Anti-glare panel detection method, device, equipment, medium and product
By using movable devices to collect images and perform linear fitting to confirm the reference line of linear laser marks, the problems of low efficiency and low accuracy of traditional detection methods are solved, and fast and accurate anti-glare detection is achieved.
Patent Information
- Application Number
- CN202411747675.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-02
- Publication Date
- 2025-03-11
AI Technical Summary
Traditional anti-glare panel detection methods rely on manual inspection and handheld equipment, and there are problems of slow detection speed, low accuracy and low efficiency.
The anti-glare plate detection image is collected by a movable device, the pixel coordinates of the linear laser trace are obtained, and the linear fit is performed to obtain the linear vector, confirm the reference line of the linear laser trace, and then the anti-glare plate is detected.
It realizes rapid and accurate detection of damage to anti-glare boards, reduces labor costs, and improves detection efficiency and accuracy.
Smart Images
Figure CN119595647A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of highway engineering technology, and in particular to an anti-glare plate detection method, device, equipment, medium and product. Background Art
[0002] Anti-glare panels are common traffic safety facilities on highways and main roads. They are used to prevent direct exposure to oncoming headlights and reduce glare for drivers when driving at night, thereby improving driving safety. However, due to exposure to the outdoors, affected by the natural environment and human factors, anti-glare panels are prone to damage and performance degradation.
[0003] Anti-glare panels are mostly green sheet structures, and their main forms of damage include missing, tilt deformation, torsional deformation, etc. Traditional detection methods usually rely on manual inspections and handheld devices, but due to the long distance and high speed of highways, this method has the problems of slow detection speed, low accuracy and low efficiency. Summary of the invention
[0004] The present disclosure is proposed in view of the above problems, and provides an anti-glare plate detection method, device, equipment, medium and product.
[0005] According to one aspect of the present disclosure, there is provided an anti-glare plate detection method, comprising:
[0006] Acquire an anti-glare plate detection image collected by a movable device, wherein the anti-glare plate detection image includes a plurality of anti-glare plates to be detected and line laser traces left by a same line laser on the plurality of anti-glare plates to be detected;
[0007] Obtaining pixel coordinates corresponding to the line laser trace on the anti-glare plate detection image;
[0008] Performing linear fitting on all the pixel point coordinates to obtain the straight line vector corresponding to the line laser trace;
[0009] Based on all the pixel coordinates and the straight line vectors, determining the reference line of the line laser trace;
[0010] Based on the linear laser trace and the reference line, a plurality of the anti-glare panels to be inspected are inspected.
[0011] In addition, according to an anti-glare plate detection method of one aspect of the present disclosure, based on all the pixel point coordinates and the straight line vectors, confirming the reference line of the target line laser trace includes:
[0012] Calculating the residual absolute value of the coordinates of each pixel point and the straight line vector;
[0013] In the case where there is a target residual absolute value greater than a preset residual threshold value in the residual absolute values, the target pixel point coordinates whose residual absolute value is less than or equal to the preset residual threshold value are obtained, the pixel point coordinates are updated to the target pixel point coordinates, and the step of performing linear fitting on all the pixel point coordinates is repeated until there is no target residual absolute value greater than the preset residual threshold value in the residual absolute values, and a final straight line vector corresponding to the target line laser trace is obtained;
[0014] Based on the final straight line vector, a reference line of the line laser trace is confirmed.
[0015] In addition, according to an anti-glare plate detection method of one aspect of the present disclosure, based on the line laser trace and the reference line, a plurality of the anti-glare plates to be detected are detected, including:
[0016] Based on the preset position of each anti-glare plate to be detected on the anti-glare plate detection image, obtaining the target trace of the linear laser trace distributed on each anti-glare plate to be detected;
[0017] In the case where all the target traces on the anti-glare plate to be detected are not obtained, the distortion feature of the line laser trace is identified as a partial loss; in the case where all the target traces on the anti-glare plate to be detected are obtained, the distortion feature of the line laser trace is identified based on the distance between the pixel coordinates corresponding to the target trace and the reference line;
[0018] Based on the distortion characteristics of the line laser trace, detection results of the plurality of anti-glare panels to be detected are obtained.
