Conveyor belt detection method, device and storage medium

Abstract

The present disclosure proposes a conveyor belt detection method, device and storage medium, the method comprising: obtaining multiple first images of the conveyor belt surface captured by a first camera of a binocular vision system, and judging whether there is an abnormal image among the multiple first images, and when there is an abnormal image, obtaining a second image of the conveyor belt surface captured by a second camera of the binocular vision system, wherein the second image and the abnormal image are images captured at the same time, and judging whether the conveyor belt is damaged based on the abnormal image and the second image, so as to be able to perform comprehensive quantitative detection of the conveyor belt, improve the accuracy of detection, and do not need to rely on the amount of sample data. In addition, the present solution only performs binocular image detection when there is an abnormality in the image captured by a single camera, thereby avoiding real-time binocular image detection, reducing the occupation of computing resources, and improving the effect of conveyor belt detection.

Description

Technical Field

[0001] The present disclosure relates to the field of image detection technology, and in particular to a conveyor belt detection method, device and storage medium. Background Art

[0002] Belt conveyor is one of the main transportation equipment in coal mines. It is easy to be damaged by tearing during use. If the abnormal condition of the belt surface is not discovered in time, serious production accidents are likely to occur.

[0003] In the related technology, the detection method based on linear laser assistance or the detection method based on machine learning is generally used. Among them, the detection method based on linear laser assistance is mainly used to identify longitudinal tears. Since it only performs calculations and processing on the laser stripe area, it only judges whether the belt has longitudinal tears from the fluctuation of the laser stripes. It is easily affected by residual coal and wear on the surface of the belt, and it is impossible to quantify and analyze abnormal conditions. The detection method based on machine learning cannot quantify and analyze the tearing situation; and because it is difficult to collect a large number of image samples of belt tears, methods such as deep learning that rely more on the amount of sample data are difficult to be effectively applied. Therefore, it affects the detection effect of the conveyor belt surface health. Summary of the invention

[0004] The present application proposes a conveyor belt detection method, device and storage medium, aiming to solve one of the technical problems in the related art at least to a certain extent.

[0005] The first aspect of the present application proposes a conveyor belt detection method, including: acquiring multiple first images of the conveyor belt surface captured by a first camera, wherein the first camera is a first camera of a binocular vision system; determining whether there is an abnormal image among the multiple first images; if there is an abnormal image, acquiring a second image of the conveyor belt surface captured by a second camera, wherein the second image and the abnormal image are images captured at the same time, and the second camera is a second camera of the binocular vision system; and determining whether the conveyor belt is damaged based on the abnormal image and the second image.

[0006] The second aspect of the present application proposes a conveyor belt detection device, including: a first acquisition module, used to acquire multiple first images of the conveyor belt surface captured by a first camera, wherein the first camera is a first camera of a binocular vision system; a first judgment module, used to judge whether there is an abnormal image among the multiple first images; a second acquisition module, used to acquire a second image of the conveyor belt surface captured by a second camera if an abnormal image exists, wherein the second image and the abnormal image are images captured at the same time, and the second camera is a second camera of a binocular vision system; and a second judgment module, used to judge whether the conveyor belt is damaged based on the abnormal image and the second image.

[0007] The third aspect embodiment of the present application proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the conveyor belt detection method of the embodiment of the present application.

[0008] The fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the conveyor belt detection method disclosed in the embodiment of the present application.

[0009] In this embodiment, by acquiring multiple first images of the conveyor belt surface captured by the first camera of the binocular vision system, and judging whether there are abnormal abnormal images in the multiple first images, and when there are abnormal images, acquiring the second image of the conveyor belt surface captured by the second camera of the binocular vision system, wherein the second image and the abnormal image are images captured at the same time, and judging whether the conveyor belt is damaged based on the abnormal image and the second image, the conveyor belt can be comprehensively quantitatively detected, the accuracy of the detection is improved, and it does not need to rely on the amount of sample data. In addition, this scheme only performs binocular image detection when there is an abnormality in the image captured by a single camera, thereby avoiding real-time binocular image detection, reducing the occupation of computing resources, and improving the effect of conveyor belt detection. This solves the technical problems existing in the related art that affect the detection effect of the belt surface health of the conveyor belt.

