture device, and in the subsequent processing, it is used to differentiate the capture process and the capture results for each chain.

[0018] Since incomplete rows may occur at the beginning and end of the original chain image, the incomplete rows at the beginning and end of the original chain image can be removed, i.e., the chain pins at the beginning and end of the original chain image can be removed.

[0019] Specifically, an image of the chain main body can first be extracted from the original chain image, and the information of the corner point coordinates of the image of the chain main body is determined; according to the information of the corner point coordinates, the chain bolts at the beginning and end of the original chain image are removed.

[0020] The image of the chain main body refers to the part of the connecting plates remaining after the removal of the two ends of the part of the chain pins projecting beyond the connecting plates, wherein the image of the chain main body is rectangular and the four vertices of the rectangle are the vertices of the image of the chain main body.

[0021] During the removal process, a rectangular frame is first created using the coordinate information of any corner point, where the center point of the rectangular frame is the corner point and the length and width of the rectangular frame are all preset values. Then, an image recognition algorithm identifies the chain pin located at the furthest end of the target direction within the rectangular frame, and then the entire row of that chain pin is removed.

[0022] The direction of the target varies depending on the position of the corner point; for a corner point located at the beginning, the direction of the target is the direction pointing towards the beginning, and for a corner point located at the end, the direction of the target is the direction pointing towards the end.

[0023] Furthermore, when determining the single-line detection area image in this step, since the arrangement of the chain pins and connecting plates in chains of the same type is fixed and each row has a corresponding row number identifier, the first chain pin must first be identified to facilitate the subsequent determination of which row is missing connecting plates. Then, the single-line detection area corresponding to each row number identifier is determined in the chain to be detected. With this method, only the row number identifier for the missing connecting plates needs to be displayed subsequently, and the operator can thus assign the corresponding row in the actual chain.

[0024] Specifically, based on the type of chain to be detected and the original chain image, the first chain pin in the original chain image can first be determined; then, starting from the first chain pin, a preset number of single-row detection area images corresponding to the type of chain to be detected are extracted, where the single-row detection area image is the area image between two chain pins.

[0025] Specifically, when determining the first chain pin, the distances between the individual chain pins in the original chain pattern can first be determined. Based on the sequence of these distances, the target chain pin that meets the conditions for the corresponding preset first chain pin of the type of chain to be detected is identified. The target chain pin is then determined as the first chain pin in the original chain pattern. It should be noted that each type of chain to be detected has exactly one first chain pin.

[0026] In a specific example, the spacing between the chain pins is distributed differently depending on the type of chain being detected. For example, for a chain of the first preset type, the total number of chain pins is m, and the first chain pin is the o-th of n low continuous intervals; for a chain of the second preset type, the total number of chain pins is p, and the first chain pin is the r-th of q low continuous intervals; for a chain of the third preset type, the total number of chain pins is s, and the first chain pin is the u-th of t low continuous intervals.

[0027] The low continuous distances refer to continuous distances with low values. In this embodiment, the distribution of distances exhibits a relatively clear distinction between high and low values, so that the continuous low values ​​can be determined based on the characteristics of the distance distribution.

[0028] Furthermore, when determining the distance between individual chain pins in the original chain image, the portion of the chain pins protruding beyond the connecting plates in the captured image may be relatively short due to factors such as the rotation of the chain being detected. Since the distance calculation for determining the first chain pin targets the portion of the chain pins protruding beyond the connecting plates, if this portion is relatively short, it may not be within the calculated range for the chain pin spacing. This leads to abnormal data when positioning the first chain pin. Therefore, the image of the chain pin segment can first be extracted from the original chain image, and the chain pins in the chain pin segment image are then lengthened to obtain an image of the lengthened chain pin segment.

[0029] The previously extracted image of the main chain body is then merged with the image of the extended chain pin section to obtain an extended chain image. Based on this extended chain image, the distance between each chain pin is determined to further identify the first chain pin. The previously extracted image of the main chain body is the same image extracted in the preceding process.

[0030] Furthermore, when determining the single-line detection area image starting from the first chain pin, a preset number of single-line area images corresponding to the type of chain to be detected can first be extracted; for each single-line area image, the areas affected by contamination in the single-line area image are filtered out, and the enclosing image of the single-line main body is extracted from the filtered single-line area image; for each target line, the single-line detection area image of the target line is determined based on the single-line area image of the target line and the enclosing image of the single-line main body.