[0019] In addition, according to an anti-glare plate detection method of one aspect of the present disclosure, based on the distance between the pixel coordinates corresponding to the target trace and the reference line, the distortion feature of the line laser trace is identified, including:
[0020] When the distances between the pixel coordinates corresponding to the target trace and the reference line are both less than or equal to a distance threshold, identifying the distortion feature of the line laser trace as no distortion;
[0021] When the distances between the pixel coordinates corresponding to the target trace and the reference line are greater than a distance threshold, identifying the distortion feature of the line laser trace as a local offset;
[0022] When the distance from the reference line to the pixel point coordinates corresponding to the target trace is greater than the distance threshold and less than or equal to the distance threshold at the same time, the distortion feature of the line laser trace is identified as a local bend.
[0023] In addition, according to an anti-glare plate detection method of one aspect of the present disclosure, based on the distortion characteristics of the line laser trace, the detection results of the plurality of anti-glare plates to be detected are obtained, including:
[0024] When the distortion feature is no distortion, obtaining a detection result of the plurality of anti-glare panels to be detected as no damage;
[0025] In the case where the distortion feature is a partial loss, obtaining a detection result of the plurality of anti-glare panels to be detected as a partial loss of the anti-glare panels;
[0026] In the case where the distortion feature is a local offset, obtaining a detection result of the plurality of anti-glare panels to be detected as a local tilt deformation of the anti-glare panels;
[0027] In the case where the distortion feature is a local bend, the detection result of the plurality of anti-glare panels to be detected is a torsional deformation of the local anti-glare panels.
[0028] In addition, according to an anti-glare plate detection method of one aspect of the present disclosure, based on the line laser trace and the reference line, a plurality of the anti-glare plates to be detected are detected, including:
[0029] When the anti-glare plate inspection image includes a plurality of line laser marks left by a plurality of line lasers, the plurality of anti-glare plates to be inspected are inspected based on each of the line laser marks and a reference line corresponding to each of the line laser marks.
[0030] According to another aspect of the present disclosure, there is provided an anti-glare plate detection device, comprising:
[0031] A first acquisition module is used to acquire an anti-glare plate detection image collected by a movable device, wherein the anti-glare plate detection image includes a plurality of anti-glare plates to be detected and line laser traces left by a same line laser on the plurality of anti-glare plates to be detected;
[0032] A second acquisition module is used to acquire pixel coordinates corresponding to the line laser trace on the anti-glare plate detection image;
[0033] A linear fitting module performs linear fitting on all the pixel coordinates to obtain a straight line vector corresponding to the line laser trace;
[0034] A calculation module, used for confirming the reference line of the line laser trace based on all the pixel point coordinates and the straight line vector;
[0035] A detection module is used to detect the plurality of anti-glare panels to be detected based on the linear laser trace and the reference line.
[0036] According to another aspect of the present disclosure, a computer device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method of the above aspect.
[0037] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method of the above aspect is implemented.
[0038] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method of the above aspect is implemented.
[0039] As will be described in detail below, according to an anti-glare plate detection method, device, equipment, medium and product of an embodiment of the present disclosure, by processing the collected anti-glare plate detection image, a baseline corresponding to the line laser trace is obtained, and the anti-glare plate to be inspected can be inspected based on the line laser trace and the baseline to determine whether it is damaged and the form of damage. Compared with manual inspection, this reduces labor costs and is conducive to improving detection efficiency and detection accuracy.
[0040] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] The above and other purposes, features and advantages of the present disclosure will become more apparent by describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same reference numerals generally represent the same components or steps.
[0042] Figure 1 is a flowchart illustrating application of the anti-glare plate detection method according to an embodiment of the present disclosure.
[0043] Figure 2 is another flow chart illustrating the application of the anti-glare plate detection method according to an embodiment of the present disclosure.
[0044] Figure 3 It is a comparison diagram illustrating the damage forms of the anti-glare panels according to the embodiments of the present disclosure.
[0045] Figure 4 is a schematic diagram illustrating the structure of an anti-glare plate detection device according to an embodiment of the present disclosure.
[0046] Figure 5 It is a schematic diagram illustrating the structure of a computer device according to an embodiment of the present disclosure.
[0047] Figure 6 is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0048] In order to make the purpose, technical solution and advantages of the present disclosure more obvious, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.
[0049] Anti-glare panels are common traffic safety facilities on highways and main roads. They are used to prevent direct exposure to oncoming headlights and reduce glare for drivers when driving at night, thereby improving driving safety. However, due to exposure to the outdoors, affected by the natural environment and human factors, anti-glare panels are prone to damage and performance degradation.