[0010] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0012] Figure 1 It is a flow chart of a conveyor belt detection method provided according to an embodiment of the present disclosure;

[0013] Figure 2 is a structural schematic diagram of a conveyor belt detection system provided according to an embodiment of the present disclosure;

[0014] Figure 3 is a flow chart of a conveyor belt detection method provided according to another embodiment of the present disclosure;

[0015] Figure 4is a flow chart of a conveyor belt detection method provided according to another embodiment of the present disclosure;

[0016] Figure 5 is a schematic diagram of a conveyor belt detection process provided according to an embodiment of the present disclosure;

[0017] Figure 6 is a schematic diagram of a conveyor belt detection device provided according to another embodiment of the present disclosure;

[0018] Figure 7 A block diagram of an exemplary computer device suitable for implementing embodiments of the present application is shown. DETAILED DESCRIPTION

[0019] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present disclosure, and are not to be construed as limitations of the present disclosure. On the contrary, the embodiments of the present disclosure include all changes, modifications, and equivalents that fall within the spirit and connotation of the appended claims.

[0020] In order to solve the technical problem that the use of linear laser-assisted detection methods or machine learning-based detection methods in the related technologies mentioned in the background technology affects the detection effect of the health of the conveyor belt surface, the technical solution of this embodiment provides a conveyor belt detection method, which is described in conjunction with specific embodiments below.

[0021] It should be noted that the executor of the conveyor belt detection method of this embodiment can be a conveyor belt detection device, which can be implemented by software and / or hardware. The device can be configured in an electronic device, and the electronic device can include but is not limited to a terminal, a server, etc.

[0022] Figure 1 is a flow chart of a conveyor belt detection method provided according to an embodiment of the present disclosure, such as Figure 1 As shown, the method includes:

[0023] S101: Acquire a plurality of first images of the conveyor belt surface captured by a first camera.

[0024] Among them, the conveyor in the embodiment of the present disclosure can be a belt conveyor. During the operation of the conveyor, the present solution can use a first camera to capture images of the surface of the conveyor belt, for example: continuously capturing single-frame images, or capturing videos and capturing multiple continuous video frames from the video, thereby obtaining multiple first images.

[0025] The first camera is the first camera of a binocular vision system. The first camera and the second camera of the binocular vision system can simultaneously capture images of the conveyor belt. In the process of detecting the conveyor belt, the first camera first captures multiple first images, and the images captured by the second camera are stored. That is to say, the conveyor belt detection method of this scheme uses a monocular camera as a normalized detection.

[0026] Figure 2 is a structural schematic diagram of a conveyor belt detection system provided according to an embodiment of the present disclosure, such as Figure 2 As shown, generally, the conveyor belt detection system may include a binocular vision system, an industrial computer, and an LED array light source. The binocular vision system may be arranged in the area below the return path of the conveyor to collect images of the conveyor belt surface, the LED array light source is used for supplementary lighting during the image collection process, and the industrial computer is used to detect the conveyor belt according to the images collected by the binocular vision system to determine whether the belt surface is damaged. That is to say, the conveyor belt detection method provided in this embodiment may be executed by the industrial computer.

[0027] In some embodiments, the detection area (i.e., the image acquisition area) is the overlapping area of ​​the fields of view of the first camera and the second camera of the binocular vision system, and the field of view widths of the first camera and the second camera are greater than the width of the conveyor belt, and the field of view lengths of the first camera and the second camera are greater than the product of the maximum speed of the conveyor and the single-frame image processing time, thereby ensuring that each frame of the image of the conveyor belt surface is completely acquired, which is facilitating subsequent detection of the conveyor belt surface.

[0028] S102: Determine whether there is an abnormal image among the multiple first images.

[0029] Among them, the images in which the belt surface has abnormal conditions such as scratches, dirt, cracks, etc. in the multiple first images can be called abnormal images.

[0030] After acquiring the plurality of first images, the embodiment of the present disclosure can determine whether the abnormal image exists in the plurality of first images. In some embodiments, an image recognition algorithm can be used to identify the plurality of first images to determine whether there is an abnormal image, or manual recognition can be used to determine whether there is an abnormal image, or any other possible method can be used to determine the abnormal image, without limitation.