[0031] The preset number mentioned above refers to the total number of chain pins according to the type of chain being detected. The single-line area image is in Fig. 2 to see, whereby Fig. 2 is a schematic diagram of the single-line area image provided by embodiment 1 of the present disclosure. As in Fig. As shown in Figure 2, the single-row area image is the part selected by the rectangular frame, where this part has a certain angle.

[0032] The areas affected by impurities are mainly areas where black blocks are present, where the black blocks mainly have a depth that differs from the image depth of the chain, i.e., different gray values; therefore, the black blocks can be identified by gray values, and then the areas where the black blocks are present are determined as areas affected by impurities.

[0033] The morphological opening operation can be used for processing when specifically filtering out the data.

[0034] Furthermore, since the single-line area image may have some angles due to the rotation of the chain to be detected, the single-line area image and the enclosing image of the single-line main body (the enclosing image of the single-line main body can be considered an image without angles) can be subtracted from each other to obtain the angle influence area, and then the angle influence area is subtracted from the enclosing image of the single-line main body to obtain the single-line detection area image.

[0035] The surrounding image of the single-line main body is in Fig. 3 to see, whereby Fig. 3 is a schematic diagram of the enclosing image of the single-line main body according to embodiment 1 of the present disclosure. As in Fig. As shown in Figure 3, the enclosing image of the single-line main body is the part selected by the rectangular frame.

[0036] It should be noted that the in Fig. 2 and Fig. The 3 illustrations shown are examples, whereby in the actual implementation the angle of the single-line area image is relatively small and may be difficult to distinguish manually, therefore this method can be used for processing.

[0037] Based on the above operations, adverse effects of the angle on recognition can be avoided. It should be noted that the above subtraction operation can be performed using the differential algorithm, which will not be discussed further here.

[0038] Step 102: Extracting gaps in the single-row recognition area image and determining a corresponding gap width for each gap for any single-row recognition area image.

[0039] In this step, the extraction method differs for single-layer and double-layer chain pins when extracting the gaps. Therefore, the height of the single-row detection area image must first be captured, and based on the height of the single-row detection area image, the row type of the single-row detection area image is determined, where the row type shown includes single-layer and double-layer chain pins; then, based on the row type, the gaps in the single-row detection area image are extracted, and the corresponding gap width of each gap is determined.

[0040] Specifically, the direct difference between single-layer chain pins and double-layer chain pins lies in their different heights; therefore, they can be compared, with the single-row detection area image being determined with a larger spacing than double-layer chain pins, and the single-row detection area image being determined with a smaller spacing than single-layer chain pins.

[0041] For single-layer chain pins, extraction can be performed directly by using a binarization threshold, i.e., the part of the binarized image with a gray value below a preset threshold is identified as a gap.

[0042] For double-layer chain pins, if the row type is double-layer chain pins, the target area in the single-row detection area image is segmented; and the gaps in the segmented single-row detection area image are extracted. Specifically, the segmentation method can be a morphological processing method, whereby this segmentation step can separate areas that are actually not connected (usually the gaps are very small and are ignored to form a disconnected feature) but appear connected in the image, thus improving the accuracy of gap detection. Subsequently, the gaps can be extracted in the manner described above for single-layer chain pins.

[0043] The target area refers to the area in the single-line detection area image that is not actually connected, but is displayed as connected in the image.

[0044] Furthermore, the gap width can be determined by the coordinates of the two ends of the edge in the gap width direction, and after determining the gap width, gaps with a width smaller than the width threshold can be filtered out, whereby these gaps can be considered as gaps that should not be detected.

[0045] Step 103: Determining the line width of the single-line recognition area image and, based on the line width, the gap width, and the type of chain to be recognized, detecting whether connecting plates are missing in a line corresponding to the single-line recognition area image.

[0046] In this step, if the type of chain to be recognized is the first preset type, a compensation of the line width can also be performed after determining the line width of the single-line recognition area image. It should be noted that this compensation is necessary because the chain to be recognized of the first preset type may exhibit blurring and slight distortion in some areas, i.e., distortion areas. In these distortion areas, some gaps may be erroneously extracted, and these gaps cause more gap widths to be erroneously subtracted during the final recognition, resulting in an insufficient final result. Therefore, some compensation must be performed.

[0047] Specifically, the distortion areas in the single-line detection area image can first be determined, and the compensation value of the line width is determined according to the distortion areas; then the line width is compensated using the compensation value of the line width.