[0050] Anti-glare panels are mostly green sheet structures, and their damage forms mainly include missing, tilt deformation, torsional deformation, etc. Traditional detection methods usually rely on manual inspections and handheld devices, which have problems of low efficiency and high cost, and it is difficult to achieve rapid detection.
[0051] In recent years, technologies such as computer vision and LiDAR 3D point cloud collection have been gradually applied in this field. However, both computer vision technology and LiDAR 3D point cloud technology mostly collect a large amount of anti-glare plate damage image data and point cloud data, train them through artificial intelligence algorithms, and identify the corresponding damage conditions. However, in actual situations, the number of such samples is limited, and the number of damaged samples of different categories is difficult to unify, resulting in limited accuracy of the recognition model and high cost of algorithm development.
[0052] In the above, an anti-glare plate detection method, device, equipment, medium and product according to an embodiment of the present disclosure are described with reference to the accompanying drawings. By processing the collected anti-glare plate detection image, a baseline corresponding to the line laser trace is obtained. The anti-glare plate to be inspected can be inspected based on the line laser trace and the baseline to determine whether it is damaged and the form of damage. Compared with manual inspection, this reduces labor costs and is conducive to improving detection efficiency and detection accuracy.
[0053] By comparing the linear laser trace with the baseline, the distortion characteristics of the linear laser trace can be identified, and then it can be determined whether the anti-glare plate is damaged and the form of damage. There is no need to collect a large number of anti-glare plate samples for measurement and training, which effectively reduces the workload of sample collection and makes it easier to ensure accuracy.
[0054] To facilitate understanding of this embodiment, a method for detecting an anti-glare plate disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the anti-glare plate detection method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the anti-glare plate detection method can be implemented by a processor calling a computer-readable instruction stored in a memory.
[0055] like Figure 1 FIG. 1 is a flow chart of an anti-glare plate detection method provided by an embodiment of the present disclosure, wherein the method includes S101-S105:
[0056] S101: Acquire an anti-glare plate detection image collected by a movable device.
[0057] The anti-glare plate detection image includes a plurality of anti-glare plates to be detected and line laser traces left by the same line laser on the plurality of anti-glare plates to be detected.
[0058] Taking the mobile device as a vehicle as an example, the acquisition process of the anti-glare plate detection image is as follows:
[0059] Step 1: Install n line laser transmitters on the vehicle. The emission direction of the line laser transmitter is the side facing the anti-glare plate. After power-on, it can emit line laser lines. The line lasers emitted by the n line laser transmitters are parallel to each other and have different heights. The n line lasers are evenly distributed between the bottom and top of the anti-glare plate.
[0060] Here, n may be 1, but in order to avoid the problem of misidentification caused by a single line of laser, in this embodiment, n is preferably greater than 1, and more preferably n=3.
[0061] Step 2: Use a high-definition camera installed on the top of the vehicle. The shooting direction of the high-definition camera is consistent with the emission direction of the line laser transmitter. After shooting, an anti-glare plate detection image including the anti-glare plate and the line laser trace is obtained.
[0062] The installation height of the high-definition camera is higher than that of the line laser transmitter, so that the camera, line laser and line laser transmitter form a triangular structure with stereoscopic vision capability. The shooting interval of the high-definition camera can be fixed-distance shooting, for example, the fixed-distance range is 4 to 8 meters, which is determined according to the image frame, so as to avoid the overlap of the anti-glare plates of adjacent images.
[0063] Preferably, in order to improve the operation efficiency, reduce the image size, and reduce the analysis complexity of the subsequent algorithm, a 1080P high-definition black and white industrial camera can be used for image data acquisition in the embodiment of the present disclosure.
[0064] S102: Obtaining pixel coordinates corresponding to the line laser trace on the anti-glare plate detection image.
[0065] Specifically, deep learning methods or threshold segmentation methods can be used to extract pixel coordinates from the anti-glare plate detection image. When using the deep learning method, it is necessary to annotate the line laser pixels on a sufficient number of images, and then perform model training to obtain an artificial intelligence model that can identify line lasers. When using the threshold segmentation method, it is necessary to first determine the difference between the pixel coordinates of the line laser and the background feature parameters, then determine the threshold for segmenting the background features and the pixel coordinates of the line laser, and finally extract the pixel coordinates.
