Bagged material bag breaking real-time detection method and system based on lightweight DF-YOLOV5N

Abstract

The invention discloses a bagged material bag breaking real-time detection method and system based on lightweight DF-YOLOV5N. The method comprises the steps that a bagged material bag image is obtained in real time, and part of edges are cut; inputting the cut image into a DF-YOLOV5N network, and outputting a classification result of the bagged material package; the DF-YOLOV5N network is obtained by improving a YOLOV5N target detection network, the improvement comprises the step of replacing a backbone network of the YOLOV5N target detection network with a Deform-FatsteriNet network, the Deform-FatsteriNet network comprises a structure in front of a global average pooling layer in the FasterNet network, and a pooling layer SPPF is connected behind the last partial convolution module; wherein a second convolution module and a third convolution module with the convolution kernel of 2 * 2 and the step length of 2 in the Faster Net network are replaced by deformable convolution modules. According to the method, the YOLOV5N backbone network is subjected to lightweight processing, so that the improved lightweight DF-YOLOV5N network model has less parameter quantity and floating point calculation quantity, and meanwhile, the detection speed is higher and the detection performance is higher.

Description

Technical Field

[0001] The present invention relates to the field of deep learning and computer vision technology, and in particular to a real-time detection method, system, terminal device and computer-readable storage medium for bagged material breakage based on lightweight DF-YOLOV5N. Background Art

[0002] In material production and packaging enterprises, material package damage detection is a necessary link. Products with damaged packaging are substandard products and need to be strictly controlled by manufacturers. Its importance is also reflected in: damaged packaging directly leads to material shortages, which harms customer interests; damaged material packages leak material, which changes the thickness and other dimensions of the packaging, makes loading and stacking uneven and unstable, and bumps and sharp turns during automobile transportation will cause safety hazards.

[0003] In the manual loading system, broken material packages are found by workers who are loading and stacking, and then directly thrown away as processed products for recycling. It is not difficult to manually detect and remove broken material packages, but broken materials will generate a lot of dust, which poses a great threat to workers' health. With the entry of material conveying, loading and stacking equipment into the era of automation, the labor force is liberated from the harsh production environment with heavy dust. After workers no longer need to stack materials, it becomes almost unrealistic to manually detect broken packages. Generally, materials are shipped from the factory 24 hours a day without interruption, and are loaded as soon as the car arrives. Since the broken package rate needs to be controlled within a few thousandths, a production line generally has no more than ten broken packages per day, which means that the workers who detect broken packages have nothing to do most of the time, but they have to stare at the material conveyor belt and cannot leave, which is very easy to cause mistakes due to fatigue, and workers need to be arranged to work in shifts. Therefore, automatic broken package identification and removal of unqualified material packages have become technical problems that need to be solved in the automated loading system.

[0004] Artificial intelligence detection technology has been studied and applied in the packet breaking detection system. YOLOV5N is a simple and efficient single-stage target detection model that has been popular in recent years. It consists of an input end, a backbone feature extraction network, a neck feature fusion network, and an output end. Through a single network, the target can be directly classified and located. However, the YOLOV5N model has many parameters, so it is not lightweight enough, and the detection speed of the model still has room for improvement. Summary of the invention

[0005] In order to solve at least one technical problem in the above-mentioned prior art, the present invention provides a real-time detection method, system, terminal device and computer-readable storage medium for bagged material breakage based on lightweight DF-YOLOV5N.

[0006] The first object of the present invention is to provide a real-time detection method for bag breakage of bagged materials based on lightweight DF-YOLOV5N.

[0007] The second object of the present invention is to provide a real-time detection system for bagged material breakage based on the lightweight DF-YOLOV5N.

[0008] The third object of the present invention is to provide a terminal device.

[0009] A fourth object of the present invention is to provide a computer-readable storage medium.