[0031] S103: When there is an abnormal image, obtain a second image of the conveyor belt surface captured by a second camera, wherein the second image and the abnormal image are images captured at the same time, and the second camera is a second camera of a binocular vision system.

[0032] In the above-mentioned case where it is determined that there is an abnormal image, this embodiment can obtain a second image of the conveyor belt surface captured by the second camera of the binocular vision system, wherein the second image and the abnormal image are images captured at the same time, that is: two frames of abnormal images of the conveyor belt surface captured by the binocular vision system at the same time.

[0033] In the actual conveyor belt inspection process, the first image captured by the first camera can be used to perform a single-purpose normalized inspection of the belt surface, and the image captured by the second camera is temporarily stored. When the detection result of the first image is normal, no other operations are performed on the image captured by the second camera; when the first image captured by the first camera is abnormal, the second image corresponding to the abnormal image captured by the second camera is obtained.

[0034] S104: Determine whether the conveyor belt is damaged based on the abnormal image and the second image.

[0035] That is to say, when the monocular camera initially detects that there is an abnormality on the belt surface, this embodiment can perform binocular detection in combination with the abnormal image and the corresponding second image to further determine whether the conveyor belt is damaged.

[0036] In this embodiment, by acquiring multiple first images of the conveyor belt surface captured by the first camera of the binocular vision system, and judging whether there are abnormal abnormal images in the multiple first images, and when there are abnormal images, acquiring the second image of the conveyor belt surface captured by the second camera of the binocular vision system, wherein the second image and the abnormal image are images captured at the same time, and judging whether the conveyor belt is damaged based on the abnormal image and the second image, the conveyor belt can be comprehensively quantitatively detected, the accuracy of the detection is improved, and it does not need to rely on the amount of sample data. In addition, this scheme only performs binocular image detection when there is an abnormality in the image captured by a single camera, thereby avoiding real-time binocular image detection, reducing the occupation of computing resources, and improving the effect of conveyor belt detection. This solves the technical problems existing in the related art that affect the detection effect of the belt surface health of the conveyor belt.

[0037] Figure 3 is a flow chart of a conveyor belt detection method provided according to another embodiment of the present disclosure, such as Figure 3 As shown, the method includes:

[0038] S301: Acquire a plurality of first images of the conveyor belt surface captured by a first camera, wherein the first camera is a first camera of a binocular vision system.

[0039] The specific description of S301 can be found in the above embodiment and will not be repeated here.

[0040] S302: Segmenting the regions in the plurality of first images that are different from the belt surface background.

[0041] In the embodiment of the present disclosure, in the operation of determining whether there are abnormal images among multiple first images, the regions in the multiple first images that are different from the belt surface background are first segmented, that is, the regions in the segmented images that are significantly different from the belt surface background may be abnormal regions with tearing, stains, etc.

[0042] In some embodiments, for example, the Otsu threshold segmentation method may be used to segment the region, or any other possible method or algorithm may be used to segment the region, which is not limited.

[0043] In other embodiments, before segmentation, the first image may be subjected to median filtering to reduce image noise, and a histogram equalization method may be used for image enhancement and other preprocessing to increase the contrast between the belt surface background and the abnormal area, thereby facilitating accurate image segmentation.

[0044] S303: Determine the minimum circumscribed rectangle of the segmented area with differences, and use the minimum circumscribed rectangle as the belt abnormality area.

[0045] After the above segmentation obtains the area where the difference exists, further, the minimum circumscribed rectangle of the area is determined, and the minimum circumscribed rectangle is used as the belt abnormal area.

[0046] In some embodiments, for example, a function in an open source computer vision library OPENCV may be used to determine the minimum bounding rectangle, or other methods may be used to determine the bounding rectangle, which is not limited thereto.

[0047] S304: Calculate the health status of the belt abnormal area in the multiple first images to obtain multiple evaluation values ​​corresponding to the multiple first images.

[0048] The numerical value obtained by calculating the health level of the abnormal belt area may be referred to as an evaluation value, and each first image may correspond to an evaluation value.