[0066] In this embodiment, the grayscale centroid method of threshold segmentation is preferably selected for calculation. Compared with other algorithms, this method has better noise resistance and faster operation speed. The calculation time of a single image is about 0.02s, which meets the sampling frame rate requirement. In addition, when identifying the line laser, some anti-glare plates will have gaps in the middle, making the line laser discontinuous. Therefore, the image expansion algorithm can be used for preprocessing to ensure the continuity of the line laser trace.
[0067] S103: Perform linear fitting on the coordinates of all pixel points to obtain the straight line vector corresponding to the line laser trace.
[0068] Specifically, when the anti-glare plate detection image includes multiple line laser traces left by multiple line lasers, after obtaining the pixel point coordinates corresponding to each line laser trace respectively, the pixel point coordinates corresponding to each line laser trace are linearly fitted to obtain the straight line vector corresponding to each line laser trace.
[0069] S104: Based on all pixel point coordinates and straight line vectors, confirm the baseline of the line laser trace.
[0070] Specifically, S104 includes the following steps:
[0071] Step 1: Calculate the absolute value of the residual between the coordinates of each pixel point and the line vector.
[0072] Taking the coordinates of one pixel point (x, y) as an example, the absolute value of the residual is the distance between (x, y) and the straight line vector.
[0073] Step 2: When there is a target residual absolute value greater than the preset residual threshold in the residual absolute value, obtain the target pixel point coordinates whose residual absolute value is less than or equal to the preset residual threshold, update the pixel point coordinates to the target pixel point coordinates, and repeat the step of linear fitting of all pixel point coordinates until there is no target residual absolute value greater than the preset residual threshold in the residual absolute value, and obtain the final straight line vector corresponding to the target line laser trace.
[0074] The residual threshold can be determined based on actual measurements, and is generally 5-10 pixels.
[0075] Step 3: Based on the final straight line vector, confirm the reference line of the line laser trace.
[0076] S105: Based on the line laser trace and the reference line, multiple anti-glare panels to be inspected are inspected.
[0077] This embodiment takes one of the anti-glare panels to be detected as an example to explain the detection process in detail. Specifically, S105 includes the following steps:
[0078] Step 1: based on the preset position of each anti-glare plate to be detected on the anti-glare plate detection image, obtaining the target trace of the line laser trace distribution on each anti-glare plate to be detected;
[0079] Step 2: When all target traces of the anti-glare plate to be detected are not obtained, the distortion feature of the identification line laser trace is partially missing;
[0080] When all target traces on the anti-glare plate to be detected are obtained, the distortion characteristics of the line laser trace are identified based on the distance between the pixel coordinates corresponding to the target trace and the reference line. Specifically:
[0081] When the distances between the pixel coordinates corresponding to the target trace and the reference line are less than or equal to the distance threshold, the distortion feature of the laser trace of the recognition line is no distortion;
[0082] When the distances between the pixel coordinates corresponding to the target trace and the baseline are greater than the distance threshold, the distortion feature of the laser trace of the recognition line is a local offset;
[0083] When the distance from the reference line to the pixel point coordinates corresponding to the target trace is greater than the distance threshold and less than or equal to the distance threshold at the same time, the distortion feature of the identification line laser trace is a local bend.
[0084] Step 3: Based on the distortion characteristics of the line laser trace, the test results of the multiple anti-glare panels to be tested are obtained. Specifically:
[0085] When the distortion feature is no distortion, obtaining a detection result of no damage on the plurality of anti-glare panels to be detected;
[0086] In the case where the distortion feature is a partial loss, obtaining a detection result of the plurality of anti-glare panels to be detected as a partial loss of the anti-glare panels;
[0087] In the case where the distortion feature is a local offset, the detection result of the plurality of anti-glare panels to be detected is obtained as a tilt deformation of the local anti-glare panels;
[0088] When the distortion feature is a local bend, the detection result of the plurality of anti-glare panels to be detected is a torsional deformation of the local anti-glare panels.
[0089] Preferably, in the embodiment of the present disclosure, when the anti-glare plate detection image includes multiple line laser traces left by multiple line lasers, multiple anti-glare plates to be detected are detected based on each line laser trace and the reference line corresponding to each line laser trace. The final detection result is determined by combining the detection results corresponding to each line laser trace. Assuming that the anti-glare plate detection image includes 3 parallel line laser traces left by 3 parallel line lasers, and each anti-glare plate detection image includes 4 anti-glare plates to be detected, taking one of the anti-glare plates to be detected as an example, the detection result corresponding to the top line laser trace may be missing, and the detection results corresponding to the second and third line laser traces are tilt deformation. Since the anti-glare plate is missing, it is impossible to detect the tilt deformation, so the final detection result is determined to be tilt deformation after comprehensive consideration.
