A glass crack detection system and method on a conveyor belt

Abstract

The application relates to the technical field of image recognition, and discloses a glass crack detection system and method on a conveying belt, the detection system comprising a sealed box for shielding external light, a conveying belt for conveying glass passing through the sealed box, a light source and a camera being arranged in the sealed box, and a pneumatic blowing nozzle being arranged outside the sealed box and used for blowing the surface of the glass about to enter the sealed box; the camera is electrically connected with a server, the server establishes an ROI area according to video data information, monitors the pixel statistical features of the ROI area, and judges that a crack is detected when the pixel statistical features of the ROI area meet the glass crack condition. The application samples the video of the glass in the sealed box, eliminates the interference of the environmental light source on imaging, and reduces the image processing complexity; whether a crack exists is judged by comparing the gray standard deviation of the normal glass image, the calculation amount is small, and the glass crack judgment is completed under high-speed sampling of the video image.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image recognition, in particular to a glass crack detection system and method on a conveyor belt. BACKGROUND

[0002] Glass is an important material in daily life, production and scientific and technological fields. Because of its light transmission, it is widely used in the fields of building, furniture manufacturing, automobile and electronics, instruments, etc.

[0003] The glass produced from the kiln is usually transferred to other areas for storage through a conveyor belt. However, if the glass has cracks or even breaks on the conveyor belt, it not only indicates that the glass has quality problems, but also affects the normal conveying of the glass on the conveyor belt, and even causes congestion and leads to the phenomenon of subsequent glass breakage. Therefore, it is necessary to detect the glass cracks on the conveyor belt in a timely manner. SUMMARY

[0004] In order to overcome or alleviate one or more of the above technical problems, the present application aims to provide a glass crack detection system and method on a conveyor belt.

[0005] In one aspect, the present application provides a glass crack detection system on a conveyor belt, which comprises a closed box for shielding external light, a conveyor belt for conveying glass passing through the closed box, a light source for lighting and a camera for shooting glass video inside the closed box, and a pneumatic nozzle outside the closed box for blowing the surface of the glass about to enter the closed box.

[0006] The camera is electrically connected with a server, the camera transmits the collected video data information to the server, the server establishes an ROI area according to the video data information, and monitors the pixel statistical characteristics of the ROI area. When the pixel statistical characteristics of the ROI area meet the glass crack condition, it is judged that a crack is detected, that is, a shutdown signal is sent to the control device of the conveyor belt.

[0007] According to some embodiments, the pneumatic nozzle forms an angle of 45° with the horizontal plane.

[0008] In another aspect, the present application also provides a detection method of the above-mentioned glass crack detection system on a conveyor belt, which comprises the following steps:

[0009] S1: Start data collection, place the glass to be tested on the conveyor belt, and after the pneumatic nozzle blows the surface of the glass, the glass to be tested enters the closed box. Under the illumination of the light source, the camera arranged at the top of the closed box collects video data of the glass surface and transmits it to the server.

[0010] S2: the server reads a frame of image data on the acquired video data;

[0011] S3: whether a new mouse frame is drawn is detected, if yes, the ROI region is updated on the read image data and the image data of the new ROI region is extracted, if not, the image data of the ROI region is directly extracted on the read image data;

[0012] S4: the image of the ROI region is processed to obtain a gray picture;

[0013] S5: the gray picture is preprocessed by filtering;

[0014] S6: the mean and the standard deviation of the filtered image are calculated;

[0015] S7: the difference and the product thr of the mean and the standard deviation are calculated respectively, and the calculation formulas are as follows:

[0016] Δmean = mean - mean0; (1)

[0017] Δstd = std - std0; (2)

[0018] thr = Δmean * Δstd; (3)

[0019] Wherein, mean0 and std0 are the gray mean and the standard deviation of the last picture respectively;

[0020] S8: if the calibration process is needed, the maximum values dMeanMax and dStdMax of the absolute values of Δmean and Δstd and the minimum value Thr of thr are saved respectively, and the step S2 is executed; otherwise, the step S9 is executed;

[0021] S9: A = (first condition and second condition and third condition) is calculated, wherein:

[0022] The first condition is: the absolute value of Δmean is greater than dMeanMax?

[0023] The second condition is: the absolute value of Δstd is greater than dStdMax?