[0049] In some embodiments, the abnormal pixels in the minimum bounding rectangle corresponding to each first image can be first determined, and the pixel ratio of the abnormal pixels can be further calculated, that is, the ratio of the pixels in the abnormal area to all the pixels in the minimum bounding rectangle. The abnormal pixels can be determined and the pixel ratio can be calculated in any manner without limitation.

[0050] Furthermore, the health status of the belt abnormality area in the plurality of first images is calculated based on the pixel ratio and the minimum circumscribed rectangle.

[0051] In some embodiments, the health degree of the belt abnormal area in the plurality of first images is calculated according to the pixel ratio and the minimum bounding rectangle, and the calculation may be performed according to the following formula:

[0052] Evaluation value=ω*a(i)+β*b(i)+γ*s(i)

[0053] Among them, a is the length of the minimum circumscribed rectangle, b is the width of the minimum circumscribed rectangle, s is the pixel ratio, ω, β, γ are the weight coefficients corresponding to a, b, s respectively, and i is the number of multiple first images.

[0054] It can be understood that the above formula is only an exemplary method for calculating the evaluation value. In practical applications, the evaluation value can also be calculated in any other possible manner, and there is no limitation to this.

[0055] S305: Determine the maximum evaluation value among the multiple evaluation values.

[0056] The maximum evaluation value can be represented by Score, Score=max(ω*a(i)+β*b(i)+γ*s(i)), i=1, ..., n, and n is the number of the multiple first images.

[0057] S306: Determine whether there is an abnormal image among the plurality of first images according to the maximum evaluation value and the first threshold.

[0058] After obtaining the maximum evaluation value, the maximum evaluation value Score is further compared with the first threshold (K) to determine whether there is an abnormal image among the multiple first images. For example, when Score is greater than K, the first image corresponding to the maximum evaluation value is determined to be an abnormal image.

[0059] In some other embodiments, a deep learning method can also be used to detect abnormal conditions of the belt in the image. By collecting images of fault conditions such as longitudinal tearing of the belt and images of the normal and undamaged belt surface, the abnormal areas in the image are manually marked, a training data set is constructed, and a deep neural network model is trained to detect abnormal areas on the belt surface and mark them with rectangular boxes.

[0060] When judging whether there is an abnormal image, this embodiment can first determine the abnormal area, then calculate the abnormal pixel ratio of the abnormal area, and quantitatively evaluate the health level according to the pixel ratio of the abnormal area, and determine whether there is an abnormal image through a threshold. Therefore, the abnormal image can be accurately judged, and the influence of factors such as scratches on the belt surface, normal wear and dirt can be eliminated, and different needs can be met by adjusting the threshold.

[0061] S307: If there is an abnormal image, obtain a second image of the conveyor belt surface captured by a second camera, wherein the second image and the abnormal image are images captured at the same time, and the second camera is a second camera of a binocular vision system

[0062] S308: Determine whether the conveyor belt is damaged based on the abnormal image and the second image.

[0063] The specific description of S307-S308 can be found in the above embodiment and will not be repeated here.

[0064] In this embodiment, by acquiring multiple first images of the conveyor belt surface captured by the first camera of the binocular vision system, and judging whether there are abnormal abnormal images in the multiple first images, and when there are abnormal images, acquiring the second image of the conveyor belt surface captured by the second camera of the binocular vision system, wherein the second image and the abnormal image are images captured at the same time, and judging whether the conveyor belt is damaged according to the abnormal image and the second image, the conveyor belt can be comprehensively quantitatively detected, the accuracy of the detection is improved, and it does not need to rely on the amount of sample data. In addition, this scheme only performs binocular image detection when there is an abnormality in the image captured by a single camera, thereby avoiding real-time binocular image detection, reducing the occupation of computing resources, and improving the effect of conveyor belt detection. Thus, the technical problems existing in the related art that affect the detection effect of the belt surface health of the conveyor belt are solved. In addition, this scheme can also accurately determine the abnormal image, eliminate the influence of factors such as scratches, normal wear and dirt on the belt surface, and meet different needs by adjusting the threshold.

[0065] Figure 4 is a flow chart of a conveyor belt detection method provided according to another embodiment of the present disclosure, such as Figure 4 As shown, the method includes:

[0066] S401: Acquire a plurality of first images of the conveyor belt surface captured by a first camera, wherein the first camera is a first camera of a binocular vision system.