[0048] By querying the gaps, it can be determined whether a distortion area exists in any gap. The specific method of determination can consist of merging overlapping gap areas into a temporary area. First, the horizontal gaps (gaps parallel to the chain pin direction) and the vertical gaps (gaps perpendicular to the chain pin direction) can be combined. Then, for each arbitrary vertical gap, the individual horizontal gaps are queried successively to assess whether there is an overlap between the vertical gap and the queried horizontal gaps. If so, the vertical gap can be merged with the queried horizontal gaps into a temporary area.

[0049] Then, it is assessed whether the width of the vertical gap in the temporary area is greater than a first distortion assessment threshold and whether the total width of the temporary area is less than a second distortion assessment threshold; if the width of the vertical gap is greater than the first distortion assessment threshold and the total width of the temporary area is less than the second distortion assessment threshold, the temporary area is assessed as normal and no compensation is required.

[0050] If the total width of the temporary area is greater than or equal to the second distortion assessment threshold and less than the third distortion assessment threshold, and the height of the vertical gaps in the temporary area is greater than the fourth distortion assessment threshold, the area with the lower gray value in the temporary area is set as the distortion area (meaning that the gray value is significantly smaller than the surrounding influence gray value; alternatively, a gray value threshold can be set for quantification, with the value below this gray value threshold being considered lower).

[0051] It should be noted that the aforementioned first distortion assessment threshold, second distortion assessment threshold, third distortion assessment threshold, and fourth distortion assessment threshold are all determined according to the relevant parameter values ​​in temporary ranges that are indicated as normal in the historical data in order to distinguish the abnormal temporary ranges.

[0052] The number of pixels in the distortion area is then determined, and the row width compensation value is calculated proportionally to the number of pixels. For example, the row width compensation value is determined as the product of the number of pixels and a specific ratio. This ratio can be predefined and is not discussed further here. If this ratio is preset, statistical analysis based on previous data can be performed to determine the appropriate ratio.

[0053] Of course, a mapping relationship can also be defined for different numbers of pixels and different compensation values ​​for the row widths, whereby this mapping relationship can also be determined statistically according to previous experience data, for example, the corresponding compensation value for the row widths is a if the number of pixels is in the first range, and the corresponding compensation value for the row widths is b if the number of pixels is in the second range; the more ranges are defined, the more accurate the compensation.

[0054] For concrete detection, an assessment threshold can first be determined according to the type of chain to be detected, and the difference between the line width and the sum of the gap widths is determined.

[0055] If the difference is greater than or equal to the assessment threshold, it is assessed that no connecting plate is missing in the row corresponding to the single-line recognition area image; if the difference is less than the assessment threshold, it is assessed that a connecting plate is missing in the row corresponding to the single-line recognition area image, and the position of the missing connecting plate is determined according to the gap width.

[0056] It should be noted that when assessing whether a connecting plate is missing, the differences between adjacent rows can also be used comprehensively for the determination; if the difference between a particular row and its adjacent rows shows a sudden change in the overall row differences, it can be determined that this row and its adjacent rows have a risk of missing connecting plates, and a warning can be given.

[0057] In this embodiment, the original chain image of the chain to be detected is captured, and the single-row detection area images between the respective chain pins are determined according to the type of chain to be detected and the original chain image; for any single-row detection area image, the gaps in the single-row detection area image are extracted, and the respective corresponding gap width of each gap is determined; the line width of the single-row detection area image is determined, and it is detected, according to the line width, the gap width, and the type of chain to be detected, whether connecting plates are missing in the line corresponding to the single-row detection area image.Based on this, the present disclosure can automatically detect the respective lines in the chain one after the other and, using the line width and gap width, determine more intuitively whether connecting plates are missing in the respective lines, thereby avoiding the problems of missed detection that occur during manual inspection. This leads to higher detection efficiency and accuracy.

[0058] With reference to Fig. 4 is Fig. 4 A schematic structure diagram of a device for detecting missing connecting plates in a chain according to some other embodiments of the present disclosure. The device for detecting missing connecting plates in a chain provided in the embodiments of the present disclosure can perform the method for detecting missing connecting plates in a chain provided in any embodiment of the present disclosure and has corresponding functional modules and advantageous effects. The device can be implemented by software and / or hardware, and as shown in Fig. As shown in Figure 4, the device for detecting missing connecting plates in a chain specifically comprises: a first determination module 401, a second determination module 402 and a detection module 403.