[0024] The third condition is: thr < K * Thr? Wherein K is a positive number greater than 1, but too large K value will lead to crack missed detection;

[0025] If the value of A is false, it is judged as no crack, and the step S2 is executed; otherwise, it is judged as having crack, and the step S10 is executed;

[0026] S10: Server alarm processing, send alarm information to the monitoring personnel, and send the conveyor belt stop control signal, then go to step S2 to continue the cycle detection of glass cracks.

[0027] According to some embodiments, in step S9, the value of K ranges from 2 to 5.

[0028] According to some embodiments, in step S3, the width of the ROI region is the maximum width of the glass on the conveyor belt, and the length of the ROI region is one fourth of the length of the video region of the camera.

[0029] Compared with the prior art, the present application has the following beneficial effects:

[0030] (1) The glass crack detection system provided by the present application can sample the video of the glass in the closed box, eliminate the interference of the environmental light source on the imaging, and reduce the complexity of image processing.

[0031] (2) The dust and debris on the surface of the glass are blown away by the blowing nozzle in front of the closed box, thereby reducing the false detection rate.

[0032] (3) The detection method provided by the present application can determine whether there is a crack by comparing the gray scale standard deviation of the normal glass image, without the need for edge feature extraction and other processes, so that the calculation amount is small, the calculation speed is fast, the glass crack can be determined under high-speed video image sampling, and the normal transmission of the glass on the production line is not affected. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 The figure is a structural schematic diagram of the glass crack detection system on the conveyor belt provided by the embodiment of the present application.

[0034] Figure 2 The figure is a flow chart of the detection method of the glass crack detection system on the conveyor belt provided by the embodiment of the present application.

[0035] Figure 3 The figure is a screenshot of the glass crack detection video provided by the embodiment of the present application.

[0036] Figure 4 The figure is another screenshot of the glass crack detection video provided by the embodiment of the present application.

[0037] Figure 5 The figure is a screenshot of the ROI region at a certain time in the glass crack detection provided by the embodiment of the present application.

[0038] Figure 6 The figure is a screenshot of the ROI region at a certain time in the glass crack detection provided by the embodiment of the present application.

[0039] Figure 7The ROI region screenshot picture at a certain time in the glass crack detection provided by the embodiment of the present application.

[0040] Figure 8 The ROI region screenshot picture at a certain time in the glass crack detection provided by the embodiment of the present application.

[0041] Figure 9 The ROI region screenshot picture at a certain time in the glass crack detection provided by the embodiment of the present application.

[0042] Figure 10 The ROI region screenshot picture at a certain time in the glass crack detection provided by the embodiment of the present application.

[0043] Figure 11 The ROI region screenshot picture at a certain time in the glass crack detection provided by the embodiment of the present application.

[0044] Figure 12 The ROI region screenshot picture at a certain time in the glass crack detection provided by the embodiment of the present application.

[0045] Figure 13 The ROI region screenshot picture at a certain time in the glass crack detection provided by the embodiment of the present application.

[0046] In the figure:

[0047] Conveying belt 1; closed box 2; camera 3; light source 4; pneumatic blow nozzle 5. DETAILED DESCRIPTION

[0048] The present application will be described in detail below with reference to the embodiments and drawings, but it should be understood that the embodiments and drawings are only used to exemplarily describe the present application, and cannot constitute any limitation on the protection scope of the present application. All reasonable modifications and combinations within the scope of the inventive concept of the present application fall within the protection scope of the present application.

[0049] The present application will be described in detail below with reference to the embodiments and drawings, but it should be understood that the embodiments and drawings are only used to exemplarily describe the present application, and cannot constitute any limitation on the protection scope of the present application. All reasonable modifications and combinations within the scope of the inventive concept of the present application fall within the protection scope of the present application.

[0050] Embodiment 1

[0051] As Figure 1 , the present embodiment provides a glass crack detection system on a conveying belt, which comprises a closed box 2 for shielding external light, a conveying belt 1 for conveying glass horizontally passing through the middle part of the closed box 2, a light source 4 arranged on the top surface of the closed box 2 for irradiating the glass, a camera 3 arranged on the top surface of the closed box 2 for shooting the image of the glass, and a pneumatic blow nozzle 5 arranged at a certain angle outside the closed box 2 for blowing the glass on the surface of the glass about to enter the closed box 2, which is preferably arranged at an angle of 45° on the horizontal plane.