[0090] like Figure 2 As shown, it is another flow chart of the anti-glare plate detection method provided by the embodiment of the present disclosure, and the method includes S201-S204:
[0091] S201: Install n line laser transmitters on the vehicle to emit line lasers.
[0092] The emission direction of the line laser transmitter is the side facing the anti-glare plate. After power is turned on, it can emit a line laser line, marked as Laser 1 , Laser 2 , ...Laser n The line lasers emitted by the n line laser emitters are parallel to each other and have different heights, and the n line lasers are evenly distributed between the bottom and the top of the anti-glare plate.
[0093] Among them, n can be 1, but in order to avoid the problem of misidentification caused by a single line laser, this embodiment preferably prefers n=3, and adjusts the emission angle of the line laser emitter to make it evenly distributed between the bottom and top of the anti-glare plate.
[0094] S202: Use a high-definition camera installed on the top of the vehicle to obtain an anti-glare plate detection image including the anti-glare plate and the line laser trace.
[0095] Among them, the anti-glare plate detection image includes multiple anti-glare plates to be detected and line laser traces left by the same line laser on multiple anti-glare plates to be detected. The shooting direction of the high-definition camera is consistent with the emission direction of the line laser transmitter. The installation height of the high-definition camera is higher than the height of the line laser transmitter, so that the camera, line laser, and line laser transmitter form a triangular structure with stereoscopic vision capability. Adjust the front and rear position and focal length of the high-definition camera to ensure that all line lasers are covered. To ensure that all anti-glare plates can be photographed, the image acquisition frame rate is usually not less than 40fps. The shooting interval of the high-definition camera can be fixed-distance shooting, for example, the fixed-distance range is 4 to 8m, which is determined according to the image frame size, to avoid the overlap of anti-glare plates captured in adjacent images.
[0096] Preferably, in order to improve the operation efficiency, reduce the image size, and reduce the analysis complexity of the subsequent algorithm, a 1080P high-definition black and white industrial camera can be used for image data acquisition in the embodiment of the present disclosure.
[0097] S203: Acquire an anti-glare plate detection image, and extract pixel coordinates of the laser traces on the anti-glare plate detection image.
[0098] Specifically, deep learning methods or threshold segmentation methods can be used to extract pixel coordinates from the anti-glare plate detection image. When using the deep learning method, it is necessary to annotate the line laser pixels on a sufficient number of images, and then perform model training to obtain an artificial intelligence model that can identify line lasers. When using the threshold segmentation method, it is necessary to first determine the difference between the pixel coordinates of the line laser and the background feature parameters, then determine the threshold for segmenting the background features and the pixel coordinates of the line laser, and finally extract the pixel coordinates.
[0099] In this embodiment, the grayscale centroid method of threshold segmentation is preferably selected for calculation. Compared with other algorithms, this method has better noise resistance and faster operation speed. The calculation time of a single image is about 0.02s, which meets the sampling frame rate requirement. In addition, when identifying the line laser, some anti-glare plates will have gaps in the middle, making the line laser discontinuous. Therefore, the image expansion algorithm can be used for preprocessing to ensure the continuity of the line laser trace.
[0100] S204: Testing the anti-glare plate to be tested through multiple iterations of straight line fitting.
[0101] For each line laser trace, all pixel coordinates L i , use multiple iterations of the straight line fitting method to obtain the corresponding straight line vector Lb i , and according to L i and Lb iThe difference between the linear laser traces is used to calculate the distortion characteristics, and the damage form of the anti-glare plate to be detected is determined based on the distortion characteristics. Among them, the multiple iterations of the straight line fitting method are used to improve the stability and reliability of the baseline, which is better than the single straight line fitting. The specific process is as follows:
[0102] (1) The coordinates of all pixels of each line laser trace are L i Perform linear fitting and calculate the fitted straight line vector Lt i .
[0103] (2) Calculate the coordinates L of each pixel point i With the straight line vector Lt i The absolute value of the residual will exceed the pixel coordinate L of the residual threshold T. i The corresponding pixel point is taken as the distortion point, and the coordinates of the distortion point are converted from the coordinates of all pixel points L i Eliminate from.