[0067] S402: Determine whether there is an abnormal image among the multiple first images.

[0068] S403: If there is an abnormal image, a second image of the conveyor belt surface captured by a second camera is obtained, wherein the second image and the abnormal image are images captured at the same time, and the second camera is a second camera of a binocular vision system.

[0069] The specific description of S401 - S403 can be found in the above embodiment and will not be repeated here.

[0070] S404: Perform stereo matching on the abnormal image and the second image to obtain a binocular disparity image.

[0071] In the process of determining whether a conveyor belt is damaged based on an abnormal image and a second image, the disclosed embodiment first performs stereoscopic correction, stereo matching and other operations on the abnormal image and the second image to obtain a stereoscopic binocular parallax image.

[0072] S405: Calculate a first average value of depth information of the abnormal area of ​​the binocular parallax image, and calculate a second average value of depth information of the background area of ​​the binocular parallax image.

[0073] Further, the depth information of the abnormal area of ​​the binocular disparity image is calculated. For example, the depth information can be calculated according to each abnormal pixel coordinate in the abnormal area, and the average value of the depth information of the abnormal pixel coordinates is further calculated, which can be called a first average value.

[0074] Furthermore, the depth information of the background area of ​​the binocular disparity image may be calculated, that is, the depth information of each normal pixel coordinate in the normal background area, and the average value of the depth information of the normal pixel coordinates may be calculated to obtain a second average value.

[0075] S406: Calculate the difference between the first average value and the second average value.

[0076] That is, the second average value of the depth information of the background area on the belt surface in the binocular parallax image is subtracted from the first average value of the depth information of the abnormal area to obtain a difference.

[0077] S407: If the difference is greater than the second threshold, it is determined that the conveyor belt is damaged.

[0078] Furthermore, the difference is compared with a second threshold value, and when the difference is greater than the second threshold value, it is determined that the abnormal area is damaged, that is, the conveyor belt is damaged. The second threshold value can be flexibly set according to the actual application scenario, and there is no restriction on this.

[0079] Therefore, this embodiment can obtain a binocular parallax image based on the abnormal image and the second image, and judge whether the conveyor belt is damaged based on the depth values ​​of the abnormal area and the normal area of ​​the binocular inspection image, thereby improving the accuracy of the judgment result, and can be flexibly applied to different application scenarios through the setting of thresholds.

[0080] In the disclosed embodiment, by acquiring multiple first images of the conveyor belt surface captured by the first camera of the binocular vision system, and judging whether there are abnormal abnormal images in the multiple first images, and when there are abnormal images, acquiring the second image of the conveyor belt surface captured by the second camera of the binocular vision system, wherein the second image and the abnormal image are images captured at the same time, and judging whether the conveyor belt is damaged based on the abnormal image and the second image, the conveyor belt can be comprehensively quantitatively detected, the accuracy of the detection is improved, and it does not need to rely on the amount of sample data. In addition, this scheme only performs binocular image detection when there is an abnormality in the image captured by a single camera, thereby avoiding real-time binocular image detection, reducing the occupation of computing resources, and improving the effect of conveyor belt detection. In addition, judging whether the conveyor belt is damaged based on the depth values ​​of the abnormal area and the normal area of ​​the binocular inspection image, the accuracy of the judgment result can be improved, and it can be flexibly applied to different application scenarios through the setting of thresholds.

[0081] Figure 5 is a schematic diagram of a conveyor belt detection process provided according to an embodiment of the present disclosure, such as Figure 5 As shown, during the conveyor belt inspection process, firstly, the A and B cameras of the binocular vision system are used to collect images. Furthermore, a health quantitative assessment is performed on the belt surface of the image collected by the A camera. Further, the image collected by the B camera is obtained based on the assessment result. Then, the depth map is calculated based on the images collected by the A and B cameras to determine whether the belt has a fault, and then decide whether to issue an alarm or perform an emergency stop.