[0059] The first identification module serves to capture the original chain pattern of the chain to be recognized and to determine the single-row recognition area image between the individual chain pins according to the type of chain to be recognized and the original chain pattern; The second determination module serves to extract the gaps in any single-line recognition area image and to determine the respective gap width of each gap; and The recognition module serves to determine the line width of the single-line recognition area image and, based on the line width and the gap width, to recognize whether connecting plates are missing in the line corresponding to the single-line recognition area image.

[0060] Optionally, the first determination module serves specifically this purpose: During the rotation of the chain to be detected, the image information of the chain to be detected is captured line by line until the number of captured lines reaches a preset threshold to obtain the original chain image, where the preset threshold is greater than the number of pixel lines of the chain to be detected.

[0061] Optionally, the first determination module also serves the following specific purpose: to determine the first chain pin in the original chain pattern according to the type of chain to be identified and the original chain pattern; and starting from the first chain pin, extract the preset number of single-line detection area images corresponding to the type of chain to be detected, where the single-line detection area image is an area image between two chain pins.

[0062] Optionally, the first determination module also serves the following specific purpose: to determine the distances between the respective chain pins in the original chain pattern and, according to the sequential arrangement of the distances, to determine the target chain pin that fulfills the preset condition of the first chain pin corresponding to the type of chain to be detected; and to determine the target chain pin as the first chain pin in the original chain pattern.

[0063] Optionally, the first determination module also serves the following specific purpose: to extract the preset number of single-line area images corresponding to the type of chain to be detected; to filter out the contaminant-affected areas from any single-row area image and to extract the enclosing image of the single-row main body from the filtered single-row area image; and to determine, for any given target line, the single-line recognition area image of the target line according to the single-line area image of the target line and the enclosing image of the single-line main body.

[0064] Optionally, the second determination module serves specifically this purpose: to capture the height of the single-line recognition area image and, based on the height of the single-line recognition area image, to determine the line type of the single-line recognition area image; and to extract the gaps in the single-line recognition area image according to the line type and to determine the respective gap width of each gap.

[0065] Optionally, the second determination module also serves the following specific purpose: to segment the target area in the single-row detection area image when the row type is a double-layer chain bolt; and to extract the gap in the segmented single-line detection area image.

[0066] Optionally, the first determination module also serves the following specific purpose: to extract the image of a chain pin section from the original chain image and to extend the chain pins in the image of the chain pin section to obtain an image of the extended chain pin section; and to combine the previously extracted image of a chain main body with the image of the extended chain pin section to obtain an extended chain image, and to determine the distances between the individual chain pins according to the extended chain image.

[0067] Optionally, the device also includes: A removal module used to remove the chain pins at the beginning and end of the original chain pattern.

[0068] Optionally, the distance module serves the following specific purpose: to extract the image of the chain main body from the original chain image and to determine the information of the vertex coordinates of the image of the chain main body; and Remove the chain pins at both ends in the original chain diagram according to the information from the corner point coordinates.

[0069] Optionally, if the type of chain to be detected is a first preset type, the device also includes: a third determination module for determining a distortion area in the single-line recognition area image and for determining a compensation value for the line width according to the distortion area; and A compensation module for compensating the row width using the row width compensation value.

[0070] Optionally, the recognition module serves the following specific purpose: to determine an assessment threshold according to the type of chain to be detected, and to determine a difference between the line width and the sum of the gap widths; If the difference is greater than or equal to the assessment threshold, it is to be assessed that no connecting plates are missing from the line corresponding to the single-line recognition area image; and If the difference is less than the assessment threshold, assess that connecting plates are missing in the row corresponding to the single-line recognition area image, and determine the positions of the missing connecting plates according to the gap width.

[0071] Fig. Figure 5 is a schematic structure diagram of an electronic device provided in some further embodiments of the present disclosure. As in Fig. As shown in Figure 5, the electronic device comprises a processor 510, a memory 520, an input device 530 and an output device 540; the number of processors 510 in the electronic device can be one or more, wherein in Fig. 5 a processor 510 serves as an example; the processor 510, the memory 520, the input device 530 and the output device 540 in the electronic device can be connected via a bus or in some other way, wherein in Fig. 5. The connection via a bus serves as an example.

[0072] The memory 520 can be used as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to the method for detecting missing connecting plates in a chain in the embodiments of the present disclosure (for example, the first determination module 401, the second determination module 402, and the detection module 403 in the device for detecting missing connecting plates in a chain). The processor 510 performs various functional applications and data processing of the electronic device by executing the software programs, instructions, and modules stored in the memory 520; that is, it implements the method for detecting missing connecting plates in a chain described above.