[0010] The first object of the present invention can be achieved by adopting the following technical solutions: A real-time detection method for bagged material breakage based on lightweight DF-YOLOV5N, the method comprising: Get the bagged material package image in real time and crop some edges; The cropped image is input into the DF-YOLOV5N network, and the classification result of the bagged material package is output; the DF-YOLOV5N network is obtained by improving the YOLOV5N target detection network, and the improvement includes using the Deformer-FatsterNet network to replace the backbone network of the YOLOV5N target detection network, and the Deformer-FatsterNet network includes the structure before the global average pooling layer in the FasterNet network, and the pooling layer SPPF is connected after the last partial convolution module; wherein the second and third convolution modules with a convolution kernel of 2×2 and a stride of 2 in the FasterNet network are replaced by deformable convolution modules.

[0011] Furthermore, the improvement also includes reconstructing the neck network in the YOLOV5N target detection network, wherein the reconstructed neck network includes a convolution module, an upsampling module, and a deformable cross-level connection module, wherein the deformable cross-level connection module is a module obtained by replacing the standard convolution with a convolution kernel of 3×3 in the cross-level connection module of the original YOLOV5N neck with a deformable convolution; The data processing flow of the reconstructed neck network is as follows: The feature map output by the pooling layer SPPF in the Deformer-FatsterNet network is processed using a convolution module with a convolution kernel of 1×1 to obtain the feature map T1; The feature map T1 is processed by the upsampling module to obtain the feature map T2; The feature map T2 is concatenated with the feature map output by the penultimate partial convolution module in the Deformer-FatsterNet network and sent to the deformable cross-level connection module to obtain the feature map T3. The feature map T3 is processed using a convolution module with a convolution kernel of 3×3 to obtain a feature map T4; The feature map T4 is concatenated with the feature map T1 and sent to the deformable cross-level connection module to obtain the feature map T5; The feature maps T3 and T5 are output to the head network.

[0012] Furthermore, before the cropped image is input into the DF-YOLOV5N network, the DF-YOLOV5N network is trained to detect the cropped image using the trained DF-YOLOV5N network.

[0013] Furthermore, the training of the DF-YOLOV5N network includes: Get a dataset of bagged material images; Label the samples in the dataset; Perform data augmentation on samples in the labeled dataset to make the number of sample labels in each category close; The DF-YOLOV5N network is trained using data-enhanced samples.

[0014] Furthermore, the data enhancement includes at least one method of rotation transformation, noise addition, brightness adjustment, mosaic, copy and paste, and contrast-limited adaptive histogram equalization.

[0015] Furthermore, there are four marked categories: normal package, there is only one package in the marked box, and the shape of the package is relatively full without holes; empty package, there is only one package in the marked box, and the shape of the package is flat; overlapped package, there are two packages in the marked box, one of which is pressed underneath or squeezed to the side; broken package, there is only one package in the marked box, and the package has holes and is smaller than a normal package.

[0016] Furthermore, the data set of bagged material package images is obtained, including: Take a video of the bagged material packages; Frames are extracted from the video and images of bagged materials are taken as samples in the dataset.

[0017] The second object of the present invention can be achieved by adopting the following technical solutions: A real-time detection system for bagged material breakage based on lightweight DF-YOLOV5N, the system comprising: An acquisition module is used to acquire the bagged material package image in real time and crop some edges; The detection module is used to input the cropped image into the DF-YOLOV5N network and output the classification result of the bagged material package; the DF-YOLOV5N network is obtained by improving the YOLOV5N target detection network, and the improvement includes using the Deformer-FatsterNet network to replace the backbone network of the YOLOV5N target detection network, and the Deformer-FatsterNet network includes the structure before the global average pooling layer in the FasterNet network, and the pooling layer SPPF is connected after the last partial convolution module; wherein the second and third convolution modules with a convolution kernel of 2×2 and a stride of 2 in the FasterNet network are replaced by deformable convolution modules.

[0018] The third object of the present invention can be achieved by adopting the following technical solutions: A terminal device includes a processor and a memory for storing a program executable by the processor. When the processor executes the program stored in the memory, the above-mentioned real-time detection method for bag breakage of bagged materials based on lightweight DF-YOLOV5N is implemented.

[0019] The fourth object of the present invention can be achieved by adopting the following technical solutions: A computer-readable storage medium stores a program, which, when executed by a processor, implements the above-mentioned real-time detection method for bag breakage of bagged materials based on lightweight DF-YOLOV5N.