[0104] The residual threshold T can be determined based on actual measurements, and is generally 5-10 pixels.
[0105] (3) Repeat (1) to (2) until the number of distortion points is 0. The straight line vector Lt calculated at this time is i Determined as the final straight line vector Lb i , according to the final straight line vector Lb i , confirm the reference line corresponding to each line laser trace.
[0106] By comparing the baseline with the actual line laser trace, it can be used to extract the distortion characteristics of the line laser trace, specifically:
[0107] (1) When the line laser does not leave a line laser trace at the preset position of each anti-glare plate to be inspected, the distortion feature of the line laser trace is identified as a partial loss;
[0108] (2) When the distance between the pixel coordinates corresponding to the line laser trace and the reference line is less than or equal to the distance threshold, the distortion feature of the line laser trace is identified as no distortion;
[0109] (3) When the distances between the pixel coordinates corresponding to the line laser trace and the reference line are greater than the distance threshold, the distortion feature of the line laser trace is identified as a local offset;
[0110] (4) When the distance between the pixel point coordinates corresponding to the line laser trace and the baseline is greater than the distance threshold and less than or equal to the distance threshold at the same time, the distortion feature of the line laser trace is identified as a local offset.
[0111] like Figure 3As shown in the figure, according to the influence of different damage forms on the line laser, the damage form of the anti-glare plate can be judged by the distortion characteristics:
[0112] (1) Distortion characteristics: no distortion; Damage form: no damage.
[0113] (2) Distortion characteristics: partial loss; Damage form: partial loss of anti-glare panel.
[0114] (3) Distortion characteristics: local offset; Damage form: local anti-glare panel tilting and deformation.
[0115] (4) Distortion characteristics: local bending; Damage form: torsional deformation of local anti-glare panel.
[0116] Whether to replace the damaged anti-glare panels needs to be further judged based on the damage form of the anti-glare panels, among which missing panels have the highest priority, followed by tilting, and then twisting. For example, when there are 100 anti-glare panels on the road section to be inspected, and 3 are found to be missing, 5 are tilted, and 10 are twisted, the missing anti-glare panels are usually repaired first because of limited maintenance capacity, and other types of damage are repaired later based on maintenance capacity and priority.
[0117] According to another aspect of the embodiment of the present disclosure, an anti-glare plate detection device is provided. Figure 4 As shown, the device comprises:
[0118] A first acquisition module 101 is used to acquire an anti-glare plate detection image collected by a movable device, wherein the anti-glare plate detection image includes a plurality of anti-glare plates to be detected and line laser traces left by a same line laser on the plurality of anti-glare plates to be detected;
[0119] The second acquisition module 102 is used to acquire the pixel coordinates corresponding to the line laser trace on the anti-glare plate detection image;
[0120] A linear fitting module 103 is used to perform linear fitting on all the pixel coordinates to obtain a straight line vector corresponding to the line laser trace;
[0121] A calculation module 104, configured to determine a reference line of the line laser trace based on all the pixel coordinates and the line vector;
[0122] The detection module 105 is used to detect the plurality of anti-glare panels to be detected based on the linear laser trace and the reference line.
[0123] In one or more embodiments, the computing module 104 is configured to:
[0124] Calculating the residual absolute value of the coordinates of each pixel point and the straight line vector;
[0125] In the case where there is a target residual absolute value greater than a preset residual threshold value in the residual absolute values, the target pixel point coordinates whose residual absolute value is less than or equal to the preset residual threshold value are obtained, the pixel point coordinates are updated to the target pixel point coordinates, and the step of performing linear fitting on all the pixel point coordinates is repeated until there is no target residual absolute value greater than the preset residual threshold value in the residual absolute values, and a final straight line vector corresponding to the target line laser trace is obtained;
[0126] Based on the final straight line vector, a reference line of the line laser trace is confirmed.
[0127] In one or more embodiments, the detection module 105 is used to:
[0128] Selecting a target anti-glare plate from the plurality of anti-glare plates to be detected, and obtaining a target trace of the linear laser trace distributed on the target anti-glare plate;
[0129] In the case where the target trace is not obtained, the distortion feature of the line laser trace is identified as the target trace missing; in the case where the target trace is obtained, the distortion feature of the line laser trace is identified based on the distance between the pixel coordinates corresponding to the target trace and the reference line;
[0130] Based on the distortion characteristics of the line laser trace, a detection result of the target anti-glare plate is obtained.