[0073] Capturing an original chain image of a chain to be detected and determining a single-row detection area image between the respective chain pins according to a type of chain to be detected and the original chain image;

[0074] Extracting gaps in the single-row recognition area image and determining a corresponding gap width for each gap for any single-row recognition area image; and

[0075] Determining the line width of the single-line recognition area image and recognizing, according to the line width, the gap width and the type of chain to be recognized, whether connecting plates are missing in a line corresponding to the single-line recognition area image.

[0076] Optionally, capturing an original chain image of the chain to be detected includes: During the rotation of the chain to be detected, image information of the chain to be detected is captured line by line until the number of captured lines reaches a preset threshold to obtain the original chain image, where the preset threshold is greater than the number of pixel lines of the chain to be detected.

[0077] Optionally, this includes determining the single-line detection area image between the respective chain pins according to the type of chain to be detected and the original chain image: Determining the first chain pin in the original chain pattern according to the type of chain to be identified and the original chain pattern; and Starting from the first chain pin, extract a preset number of single-line detection area images corresponding to the type of chain to be detected, wherein the single-line detection area image is an area image between two chain pins.

[0078] Optionally, determining the first chain pin in the original chain pattern according to the type of chain to be identified and the original chain pattern includes: Determining the distances between the respective chain pins in the original chain pattern and determining a target chain pin that fulfills a preset condition of the first chain pin corresponding to the type of chain to be detected, according to a sequential arrangement of the distances; and Determine the target chain pin as the first chain pin in the original chain pattern.

[0079] Optionally, extracting a preset number of single-line detection area images corresponding to the type of chain to be detected includes: Extracting the preset number of single-line area images corresponding to the type of chain to be detected; for any single-row area image, filtering out areas affected by impurities from the single-row area image and extracting an enclosing image of a single-row main body from the filtered single-row area image; and For any target line, determine the single-line recognition area image of the target line according to the single-line area image of the target line and the enclosing image of the single-line main body.

[0080] Optionally, this includes extracting gaps in the single-line recognition area image and determining a corresponding gap width for each gap: Determining the height of the single-line recognition area image and defining a line type for the single-line recognition area image based on the height of the single-line recognition area image; and Extracting the gaps in the single-line recognition area image according to the line type and determining the respective corresponding gap width of each gap.

[0081] Optionally, extracting the gaps in the single-line detection area image according to the line type includes: Segmenting a target area in the single-row detection area image when the row type is a double-layer chain bolt; and Extracting gaps in the segmented single-row detection area image.

[0082] Optionally, this includes determining the distances between the respective chain pins in the original chain pattern: Extracting an image of a chain pin section from the original chain image and extending chain pins in the image of the chain pin section to obtain an image of the extended chain pin section; and Merging a pre-extracted image of a chain main body with the image of the extended chain pin section to obtain an extended chain image, and determining the distances between the respective chain pins according to the extended chain image.

[0083] Optionally, the procedure includes, after capturing the original chain pattern of the chain to be detected and before determining the single-row detection area pattern between the respective chain pins according to the type of chain to be detected and the original chain pattern, further: Removing chain pins at the beginning and end of the original chain pattern.

[0084] Optionally, this includes removing chain pins at the beginning and end of the original chain pattern. Extracting an image of a chain principal body from the original chain image and determining information about the vertex coordinates of the chain principal body image; and Remove the chain pins at both ends in the original chain diagram according to the information from the corner point coordinates.

[0085] Optionally, if the type of chain to be recognized is a first preset type, the procedure includes, after determining the line width of the single-line recognition area image: Determining a distortion area in the single-line detection area image and determining a compensation value for the line width according to the distortion area; and Compensating for line width using the line width compensation value.

[0086] Optionally, the detection based on line width, gap width, and the type of chain to be detected, including whether connecting plates are missing in the line corresponding to the single-line detection area image, includes the following: Determining an assessment threshold according to the type of chain to be detected and determining a difference between the line width and a sum of the gap widths; If the difference is greater than or equal to the assessment threshold, assess that no connecting plates are missing from the line corresponding to the single-line recognition area image; and If the difference is less than the assessment threshold, assess that connecting plates are missing in the row corresponding to the single-line recognition area image, and determine the positions of the missing connecting plates according to the gap width.