[0020] The present invention has the following beneficial effects compared with the prior art: 1. The present invention performs lightweight processing on the YOLOV5N backbone network, and the improved model has fewer parameters and floating-point operations, and has faster detection speed and higher detection performance; 2. The present invention uses deformable convolution in the neck network of the DF-YOLOV5N network to construct a more efficient deformable cross-level connection module, which has stronger feature extraction capabilities and better model detection effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0022] Figure 1 This is a flow chart of a method for real-time detection of bag breakage of bagged materials based on lightweight DF-YOLOV5N according to Example 1 of the present invention; Figure 2 This is a schematic diagram of a method for real-time detection of bag breakage of bagged materials based on lightweight DF-YOLOV5N according to Example 1 of the present invention; Figure 3 This is the DF-YOLOV5N network structure diagram of this embodiment 1; Figure 4 This is the FasterNet network structure diagram of this embodiment 1; Figure 5 Schematic diagram of partial convolution operation of this embodiment 1; Figure 6 Schematic diagram of deformable convolution operation in Embodiment 1; Figure 7 This is a structural diagram of a deformable cross-layer connection module of the first embodiment; Figure 8 : are sample graphs of each category of the data set used in this embodiment 1; Fig. 9 is a new sample image obtained by each enhancement method used in this embodiment 1; Fig.10 This is a structural block diagram of a real-time detection system for bagged material breakage based on lightweight DF-YOLOV5N according to Example 2 of the present invention; Fig.11 This is a structural block diagram of the terminal device of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should be understood that the specific embodiments described are only used to explain the present application and are not used to limit the present application. It is understandable that some parts in the drawings may be omitted, enlarged or reduced, and cannot represent the size of the actual product.

[0024] Embodiment 1: like Figure 1 , 2 As shown, this embodiment provides a real-time detection method for bag breakage of bagged materials based on lightweight DF-YOLOV5N, comprising the following steps: S101, acquiring an image of a bagged material package in real time and cropping part of the edge.

[0025] After acquiring the image of the bagged material package in real time through the industrial camera, some edges and areas irrelevant to the detection are cropped according to the actual situation, so that the area of ​​the bagged material package in the image is increased, thereby improving the accuracy of the detection.

[0026] In this embodiment, 10% and 15% of the upper and lower and left and right edge images are cropped respectively.

[0027] S102: Input the cropped image into the DF-YOLOV5N network and output the classification result of the bagged material package.

[0028] The cropped image is used as the input of the DF-YOLOV5N network, and the model performs forward reasoning and outputs the detection results.

[0029] The DF-YOLOV5N network is improved based on the YOLOV5N target detection network.

[0030] The structure of DF-YOLOV5N network can be referred to Figure 3 Specific improvements include: (1) Replace the backbone network of YOLOV5N with Deformer-FatsterNet.

[0031] (1-1) Introduced the lighter and more efficient FasterNet.

[0032] The specific structure of FasterNet is as follows Figure 4 As shown in the figure, it is mainly composed of a convolution module with a convolution kernel size of 4×4 and a stride of 2, three convolution kernels with a size of 2×2 and a stride of 2, and four partial convolution modules. Finally, it is processed by the global average pooling layer, the convolution layer with a convolution kernel size of 1×1, and the fully connected layer for output processing. The principle of partial convolution is as follows Figure 5 As shown, it only applies to some channels ( c p , which defaults to 1 / 4 of the input channel) for convolution, and the remaining channels are directly spliced ​​with the channels after partial convolution, so the computational complexity is lower and the feature extraction efficiency is higher. The present invention uses all modules before the global average pooling layer in FasterNet to replace all modules before the spatial pyramid pooling module in the YOLOV5N backbone network.

[0033] (1-2) A more efficient deformable convolution is introduced.

[0034] The principle of deformable convolution is as follows Figure 6As shown. On the basis of standard convolution, deformable convolution additionally learns the sampling offset, so it has a more diverse sampling range and stronger feature extraction ability than standard convolution. The present invention uses deformable convolution to replace the second and third convolution modules with a kernel size of 2×2 and a step size of 2 in FasterNet to balance the model complexity and detection accuracy. The improved backbone network is called Deformer-FatsterNet.