[0082] Figure 6 Schematic diagram of a conveyor belt detection device provided according to another embodiment of the present disclosure. Figure 6 As shown, the conveyor belt detection device 60 includes:

[0083] A first acquisition module 601 is used to acquire a plurality of first images of the conveyor belt surface captured by a first camera, wherein the first camera is a first camera of a binocular vision system;

[0084] A first judging module 602 is used to judge whether there is an abnormal image among the plurality of first images;

[0085] A second acquisition module 603 is used to acquire a second image of the conveyor belt surface acquired by a second camera when there is an abnormal image, wherein the second image and the abnormal image are acquired at the same time, and the second camera is a second camera of a binocular vision system; and

[0086] The second judgment module 604 is used to judge whether the conveyor belt is damaged according to the abnormal image and the second image.

[0087] In some embodiments, the first judgment module 602 includes: a first calculation submodule, used to calculate the health status of the abnormal belt area in multiple first images to obtain multiple evaluation values ​​corresponding to the multiple first images; a first determination submodule, used to determine the maximum evaluation value among the multiple evaluation values; and a first judgment submodule, used to judge whether there are abnormal images in the multiple first images based on the maximum evaluation value and the first threshold.

[0088] In some embodiments, the device 60 also includes: a segmentation submodule for segmenting areas in multiple first images that are different from the belt surface background; and a second determination submodule for determining the minimum circumscribed rectangle of the segmented different areas, and using the minimum circumscribed rectangle as the belt abnormality area.

[0089] In some embodiments, the calculation submodule is specifically used to: determine the pixel ratio of abnormal pixels in the minimum circumscribed rectangle corresponding to each first image; and calculate the health status of the abnormal belt area in multiple first images based on the pixel ratio and the minimum circumscribed rectangle.

[0090] In some embodiments, the calculation submodule is specifically used to: perform calculations according to the following formula: Evaluation value = ω*a(i)+β*b(i)+γ*s(i), wherein a is the length of the minimum enclosing rectangle, b is the width of the minimum enclosing rectangle, s is the pixel ratio, ω, β, and γ are weight coefficients corresponding to a, b, and s, respectively, and i is the number of multiple first images.

[0091] In some embodiments, the second judgment module 604 includes: a processing submodule, used to perform stereo matching on the abnormal image and the second image to obtain a binocular parallax image; a second calculation submodule, used to calculate a first average value of the depth information of the abnormal area of ​​the binocular parallax image, and calculate a second average value of the depth information of the background area of ​​the binocular parallax image; a third calculation submodule, used to calculate the difference between the first average value and the second average value; and a second judgment submodule, used to judge that the conveyor belt is damaged when the difference is greater than a second threshold.

[0092] In some embodiments, the binocular vision system is disposed in the return area below the conveyor, the field of view width of the first camera and the second camera is greater than the width of the conveyor belt, and the field of view length of the first camera and the second camera is greater than the product of the maximum rotation speed of the conveyor and the single-frame image processing time.

[0093] In this embodiment, by acquiring multiple first images of the conveyor belt surface captured by the first camera of the binocular vision system, and judging whether there are abnormal abnormal images in the multiple first images, and when there are abnormal images, acquiring the second image of the conveyor belt surface captured by the second camera of the binocular vision system, wherein the second image and the abnormal image are images captured at the same time, and judging whether the conveyor belt is damaged based on the abnormal image and the second image, the conveyor belt can be comprehensively quantitatively detected, the accuracy of the detection is improved, and it does not need to rely on the amount of sample data. In addition, this scheme only performs binocular image detection when there is an abnormality in the image captured by a single camera, thereby avoiding real-time binocular image detection, reducing the occupation of computing resources, and improving the effect of conveyor belt detection. This solves the technical problems existing in the related art that affect the detection effect of the belt surface health of the conveyor belt.

[0094] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0095] In order to implement the above embodiments, the present application also proposes a computer program product. When the instruction processor in the computer program product is executed, the conveyor belt detection method proposed in the above embodiments of the present application is executed.

[0096] Figure 7 A block diagram of an exemplary computer device suitable for implementing embodiments of the present application is shown. Figure 7 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0097] like Figure 7 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0098] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.

[0099] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0100] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 Not shown, often called a "hard drive").

[0101] although Figure 7 Not shown, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0102] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0103] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0104] The processing unit 16 executes various functional applications by running programs stored in the system memory 28, such as implementing the conveyor belt detection method mentioned in the above embodiment.