[0087] The memory 520 can primarily comprise a program memory area and a data memory area, wherein the program memory area can store an operating system and at least one application program required for a function; the data memory area can store data created according to the use of the terminal and the like. Furthermore, the memory 520 can comprise a high-speed random-access memory and can also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or another non-volatile solid-state storage device. In some embodiments, the memory 520 can further comprise memory located remotely relative to the processor 510, and this remotely located memory can be connected to the electronic device via a network.Examples of the above-mentioned network include, but are not limited to, the Internet, a corporate intranet, a local network, a mobile communications network and combinations thereof.

[0088] The input device 530 can be used to receive entered electrical design drawings and to generate keystroke inputs relating to user settings and function control of the electronic device. The output device 540 can include display devices such as a display screen.

[0089] Further embodiments of the present disclosure provide a storage medium containing computer-executable instructions, wherein the computer-executable instructions, when executed by a computer processor, are used to execute a method for detecting missing connecting plates in a chain, the method comprising: Capturing an original chain image of a chain to be detected and determining a single-row detection area image between the respective chain pins according to a type of chain to be detected and the original chain image; Extracting gaps in the single-row recognition area image and determining a corresponding gap width for each gap for any single-row recognition area image; and Determining the line width of the single-line recognition area image and recognizing, according to the line width, the gap width and the type of chain to be recognized, whether connecting plates are missing in a line corresponding to the single-line recognition area image.

[0090] Optionally, capturing the original chain pattern of the chain to be detected includes: Capturing image information of the chain to be detected line by line during the rotation of the chain to be detected, until the number of captured lines reaches a preset threshold to obtain the original chain image, where the preset threshold is greater than the actual number of lines of the chain to be detected.

[0091] Optionally, determining the single-line detection area image between the respective chain pins according to the type of chain to be detected and the original chain image includes the following: Determining a first chain pin in the original chain pattern according to the type of chain to be identified and the original chain pattern; and Extracting a preset number of single-line detection area images corresponding to the type of chain to be detected, starting from the first chain pin, where the single-line detection area image represents an area image between two chain pins.

[0092] Optionally, determining the first chain pin in the original chain pattern according to the type of chain to be identified and the original chain pattern includes the following: Determining the distances between the respective chain pins in the original chain pattern and determining a target chain pin that fulfills a preset condition of the first chain pin corresponding to the type of chain to be detected, according to a sequential arrangement of the distances; and Determine the target chain pin as the first chain pin in the original chain pattern.

[0093] Optionally, extracting the preset number of single-line detection area images corresponding to the type of chain to be detected includes the following: Extracting a preset number of single-line area images corresponding to the type of chain to be detected; for any single-row area image, filtering out areas affected by impurities from the single-row area image and extracting an enclosing image of a single-row main body from the filtered single-row area image; and For any target line, determining a single-line recognition area image of the target line according to the single-line area image of the target line and the enclosing image of the single-line main body.

[0094] Optionally, extracting the gaps in the single-line detection area image and determining the respective gap width of each gap includes the following: Determining the height of the single-line recognition area image and defining a line type for the single-line recognition area image based on the height of the single-line recognition area image; and Extracting the gaps in the single-line recognition area image according to the line type and determining the respective corresponding gap width of each gap.

[0095] Optionally, extracting the gaps in the single-row detection area image according to the row type includes the following: Segmenting a target area in the single-row detection area image when the row type is a double-layer chain bolt; and Extracting gaps in the segmented single-row detection area image.

[0096] Optionally, determining the distances between the respective chain pins in the original chain pattern includes the following: Extracting an image of a chain pin section from the original chain image and extending chain pins in the image of the chain pin section to obtain an image of the extended chain pin section; and Merging a pre-extracted image of a chain main body with the image of the extended chain pin section to obtain an extended chain image, and determining the distances between the respective chain pins according to the extended chain image.

[0097] Optionally, the procedure includes, after capturing the original chain pattern of the chain to be detected and before determining the single-row detection area pattern between the respective chain pins according to the type of chain to be detected and the original chain pattern, further: Removal of chain pins at the beginning and end of the original chain pattern.

[0098] Optionally, removing the chain pins at the beginning and end of the original chain pattern includes the following: Extracting an image of a chain principal body from the original chain image and determining information about the vertex coordinates of the chain principal body image; and Removal of chain pins at both ends in the original chain image according to the information from the corner point coordinates.

