A conveyor belt jam detection method, apparatus, electronic device and storage medium

Abstract

The application relates to a conveyor belt blockage detection method and device, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring a video image to be detected of the conveyor belt and a preset background image frame; acquiring a difference image frame in the video image to be detected according to the video image to be detected and the preset background image frame; inputting the difference image frame and the preset background image frame into a pre-trained difference detection model for difference detection; and determining a blockage detection result of the conveyor belt according to a detection result of the difference detection model. By pre-inspecting the video image frames in the video image to be detected, suspected blockage frames in the video image are detected, the frequency at which a difference detection algorithm based on feature comparison needs to be run is reduced, the real-time performance of detection is realized, suspected blockage frames are detected by using the difference detection algorithm based on feature comparison, the accuracy of detection is realized, and the like.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, apparatus, electronic device, and storage medium for detecting conveyor belt blockage. Background Technology

[0002] In the production process, conveyor belts play a vital role. Once a blockage occurs, relying solely on personnel to locate the blockage is time-consuming and labor-intensive, severely impacting actual production efficiency and causing economic losses. Therefore, by utilizing monitoring equipment to automatically locate the blockage, it is possible to effectively help staff quickly identify and resolve the problem, thereby improving production efficiency and increasing factory economic benefits.

[0003] Existing technologies that use monitoring equipment to automatically locate blockages cannot achieve real-time and accurate location of blockages.

[0004] There is currently no effective solution to the problem that existing technologies cannot accurately locate blockages in real time. Summary of the Invention

[0005] This embodiment provides a conveyor belt blockage detection method, apparatus, electronic device, and storage medium to solve the problem in the prior art that the blockage location cannot be located in real time and accurately.

[0006] Firstly, this embodiment provides a conveyor belt blockage detection method, the method comprising:

[0007] Acquire the video image to be detected and the preset background image frame of the conveyor belt;

[0008] Based on the video image to be detected and the preset background image frame, obtain the difference image frame in the video image to be detected;

[0009] The difference image frame and the preset background image frame are input into a pre-trained difference detection model for difference detection;

[0010] Based on the detection results of the difference detection model, the blockage detection result of the conveyor belt is determined.

[0011] In some embodiments, obtaining the difference image frames in the video image to be detected based on the video image to be detected and a preset background image frame includes:

[0012] Calculate the frame difference between the video image frame in the video image to be detected and the preset background image frame; when the frame difference is greater than the preset value, determine the video image frame of the video image to be detected as the difference image frame.

[0013] In some embodiments, inputting the difference image frame and the preset background image frame into a pre-trained difference detection model for difference detection includes:

[0014] The difference image frame is input into the first feature detection model for feature detection, and the preset background image frame is input into the second feature detection model for feature detection;

[0015] The features output by the first feature detection model and the features output by the second feature detection model are fused together.

[0016] The features after feature fusion are input into the target region detection model to perform target region detection.

[0017] In some embodiments, the first feature detection model includes multiple feature extraction layers, and the second feature detection model includes multiple feature extraction layers;

[0018] The feature extraction layer includes multiple residual blocks, and each residual block includes a dilated convolutional layer.

[0019] In some embodiments, the third feature extraction layer of the first feature detection model includes multiple residual blocks, each of which includes a dilated convolutional layer; the third feature extraction layer of the second feature detection model includes multiple residual blocks, each of which includes a dilated convolutional layer.

[0020] In some embodiments, calculating the frame difference between a video image frame in the video image to be detected and a preset background image frame; and determining the video image frame of the video image to be detected as the difference image frame when the frame difference is greater than a preset value includes:

[0021] Calculate the difference in pixel grayscale values ​​between the video image frame in the video image to be detected and the preset background image frame; when the difference in pixel grayscale values ​​is greater than the preset grayscale difference, determine the video image frame of the video image to be detected as the difference image frame.

[0022] In some embodiments, the blockage detection result of the conveyor belt is determined based on the detection result of the difference detection model:

[0023] Based on the target area detection box output by the target area detection model, the blockage area of ​​the conveyor belt is determined.