[0131] In one or more embodiments, the detection module 105 is further configured to:
[0132] When the distances between the pixel coordinates corresponding to the target trace and the reference line are both less than or equal to a distance threshold, identifying the distortion feature of the line laser trace as no distortion;
[0133] When the distances between the pixel point coordinates corresponding to the target trace and the reference line are greater than a distance threshold, identifying the distortion feature of the line laser trace as a target trace offset;
[0134] When the distance from the reference line to the pixel point coordinates corresponding to the target trace is greater than the distance threshold and less than or equal to the distance threshold at the same time, the distortion feature of the line laser trace is identified as a bend of the target trace.
[0135] In one or more embodiments, the detection module 105 is further configured to:
[0136] When the distortion feature is no distortion, obtaining a detection result of the target anti-glare plate as no damage;
[0137] In the case where the distortion feature is target trace missing, obtaining a detection result of the target anti-glare plate as target anti-glare plate missing;
[0138] In the case where the distortion feature is a target trace offset, the detection result of the target anti-glare plate is obtained as a tilt deformation of the target anti-glare plate;
[0139] In the case where the distortion feature is a target trace bend, the detection result of the target anti-glare plate is obtained as a torsional deformation of the target anti-glare plate.
[0140] In one or more embodiments, the detection module 105 is used to:
[0141] When the anti-glare plate inspection image includes a plurality of line laser marks left by a plurality of line lasers, the plurality of anti-glare plates to be inspected are inspected based on each of the line laser marks and a reference line corresponding to each of the line laser marks.
[0142] The anti-glare plate detection device provided in the embodiment of the present disclosure and the anti-glare plate detection method provided in the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.
[0143] The present disclosure also provides a computer device to execute the above anti-glare plate detection method. Figure 5 It shows a schematic diagram of a computer device provided by some embodiments of the present disclosure. Figure 5 As shown, the computer device 8 includes: a processor 800, a memory 801, a bus 802 and a communication interface 803, and the processor 800, the communication interface 803 and the memory 801 are connected via the bus 802; the memory 801 stores a computer program that can be run on the processor 800, and when the processor 800 runs the computer program, the anti-glare plate detection method provided in any of the aforementioned embodiments of the present disclosure is executed.
[0144] The memory 801 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 803 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.
[0145] The bus 802 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 801 is used to store programs, and the processor 800 executes the programs after receiving execution instructions. The anti-glare plate detection method disclosed in any implementation of the aforementioned embodiment of the present disclosure may be applied to the processor 800, or implemented by the processor 800.
[0146] The processor 800 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 800. The above processor 800 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready-made programmable gate array (FPTA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 801, and the processor 800 reads the information in the memory 801 and completes the steps of the above method in combination with its hardware.
[0147] The computer device provided in the embodiment of the present disclosure and the anti-glare plate detection method provided in the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented therein.
[0148] An embodiment of the present disclosure also provides a computer-readable storage medium corresponding to the anti-glare plate detection method provided in the aforementioned embodiment. The computer-readable storage medium is a CD on which a computer program (i.e., a computer program product) is stored. When the computer program is run by a processor, it will execute the anti-glare plate detection method provided in any of the aforementioned embodiments.
[0149] It should be noted that examples of the computer-readable storage medium may also 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 optical or magnetic storage media, which are not listed here one by one.
[0150] The computer-readable storage medium provided by the above-mentioned embodiment of the present disclosure and the anti-glare plate detection method provided by the embodiment of the present disclosure are based on the same inventive concept, and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.
[0151] The present disclosure also provides a computer program product. Figure 6 The computer program product 600 carries a program code, namely a computer program 601. The instructions included in the computer program 601 can be used to execute the steps of the anti-glare plate detection method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.
[0152] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).
[0153] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.
[0154] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.
[0155] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.
[0156] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.
[0157] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.
[0158] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
[0159] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.
Claims
1. A method for detecting an anti-glare plate, characterized in that: include: Acquire an anti-glare plate detection image collected by a movable device, wherein the anti-glare plate detection image includes a plurality of anti-glare plates to be detected and line laser traces left by a same line laser on the plurality of anti-glare plates to be detected; Obtaining pixel coordinates corresponding to the line laser trace on the anti-glare plate detection image; Performing linear fitting on all the pixel point coordinates to obtain the straight line vector corresponding to the line laser trace; Based on all the pixel coordinates and the straight line vectors, determining the reference line of the line laser trace; Based on the linear laser trace and the reference line, a plurality of the anti-glare panels to be inspected are inspected.