[0099] Optionally, if the type of chain to be detected is the first preset type, the procedure also includes the following after determining the line width of the single-line detection area image: Determining a distortion area in the single-line detection area image and determining a compensation value for the line width according to the distortion area; and Compensating for line width using the line width compensation value.

[0100] Optionally, the detection based on line width, gap width, and the type of chain to be detected, including whether connecting plates are missing in the line corresponding to the single-line detection area image, includes the following: Determining an assessment threshold according to the type of chain to be detected and determining a difference between the line width and a sum of the gap widths; If the difference is greater than or equal to the assessment threshold, assess that no connecting plates are missing from the line corresponding to the single-line recognition area image; and If the difference is less than the assessment threshold, assess that connecting plates are missing in the row corresponding to the single-line recognition area image, and determine the positions of the missing connecting plates according to the gap width.

[0101] Naturally, the computer-executable instructions of the storage medium provided in the embodiments of the present disclosure, which contains computer-executable instructions, are not limited to the above-mentioned process operations, but can also perform the relevant operations of the method provided in any embodiment of the present disclosure for detecting missing connecting plates in a chain.

[0102] From the above description of the embodiments, those skilled in the field can clearly understand that the present disclosure can be implemented using software and necessary general hardware, and of course also using hardware, but in many cases the former is a better implementation option. Based on this understanding, the technical solution of the present disclosure can be embodied essentially, or the part that contributes to the prior art, in the form of a software product. This computer software product can be stored on a computer-readable storage medium, such as a computer's floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), a hard disk, or an optical disk, etc.It includes several instructions to cause a computer device (this may be a personal computer, a server, or a network device, etc.) to execute the method of the various embodiments of the present disclosure.

[0103] It should be noted that in the embodiments of the above-mentioned search device, the individual units and modules contained are subdivided only according to the functional logic, but are not limited to the above subdivision as long as the corresponding functions can be realized; furthermore, the specific names of the individual functional units serve only to facilitate mutual differentiation and are not intended to limit the scope of protection of the present disclosure.

[0104] It should be noted that the foregoing only describe preferred embodiments of the present disclosure and the technical principles applied. Those skilled in the art will understand that the present disclosure is not limited to the specific embodiments described herein, and that various obvious modifications, adaptations, and substitutions can be made without altering the scope of protection of the present disclosure. Therefore, although the present disclosure has been described in detail by the embodiments described above, it is not limited to these embodiments and may also include other equivalent embodiments without departing from the concept of the present disclosure, and the scope of protection of the present disclosure is determined by the scope of the accompanying claims. Commercial applicability

[0105] The present disclosure discloses a method for detecting missing connecting plates in a chain and an electronic device. The method for detecting missing connecting plates in a chain comprises: capturing an original chain image of a chain to be detected and determining a single-line detection area image between the respective chain pins according to a type of chain to be detected and the original chain image; extracting gaps in the single-line detection area image and determining a corresponding gap width for each gap for any single-line detection area image; and determining the line width of the single-line detection area image and detecting, according to the line width, the gap width, and the type of chain to be detected, whether connecting plates are missing in a line corresponding to the single-line detection area image.Based on this, the present disclosure can automatically detect the respective lines in the chain one after the other and, using the line width and gap width, determine more intuitively whether connecting plates are missing in the respective lines, thereby avoiding the problems of missed detection that occur during manual inspection. This leads to higher detection efficiency and accuracy.

[0106] Furthermore, it is understandable that the method for detecting missing connecting plates in a chain and the electronic device of the present disclosure can be reproducible and used in various industrial applications. For example, the method for detecting missing connecting plates in a chain and the electronic device of the present disclosure can be used in the technical field of chain detection. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] CN 2023109356186

[0001]