[0024] Secondly, this embodiment provides a conveyor belt blockage detection device, the device comprising:

[0025] The first acquisition module is used to acquire the video image to be detected and the preset background image frame of the conveyor belt;

[0026] The second acquisition module is used to acquire the difference image frames in the video image to be detected based on the video image to be detected and the preset background image frames;

[0027] The input module is used to input the difference image frame and the preset background image frame into a pre-trained difference detection model for difference detection;

[0028] The detection module is used to determine the blockage detection result of the conveyor belt based on the detection result of the difference detection model.

[0029] Thirdly, this embodiment provides an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the conveyor belt blockage detection method described in the first aspect.

[0030] Fourthly, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the conveyor belt blockage detection method described in the first aspect.

[0031] Compared with existing technologies, the conveyor belt blockage detection method, apparatus, electronic device, and storage medium provided in this embodiment first pre-detects video image frames in the video image to be detected, identifying suspected blockage frames in the video image. This significantly reduces the frequency of operation of the feature comparison-based difference detection algorithm, thereby achieving real-time detection. Then, the feature comparison-based difference detection algorithm is used to detect the blockage location of the suspected blockage frames, achieving detection accuracy. Thus, the location of the conveyor belt blockage is located in real time and accurately.

[0032] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0033] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0034] Figure 1 This is a hardware structure block diagram of a terminal that executes a conveyor belt blockage detection method according to this embodiment;

[0035] Figure 2 This is a flowchart of a conveyor belt blockage detection method according to this embodiment;

[0036] Figure 3 This is a preferred flowchart of a conveyor belt blockage detection method according to this embodiment;

[0037] Figure 4 This is a schematic diagram of the frame difference preselection structure in this embodiment;

[0038] Figure 5 This is a schematic diagram of the ResNet50 structure in this embodiment;

[0039] Figure 6 This is a schematic diagram of the Stage2 structure in this embodiment;

[0040] Figure 7 This is a schematic diagram of the residual module BTNK2 with dilated convolution in this embodiment;

[0041] Figure 8 This is a schematic diagram of the difference detection algorithm in this embodiment;

[0042] Figure 9 This is a structural block diagram of a conveyor belt blockage detection device according to this embodiment. Detailed Implementation

[0043] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0044] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning as understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.

[0045] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of a terminal executing a conveyor belt blockage detection method according to this embodiment. Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0046] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to a conveyor belt blockage detection method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the aforementioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0047] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0048] This embodiment provides a method for detecting conveyor belt blockage. Figure 2 This is a flowchart of a conveyor belt blockage detection method according to this embodiment, such as... Figure 2 As shown, the process includes the following steps:

[0049] Step S210: Obtain the video image to be detected and the preset background image frame of the conveyor belt.

[0050] Specifically, the system acquires a video image of the conveyor belt to be inspected and a preset background image frame, both captured by a camera device. The video image and the preset background image frame both contain the conveyor belt, and the preset background image frame is an image frame containing the conveyor belt captured when there is no blockage. For example, the camera device can be mounted on one side of the conveyor belt to acquire video images containing the conveyor belt in real time and monitor its operation.

[0051] Step S220: Based on the video image to be detected and the preset background image frame, obtain the difference image frame in the video image to be detected.

[0052] Specifically, the video image frames of the video image to be detected on the conveyor belt are compared with preset background image frames to obtain the difference image frames in the video image to be detected. The video image to be detected on the conveyor belt includes multiple video image frames. Each video image frame in the video image is compared with the preset background image frame to obtain all the difference image frames in the video image to be detected.

[0053] More specifically, the frame difference between a video frame in the video image to be detected and a preset background image frame is calculated; when the frame difference is greater than a preset value, the video frame in the video image to be detected is determined to be a difference image frame. For example, the difference image frame in the video image can be obtained by subtracting the grayscale value of the video frame in the video image from the grayscale value of the preset background image frame, that is, the suspected blocked image frame in the video image. Alternatively, the difference image frame in the video image and the suspected blocked region within the difference image frame can also be obtained by subtracting the grayscale value of the video frame in the video image from the grayscale value of the preset background image frame.

[0054] Step S230: Input the difference image frame and the preset background image frame into the pre-trained difference detection model for difference detection.

[0055] Specifically, the difference image frames and preset background image frames in the acquired video image to be detected are input into the pre-trained difference detection model to perform specific difference region detection.