2. The anti-glare plate detection method according to claim 1, characterized in that: Based on all the pixel point coordinates and the straight line vectors, determining the reference line of the target line laser trace includes: Calculating the residual absolute value of the coordinates of each pixel point and the straight line vector; In the case where there is a target residual absolute value greater than a preset residual threshold value in the residual absolute values, the target pixel point coordinates whose residual absolute value is less than or equal to the preset residual threshold value are obtained, the pixel point coordinates are updated to the target pixel point coordinates, and the step of performing linear fitting on all the pixel point coordinates is repeated until there is no target residual absolute value greater than the preset residual threshold value in the residual absolute values, and a final straight line vector corresponding to the target line laser trace is obtained; Based on the final straight line vector, a reference line of the line laser trace is confirmed.
3. The anti-glare plate detection method according to claim 1, characterized in that: Based on the line laser trace and the reference line, a plurality of the anti-glare panels to be inspected are inspected, including: Based on the preset position of each anti-glare plate to be detected on the anti-glare plate detection image, obtaining the target trace of the linear laser trace distributed on each anti-glare plate to be detected; In the case where all the target traces on the anti-glare plate to be detected are not obtained, the distortion feature of the line laser trace is identified as a partial loss; in the case where all the target traces on the anti-glare plate to be detected are obtained, the distortion feature of the line laser trace is identified based on the distance between the pixel coordinates corresponding to the target trace and the reference line; Based on the distortion characteristics of the line laser trace, detection results of the plurality of anti-glare panels to be detected are obtained.
4. The anti-glare plate detection method according to claim 3, characterized in that: Based on the distance between the pixel coordinates corresponding to the target trace and the reference line, identifying the distortion feature of the line laser trace includes: When the distances between the pixel coordinates corresponding to the target trace and the reference line are both less than or equal to a distance threshold, identifying the distortion feature of the line laser trace as no distortion; When the distances between the pixel coordinates corresponding to the target trace and the reference line are greater than a distance threshold, identifying the distortion feature of the line laser trace as a local offset; When the distance from the reference line to the pixel point coordinates corresponding to the target trace is greater than the distance threshold and less than or equal to the distance threshold at the same time, the distortion feature of the line laser trace is identified as a local bend.
5. The anti-glare plate detection method according to claim 4, characterized in that: Based on the distortion characteristics of the line laser trace, the detection results of the plurality of anti-glare panels to be detected are obtained, including: When the distortion feature is no distortion, obtaining a detection result of the plurality of anti-glare panels to be detected as no damage; In the case where the distortion feature is a partial loss, obtaining a detection result of the plurality of anti-glare panels to be detected as a partial loss of the anti-glare panels; In the case where the distortion feature is a local offset, obtaining a detection result of the plurality of anti-glare panels to be detected as a local tilt deformation of the anti-glare panels; In the case where the distortion feature is a local bend, the detection result of the plurality of anti-glare panels to be detected is a torsional deformation of the local anti-glare panels.
6. The anti-glare plate detection method according to claim 1, characterized in that: Based on the line laser trace and the reference line, a plurality of the anti-glare panels to be inspected are inspected, including: When the anti-glare plate inspection image includes a plurality of line laser marks left by a plurality of line lasers, the plurality of anti-glare plates to be inspected are inspected based on each of the line laser marks and a reference line corresponding to each of the line laser marks.
7. An anti-glare plate detection device, characterized in that: include: A first acquisition module is used to acquire an anti-glare plate detection image collected by a movable device, wherein the anti-glare plate detection image includes a plurality of anti-glare plates to be detected and line laser traces left by a same line laser on the plurality of anti-glare plates to be detected; A second acquisition module is used to acquire pixel coordinates corresponding to the line laser trace on the anti-glare plate detection image; A linear fitting module, used for performing linear fitting on all the pixel coordinates to obtain a straight line vector corresponding to the line laser trace; A calculation module, used for confirming the reference line of the line laser trace based on all the pixel point coordinates and the straight line vector; A detection module is used to detect the plurality of anti-glare panels to be detected based on the linear laser trace and the reference line.
8. A computer embedded device, comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.