Claims

[1] Method for detecting missing connecting plates in a chain, the method comprising: Capturing an original chain image of a chain to be detected and determining a single-row detection area image between the respective chain pins according to a type of chain to be detected and the original chain image; Extracting gaps in the single-row recognition area image and determining a corresponding gap width for each gap for any single-row recognition area image; and Determining the line width of the single-line recognition area image and recognizing, according to the line width, the gap width and the type of chain to be recognized, whether connecting plates are missing in a line corresponding to the single-line recognition area image. [2] The method of claim 1, wherein the detection of the original chain pattern of the chain to be detected comprises: Capturing image information of the chain to be detected line by line during the rotation of the chain to be detected, until a number of the captured lines reaches a preset threshold to obtain the original chain image, where the preset threshold is greater than a number of pixel lines corresponding to the size of the chain to be detected. [3] Method according to claim 2, wherein the acquisition of the original chain image of the chain to be detected is carried out several times and each acquisition is carried out continuously and without interruption; and according to the acquisition sequence, the images acquired several times are combined to obtain the original chain image. [4] Method according to any one of claims 1 to 3, wherein determining the single-row detection area image between the respective chain pins according to the type of chain to be detected and the original chain image comprises the following: Determining a first chain pin in the original chain pattern according to the type of chain to be identified and the original chain pattern; and Extracting a preset number of single-line detection area images corresponding to the type of chain to be detected, starting from the first chain pin, wherein the single-line detection area images represent area images between two chain pins. [5] Method according to claim 4, wherein determining the first chain pin in the original chain pattern according to the type of chain to be detected and the original chain pattern comprises the following: Determining distances between the respective chain pins in the original chain pattern and determining a target chain pin that fulfills a preset condition of the first chain pin corresponding to the type of chain to be detected, according to a sequential arrangement of the distances; Determining the target chain pin as the first chain pin in the original chain pattern; Determining the distances between the respective chain pins in the original chain diagram includes the following: Extracting an image of a chain pin section from the original chain image and extending chain pins in the image of the chain pin section to obtain an image of the extended chain pin section; and Merging a pre-extracted image of a chain main body with the image of the extended chain pin section to obtain an extended chain image, and determining the distances between the respective chain pins according to the extended chain image. [6] Method according to claim 4 or 5, wherein extracting the preset number of single-line detection area images corresponding to the type of chain to be detected comprises: Extracting a preset number of single-line area images corresponding to the type of chain to be detected; for each of the single-row area images, filtering out areas affected by impurities from the single-row area image and extracting an enclosing image of a single-row main body from the filtered single-row area image; and For any target line, determining a single-line recognition area image of the target line according to the single-line area image of the target line and the enclosing image of the single-line main body. [7] Method according to claim 6, wherein the single-line area image and the enclosing image of the single-line main body are subtracted from each other to obtain an angle influence area, and subsequently the angle influence area is subtracted from the enclosing image of the single-line main body to obtain the single-line recognition area image. [8] Method according to any one of claims 1 to 7, wherein extracting the gaps in the single-line recognition area image and determining the respective corresponding gap width of each gap comprises: Capturing a height of the single-line detection area image and determining a line type of the single-line detection area image according to the height of the single-line detection area image, wherein the line type includes single-layer chain pin and double-layer chain pin; Extracting the gaps in the single-line recognition area image according to the line type and determining the respective corresponding gap width of each gap; where extracting the gaps in the single-line detection area image according to the line type includes the following: Segmenting a target area in the single-row detection area image when the row type is a double-layer chain bolt; and Extracting gaps in the segmented single-row detection area image. [9] Method according to any one of claims 1 to 8, wherein, after capturing the original chain pattern of the chain to be detected and before determining the single-row detection area image between the respective chain pins according to the type of chain to be detected and the original chain pattern, the method further comprises: Removal of chain pins at the beginning and end of the original chain pattern; the removal of the chain pins at the beginning and end of the original chain pattern includes the following: Extracting an image of a chain principal body from the original chain image and determining information about the vertex coordinates of the chain principal body image; and Removal of chain pins at the upper and lower ends in the original chain image according to the information from the corner point coordinates. [10] Method according to any one of claims 1 to 9, wherein, if the type of chain to be detected is the first preset type, the method after determining the line width of the single-line detection area image further comprises: Determining a distortion area in the single-line detection area image and determining a compensation value for the line width according to the distortion area; and Compensating for line width using the line width compensation value. [11] Method according to any one of claims 1 to 10, wherein the detection according to the line width, the gap width and the type of chain to be detected, whether connecting plates are missing in the line corresponding to the single-line detection area image, comprises the following: Determining an assessment threshold according to the type of chain to be detected and determining a difference between the line width and a sum of the gap widths; If the difference is greater than or equal to the assessment threshold, assess that no connecting plates are missing from the line corresponding to the single-line recognition area image; and If the difference is less than the assessment threshold, assess that connecting plates are missing in the row corresponding to the single-line recognition area image, and determine the positions of the missing connecting plates according to the gap width. [12] Electronic device comprising: one or more processors; a storage device for storing one or more programs, and wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method for detecting missing connecting plates in a chain according to any one of claims 1 to 11.

Images