[0056] More specifically, the difference detection model here includes a first feature extraction model, a second feature extraction model, and a target region detection model. The difference image frame is input to the first feature detection model for feature detection, and a preset background image frame is input to the second feature detection model for feature detection. The features output by the first feature detection model and the features output by the second feature detection model are fused. The fused features are then input to the target region detection model for target region detection. For example, the target region detection model outputs a target detection bounding box for a blocked area or a blockage.

[0057] Step S240: Determine the blockage detection result of the conveyor belt based on the detection result of the difference detection model.

[0058] Specifically, the blockage detection result of the conveyor belt is determined based on the output of the target area detection model of the difference detection model. For example, when the target area detection model outputs a target detection bounding box, it is determined that the conveyor belt is blocked, and the blockage information is transmitted to the user; when the target area detection model does not output a target detection bounding box, it is determined that the conveyor belt is normal and there is no blockage.

[0059] Through the above steps, this embodiment first performs pre-detection on the video frames in the video image to be detected, identifying suspected blockage frames in the video image. This greatly reduces the frequency of the feature comparison-based difference detection algorithm, thereby achieving real-time detection. Then, the feature comparison-based difference detection algorithm is used to detect the blockage location of the suspected blockage frames, achieving detection accuracy. Thus, the location of the conveyor belt blockage is located in real time and accurately.

[0060] In some embodiments, the first feature detection model includes multiple feature extraction layers, and the second feature detection model includes multiple feature extraction layers; each feature extraction layer includes multiple residual blocks, and each residual block includes a dilated convolutional layer. The third feature extraction layer of the first feature detection model includes multiple residual blocks, and each residual block includes a dilated convolutional layer; the third feature extraction layer of the second feature detection model also includes multiple residual blocks, and each residual block includes a dilated convolutional layer.

[0061] Specifically, the first feature detection model includes five feature extraction layers, and the third feature extraction layer of the first feature detection model includes multiple residual blocks, one or more of which include dilated convolutional layers. The second feature detection model includes five feature extraction layers, and the third feature extraction layer of the first feature detection model includes multiple residual blocks, one or more of which include dilated convolutional layers.

[0062] In this embodiment, by utilizing the low-level features of the neural network in combination with dilated convolution, the detection of clogging, which is more inclined to low-level texture feature changes, can be enhanced while ensuring the network's receptive field, thereby further improving the detection accuracy.

[0063] In some embodiments, calculating the frame difference between a video image frame in the video image to be detected and a preset background image frame; determining the video image frame of the video image to be detected as a difference image frame when the frame difference is greater than a preset value includes: calculating the difference in pixel grayscale values ​​between the video image frame in the video image to be detected and the preset background image frame; determining the video image frame of the video image to be detected as a difference image frame when the difference in pixel grayscale values ​​is greater than a preset grayscale difference value.

[0064] The present embodiment will now be described and illustrated through preferred embodiments.

[0065] Figure 3 This is a preferred flowchart of a conveyor belt blockage detection method according to this embodiment, as follows: Figure 3 As shown, the method includes the following steps:

[0066] Step S310, blocking pre-detection based on frame difference.

[0067] Specifically, feature ratio algorithms based on deep learning have high requirements for device performance and are difficult to perform in real time. Therefore, this embodiment uses a frame difference algorithm, such as... Figure 4 As shown, the frame difference algorithm module 406 subtracts the grayscale values ​​of the video image frame 401 and the preset background image frame 402 to obtain the suspected blockage image frame 403 and the suspected blockage region 404 in the image frame. Then, the pre-selected video frame and background image are sent to the difference detection algorithm module 407 for feature comparison to obtain the accurate difference region 405 of the suspected blockage image frame 403, thus achieving accurate judgment of the blockage region. For example, if the frame difference algorithm module 406 detects three suspected blockage regions 404 in the suspected blockage image frame 403, the difference detection algorithm module 407 will detect one accurate difference region 405, thereby achieving real-time and accurate location of the conveyor belt blockage. The difference detection algorithm module 407 uses a feature comparison-based difference detection algorithm to detect the blockage target box. This method greatly reduces the frequency of the feature comparison algorithm, thus ensuring that the entire scheme can run in real time.

[0068] Step S320: Blocked target box detection based on feature comparison difference detection algorithm.