[0052] The camera 3 is electrically connected with the server, and transmits the collected video data information to the server; the server monitors the pixel statistical characteristics (such as the mean and mean square deviation of the gray image) of the ROI region according to the video data information. When the pixel statistical characteristics of the ROI region exceed the set threshold value, it is judged that a crack is detected, that is, a stop signal is sent to the control device of the conveying belt 1.

[0053] Embodiment 2

[0054] As Figure 2 , based on embodiment 1, the embodiment provides a glass crack detection method on a conveying belt, comprising the following steps:

[0055] S1: placing the glass to be tested on the conveying belt 1, blowing the glass surface by the pneumatic nozzle 5, and then entering the closed box 2, under the illumination of the light source 4, the camera 3 collects video data of the glass surface and transmits it to the server;

[0056] S2: reading a frame of image data on the obtained video data;

[0057] S3: further extracting image data of the ROI region (ROI, i.e. Region of Interest) on the read image data.

[0058] In step S3, the size of the ROI region is determined by the operator operating the mouse frame. Since the operator may update the ROI region at any time, in the flowchart, it is necessary to detect whether a new mouse frame operation is generated in time. If the mouse frame is detected, the ROI region needs to be updated, otherwise the subsequent process is executed.

[0059] S4: performing gray scale processing on the image of the ROI region to obtain a gray scale picture;

[0060] S5: performing filter preprocessing on the gray scale picture;

[0061] S6: calculating the mean and standard deviation std of the filtered image gray scale;

[0062] S7: calculating the difference and product thr of mean and std respectively, and the calculation formulas are as follows:

[0063] Δmean = mean - mean0; (1)

[0064] Δstd = std - std0; (2)

[0065] thr = Δmean * Δstd; (3)

[0066] Wherein, mean0 and std0 are the gray scale mean and standard deviation of the last picture respectively.

[0067] S8: If it is necessary to enter the calibration process, save the maximum value dMeanMax of the absolute value of the record Δmean and the absolute value of the record Δstd, and the minimum value Thr of thr, respectively, and go to step S2; otherwise, go to step S9;

[0068] S9: Calculate A = first condition and second condition and third condition, wherein:

[0069] The first condition is: the absolute value of Δmean is greater than dMeanMax?

[0070] The second condition is: the absolute value of Δstd is greater than dStdMax?

[0071] The third condition is: thr < K * Thr? Wherein K is a positive number greater than 1, but too large K value will lead to crack missed detection; K value is taken as 2-5. If the glass has no crack, but the system alarm appears crack, it is necessary to increase the K value; if the glass appears crack, but the system fails to detect, it is necessary to reduce the K value.

[0072] If the value of A is false, it is judged as no crack, and no processing is done, and goes to step S2; otherwise, it is judged as having crack, and goes to step S10;

[0073] S10: Alarm processing, sends alarm information to the monitoring personnel, and sends the conveyor belt stop control signal, and then goes to step S2 to continue to detect the glass crack.

[0074] In step S1, the conveyor belt 1 horizontally passes through the closed box 2, and a pneumatic nozzle is configured at the inlet end of the closed box to spray compressed filtered air flow at 45° angle forward on the glass surface, reducing the dust entering the closed box, and blowing away the foreign matters on the glass.

[0075] In step S3, the width of the ROI region is the maximum width of the glass on the conveyor belt, ensuring to cover the width of the glass; in order to improve the detection speed and the area coverage of continuous sampling, the length of the ROI region is one fourth of the video region length of the camera 3.

[0076] In step S1, the camera 3 adopts video acquisition mode, which does not affect the continuous transportation of the glass by the conveyor belt 1.

[0077] Example 3

[0078] Based on the glass crack detection system on the conveyor belt provided in example 1 and the glass crack detection method on the conveyor belt provided in example 2, verification is carried out in this example.

[0079] Figure 3The image shows a video of glass crack detection. The white cylinder represents a roller on conveyor belt 1, with the glass on the roller (left side of the video screenshot). The glass is transparent; only the white line along its right edge is visible in the image. In the upper half of the image, the area in front of the white roller is suspended, with a light-colored horizontal bar that does not interfere with the system's crack detection. The area below is dark.