[0105] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0106] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

[0107] It should be noted that, in the description of this application, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0108] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0109] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0110] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0111] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0112] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0113] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0114] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A conveyor belt detection method, characterized in that: include: Acquire a plurality of first images of the conveyor belt surface captured by a first camera, wherein the first camera is a first camera of a binocular vision system; Determining whether there is an abnormal image among the plurality of first images; If the abnormal image exists, obtaining a second image of the conveyor belt surface captured by a second camera, wherein the second image and the abnormal image are images captured at the same time, and the second camera is a second camera of the binocular vision system; and Based on the abnormal image and the second image, determine whether the conveyor belt is damaged, wherein the abnormal image and the second image are stereo matched to obtain a binocular parallax image, calculate a first average value of depth information of the abnormal area of ​​the binocular parallax image, calculate a second average value of depth information of the background area of ​​the binocular parallax image, calculate a difference between the first average value and the second average value, and if the difference is greater than a second threshold, determine that the conveyor belt is damaged.

2. The method according to claim 1, characterized in that Determining whether there is an abnormal image among the plurality of first images includes: Calculating the health degree of the belt abnormal area in the plurality of first images to obtain a plurality of evaluation values ​​corresponding to the plurality of first images; determining a maximum evaluation value among the plurality of evaluation values; and It is determined whether there is an abnormal image among the plurality of first images according to the maximum evaluation value and the first threshold.

3. The method according to claim 2, characterized in that Before evaluating the health of the belt abnormal area in the plurality of first images, the method further includes: Segmenting the regions in the plurality of first images that are different from the belt surface background; and The minimum circumscribed rectangle of the segmented area with differences is determined, and the minimum circumscribed rectangle is used as the belt abnormality area.

4. The method according to claim 3, characterized in that Calculating the health status of the belt abnormal area in the plurality of first images includes: Determining the pixel ratio of abnormal pixels in the minimum bounding rectangle corresponding to each first image; and The health status of the belt abnormality area in the plurality of first images is calculated according to the pixel ratio and the minimum circumscribed rectangle.

5. The method according to claim 4, characterized in that The health status of the belt abnormality area in the plurality of first images is calculated according to the pixel ratio and the minimum circumscribed rectangle, Included, calculated according to the following formula: Evaluation value=ω*a(i)+β*b(i)+γ*s(i) Among them, a is the length of the minimum circumscribed rectangle, b is the width of the minimum circumscribed rectangle, s is the pixel ratio, ω, β, γ are weight coefficients corresponding to a, b, s respectively, and i is the number of multiple first images.

6. The method according to claim 1, characterized in that The binocular vision system is arranged in the area below the return journey of the conveyor, the field of view width of the first camera and the second camera is greater than the width of the conveyor belt, and the field of view length of the first camera and the second camera is greater than the product of the maximum rotation speed of the conveyor and the single-frame image processing time.

7. A conveyor belt detection device, characterized in that: include: A first acquisition module, used to acquire a plurality of first images of the conveyor belt surface captured by a first camera, wherein the first camera is a first camera of a binocular vision system; A first judging module, used for judging whether there is an abnormal image among the plurality of first images; a second acquisition module, configured to acquire a second image of the conveyor belt surface acquired by a second camera if the abnormal image exists, wherein the second image and the abnormal image are acquired at the same time, and the second camera is a second camera of the binocular vision system; and A second judgment module is used to judge whether the conveyor belt is damaged based on the abnormal image and the second image, wherein the abnormal image and the second image are stereo matched to obtain a binocular parallax image, a first average value of depth information of the abnormal area of ​​the binocular parallax image is calculated, a second average value of depth information of the background area of ​​the binocular parallax image is calculated, and a difference between the first average value and the second average value is calculated. If the difference is greater than a second threshold, it is judged that the conveyor belt is damaged.

8. The device according to claim 7, characterized in that The first judgment module includes: A first calculation submodule, configured to calculate the health status of the belt abnormal area in the plurality of first images to obtain a plurality of evaluation values ​​corresponding to the plurality of first images; A first determining submodule is used to determine the maximum evaluation value among the multiple evaluation values; and The first judgment submodule is used to judge whether there is an abnormal image among the multiple first images according to the maximum evaluation value and the first threshold.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

Images