[0069] Specifically, the frame difference algorithm's pre-selected change regions, i.e., suspected congestion regions, suffer from a high number of false alarms. To address this, this embodiment uses deep learning for feature comparison of the pre-selected change regions, constructing a feature comparison-based difference detection model to effectively filter out erroneous regions. In this embodiment, ResNet50 is used as the feature extraction network, and its structure is as follows: Figure 5 As shown, ResNet50 is generally divided into five stages according to the number of samples, namely Stage 0 to Stage 4. The features output by the higher layers focus more on abstract target information, which is more effective for specific category recognition, but it is easy to ignore detailed information. The features of the lower layers focus more on texture information, which can better analyze detailed changes and is more suitable for problems such as conveyor belt blockage. Therefore, in the network design, the feature comparison network used in this embodiment uses the features of the lower Stage 2 layer rather than the features of the higher semantic Stage 4 layer. The structure diagram of the Stage 2 layer is shown below. Figure 6 As shown, the Stage2 layer includes multiple residual modules, such as... Figure 6 The model contains BTNK1 and BTNK2, where BTNK2 is a residual module with dilated convolution. A schematic diagram of the residual module BTNK2 with dilated convolution is shown below. Figure 7 As shown, the residual module BTNK2 with dilated convolutions includes multiple convolutional layers, such as... Figure 7The network employs 1×1 and 3×3 dilated convolutions. To address the issue of insufficient receptive field caused by using low-level features, this embodiment increases the network's receptive field by stacking multiple residual modules with dilated convolutions, ensuring that each feature point in the output feature map covers the entire image area. For the feature map output by the dilated convolutions, YOLO detection is used to obtain the final result for detecting change regions, achieving accurate localization of congestion areas. This design approach can better extract change regions caused by congestion, making it applicable to congestion change recognition in various scenarios.

[0070] A flowchart of the feature-matching-based difference detection algorithm is shown below. Figure 8 As shown, the background image frame and the suspected occlusion image frame obtained by frame difference pre-detection are respectively fed into the ResNet50 feature extraction improvement network to obtain the features of the two images. Then, the features of the two images are subtracted and fused to obtain the fused features. The fused features are fed into the YOLO detection model to regress the occlusion target box and output the occlusion target box.

[0071] Step S330: Congestion alarm based on the identification result.

[0072] Specifically, the output of the feature comparison-based difference detection algorithm determines whether an alarm should be generated. If the feature comparison-based difference detection algorithm identifies a change in congestion in the current area, the current location information is output and relevant personnel are notified to handle the situation.

[0073] This embodiment provides a conveyor belt blockage detection method comprising three parts. The first part is a blockage pre-detection based on frame difference. The second part is a difference detection algorithm based on feature comparison, which further discriminates the blockage pre-detection result output by frame difference, thereby outputting an accurate result indicating that a blockage has occurred. The third part is a blockage alarm, which mainly locates the blockage location based on the feature comparison result, thereby alerting relevant personnel to handle the situation.

[0074] In this embodiment, the video frames in the video image to be detected are first pre-detected to identify suspected blockage frames, which greatly reduces the frequency of the feature comparison-based difference detection algorithm, thus achieving real-time detection. Then, the feature comparison-based difference detection algorithm is used to detect the blockage location of the suspected blockage frames, thus achieving detection accuracy. By utilizing the low-level features of the neural network combined with dilated convolution, the detection of blockages, which are more inclined to low-level texture feature changes, can be strengthened while ensuring the network's receptive field, further improving the detection accuracy. Thus, the location of the conveyor belt blockage can be realized in real time and accurately.

[0075] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0076] This embodiment also provides a conveyor belt blockage detection device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. The terms "module," "unit," "subunit," etc., used below refer to combinations of software and / or hardware that perform a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0077] Figure 9 This is a structural block diagram of a conveyor belt blockage detection device according to this embodiment, as shown below. Figure 9 As shown, the device includes:

[0078] The first acquisition module 910 is used to acquire the video image to be detected on the conveyor belt and the preset background image frame;

[0079] The second acquisition module 920 is used to acquire the difference image frames in the video image to be detected based on the video image to be detected and the preset background image frames;

[0080] The input module 930 is used to input the difference image frame and the preset background image frame into the pre-trained difference detection model for difference detection;

[0081] The detection module 940 is used to determine the blockage detection result of the conveyor belt based on the detection results of the difference detection model.