[0080] Figure 4 Draw a monitoring region ROI (yellow box) in the area in front of the white scroll wheel, covering the darker area in front of the scroll wheel.

[0081] The test results are explained below:

[0082] Appendix Figures 3-4 The video screenshot shows the glass moving downwards on a conveyor belt.

[0083] Once the feature parameters of the video data meet the crack condition, the system automatically saves the image in the ROI.

[0084] In a confined environment, when a crack appears in the glass, the refractive index at the crack changes, resulting in irregular black textures in the image (the dark background below the conveyor belt).

[0085] When a crack appears, the system takes screenshots of the ROI area and saves them in chronological order.

[0086] The following are the results of a certain experiment:

[0087] During the calibration process, the results of dMeanMax, dStdMax, and Thr are as follows:

[0088] dMeanMax=0.413527; dStdMax=0.23843; Thr=-0.435618.

[0089] The following table is attached. Figures 5-13 The corresponding calibration result list:

[0090]

[0091] Figures 5-13 In the diagram, the black lines represent cracks.

[0092] The above embodiments are merely preferred embodiments of the present invention, and the scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A glass crack detection system on a conveyor belt, characterized in that: It includes an airtight box for blocking external light. A conveyor belt for transporting glass passes through the airtight box. Inside the airtight box, there is a lighting source and a camera for taking videos of the glass. A pneumatic nozzle is arranged outside the airtight box to purge the surface of the glass that is about to enter the airtight box. The camera is electrically connected to a server. The camera transmits the collected video data information to the server. The server establishes a ROI region based on the video data information and monitors the pixel statistical features of the ROI region. When the pixel statistical features of the ROI region meet the glass crack condition, it is determined that a crack is detected, and then a stop signal is sent to the control device of the conveyor belt.

2. The glass crack detection system on a conveyor belt according to claim 1, characterized in that, The pneumatic nozzle forms an angle of 45° with the horizontal plane.

3. A detection method for a glass crack detection system on a conveyor belt as described in any one of claims 1 to 2, characterized in that: It includes the following steps: S1: Start data collection. Place the glass to be tested on the conveyor belt. After the pneumatic nozzle purges the surface of the glass, the glass to be tested enters the airtight box. Under the illumination of the light source, the camera arranged at the top inside the airtight box collects video data of the glass surface and transmits it to the server. S2: The server reads a frame of image data from the acquired video data. S3: Detect whether there is a new mouse drawing frame. If so, update the ROI region in the read image data and extract the image data of the new ROI region; if not, directly extract the image data of the ROI region from the read image data. S4: Perform grayscale processing on the image of the ROI region to obtain a grayscale picture. S5: Perform filter preprocessing on the grayscale picture. S6: Calculate the gray mean value mean and the standard deviation std of the filtered image. S7: Calculate the difference and their product thr of mean and std respectively. The calculation formulas are as follows: Δmean = mean - mean0; (1) Δstd = std - std0; (2) thr = Δmean * Δstd; (3) where mean0 and std0 are the gray mean value and the standard deviation of the previous picture respectively. S8: If it is necessary to enter the calibration process, record the maximum values dMeanMax and dStdMax of the absolute values of Δmean and Δstd respectively, and the minimum value Thr of thr, and then go to execute step S2; otherwise, go to execute step S9. S9: Calculate A = (the first condition and the second condition and the third condition), where: The first condition is: Is the absolute value of Δmean greater than dMeanMax? The second condition is: Is the absolute value of Δstd greater than dStdMax? The third condition is: Is thr < K * Thr? where K is a positive number greater than 1, but an overly large K value will cause cracks to be missed. If the value of A is false, it is determined that there is no crack, and then go to execute step S2; otherwise, it is determined that there is a crack, and enter step S10. S10: The server performs alarm processing, sends an alarm message to the monitoring personnel, and sends a conveyor belt stop control signal, and then goes to execute step S2 to continue to cycle and detect glass cracks.

4. The detection method according to claim 3, characterized in that: In step S9, the value range of K is 2 - 5.

5. The detection method according to claim 3, characterized in that: In step S3, the width of the ROI region is the maximum width of the glass on the conveyor belt; the length of the ROI region is one-quarter of the length of the video area of ​​the camera.

Images