[0082] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0083] This embodiment also provides an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0084] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0085] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0086] S1, acquire the video image to be detected and the preset background image frame of the conveyor belt;

[0087] S2, based on the video image to be detected and the preset background image frames, obtain the difference image frames in the video image to be detected;

[0088] S3, input the difference image frame and the preset background image frame into the pre-trained difference detection model for difference detection;

[0089] S4. Based on the detection results of the difference detection model, determine the blockage detection results of the conveyor belt.

[0090] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0091] Furthermore, in conjunction with the conveyor belt blockage detection method provided in the above embodiments, this embodiment can also provide a storage medium for implementation. The storage medium stores a computer program; when executed by a processor, the computer program implements the steps of any of the conveyor belt blockage detection methods in the above embodiments.

[0092] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0093] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0094] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0095] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A method for detecting conveyor belt blockage, characterized in that, The method includes: The video image to be detected and a preset background image frame of the conveyor belt are acquired; the video image to be detected includes multiple video image frames; Based on the video image to be detected and the preset background image frame, obtain the difference image frame in the video image to be detected; The difference image frame and the preset background image frame are input into a pre-trained difference detection model for difference detection; Based on the detection results of the difference detection model, the blockage detection result of the conveyor belt is determined; Based on the video image to be detected and a preset background image frame, obtain the difference image frame in the video image to be detected, including: Calculate the difference in pixel grayscale values ​​between the video image frame in the video image to be detected and the preset background image frame; when the difference in pixel grayscale values ​​is greater than the preset grayscale difference, determine the video image frame of the video image to be detected as the difference image frame; the difference image frame is the suspected blocked image frame in the video image; Inputting the difference image frame and the preset background image frame into a pre-trained difference detection model for difference detection includes: The difference image frame is input into the first feature detection model for feature detection, and the preset background image frame is input into the second feature detection model for feature detection; The features output by the first feature detection model and the features output by the second feature detection model are fused together. The fused features are input into the target region detection model to detect the target region. The first feature detection model includes five feature extraction layers, and the third feature extraction layer of the first feature detection model includes multiple residual blocks, one or more of the residual blocks in the third feature extraction layer of the first feature detection model including dilated convolutional layers; the second feature detection model includes five feature extraction layers, and the third feature extraction layer of the second feature detection model includes multiple residual blocks, one or more of the residual blocks in the third feature extraction layer of the second feature detection model including dilated convolutional layers.

2. The conveyor belt blockage detection method according to claim 1, characterized in that, The blockage detection result of the conveyor belt is determined based on the detection result of the difference detection model. Based on the target area detection box output by the target area detection model, the blockage area of ​​the conveyor belt is determined.

3. A conveyor belt blockage detection device, characterized in that, The device includes: The first acquisition module is used to acquire the video image to be detected and the preset background image frame of the conveyor belt; the video image to be detected includes multiple video image frames; The second acquisition module is used to acquire the difference image frames in the video image to be detected based on the video image to be detected and the preset background image frames; The input module is used to input the difference image frame and the preset background image frame into a pre-trained difference detection model for difference detection; The detection module is used to determine the blockage detection result of the conveyor belt based on the detection result of the difference detection model; Based on the video image to be detected and a preset background image frame, obtain the difference image frame in the video image to be detected, including: Calculate the difference in pixel grayscale values ​​between the video image frame in the video image to be detected and the preset background image frame; when the difference in pixel grayscale values ​​is greater than the preset grayscale difference, determine the video image frame of the video image to be detected as the difference image frame; the difference image frame is the suspected blocked image frame in the video image; Inputting the difference image frame and the preset background image frame into a pre-trained difference detection model for difference detection includes: The difference image frame is input into the first feature detection model for feature detection, and the preset background image frame is input into the second feature detection model for feature detection; The features output by the first feature detection model and the features output by the second feature detection model are fused together. The fused features are input into the target region detection model to detect the target region. The first feature detection model includes five feature extraction layers, and the third feature extraction layer of the first feature detection model includes multiple residual blocks, one or more of the residual blocks in the third feature extraction layer of the first feature detection model including dilated convolutional layers; the second feature detection model includes five feature extraction layers, and the third feature extraction layer of the second feature detection model includes multiple residual blocks, one or more of the residual blocks in the third feature extraction layer of the second feature detection model including dilated convolutional layers.

4. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the conveyor belt blockage detection method according to any one of claims 1 to 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the conveyor belt blockage detection method according to any one of claims 1 to 2.

Images