[0035] (2) Reconstruction of the neck structure.

[0036] The data processing flow of the reconstructed neck network is as follows: (2-1) The feature map of size 20×20×80 output by the SPPF layer in Deformer-FatsterNet is fed into a 1×1 convolution module to obtain a feature map T1 of size 20×20×128.

[0037] (2-2) Send T1 to the upsampling module to obtain a feature map T2 of size 40×40×128.

[0038] (2-3) T2 is concatenated with the 40×40×40 feature map output by the penultimate partial convolution module of Deformer-FatsterNet and then fed into a deformable cross-level connection module to obtain a feature map T3 of size 40×40×128. The deformable cross-level connection module used in this embodiment is a module obtained by replacing the standard convolution with a convolution kernel size of 3×3 in the cross-level connection module of the original YOLOV5N neck with a deformable convolution. Figure 7 .

[0039] (2-4) Send T3 into a 3×3 convolution module to obtain a feature map T4 of size 20×20×64.

[0040] (2-5) T4 and T1 are concatenated and sent to a deformable cross-level connection module to obtain a feature map T5 of size 20×20×128.

[0041] (2-6) Output T3 and T5 to the detection head module of the head network.

[0042] The detection head module retains the original YOLOV5N network structure. Based on the obtained T3 and T5 feature maps, it obtains the target category through the classifier, and calculates the category and confidence loss at the same time. Then, it uses the regression loss to calculate and generate the prediction box according to the coordinates of the bounding box to achieve the output of target positioning and classification results.

[0043] Among them, the classification results are divided into four categories: normal package, empty package, overlapped package and broken package.

[0044] It is understandable that before the cropped image is input into the DF-YOLOV5N network, the DF-YOLOV5N network is also trained. The cropped image is detected using the trained DF-YOLOV5N network.

[0045] Furthermore, the DF-YOLOV5N network is trained, including: (1) Obtain a dataset of bagged material images.

[0046] Frames are extracted from the video of bagged material packages shot by the camera on the bagged material conveyor belt, and the original bagged material package images are extracted as samples in the dataset.

[0047] (2) Label the samples in the dataset.

[0048] In this embodiment, the labels are divided into four categories according to the status of the bagged material packages, namely: normal package, there is only one package in the marked box, and the package shape is relatively full without holes; empty package, there is only one package in the marked box, and the package shape is flat; overlapped package, there are two packages in the marked box, one of which is pressed underneath or squeezed next to it; broken package, there is only one package in the marked box, and the package has holes and is smaller than a normal package. Some image samples can be referenced Figure 8 .

[0049] (3) Perform data augmentation on samples in the labeled dataset.

[0050] The purpose of data augmentation is to alleviate the problem of sample imbalance.

[0051] In addition to conventional data enhancement methods such as rotation transformation, noise addition, brightness adjustment, mosaic, copy and paste, this embodiment also introduces a contrast-limited adaptive histogram equalization method. The image is first divided into many small blocks, and then the histogram of each small block is equalized.

[0052] Randomly use one or more of the above data enhancement methods to enhance the data set, focusing on enhancing the abnormal package samples, so that the ratio of the number of sample labels of the above four categories is close to 1:1:1:1, and the number of images is expanded from 8777 to 33168. Some image samples after data enhancement can be referred to Fig. 9 .

[0053] (4) Use the data-enhanced samples to train the DF-YOLOV5N network.

[0054] In this embodiment, the training rounds are set to 40, the batch size is 8, the image input size is 640×640 pixels, the optimizer used is stochastic gradient descent, and the learning rate size is set to 0.01.

[0055] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above embodiments may be completed by instructing related hardware through a program, and the corresponding program may be stored in a computer-readable storage medium.

[0056] It should be noted that although the method operations of the above embodiments are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0057] Embodiment 2: like Fig.10 As shown, this embodiment provides a real-time detection system for bagged material breakage based on lightweight DF-YOLOV5N, the system comprising an acquisition module 1001 and a detection module 1002, wherein: An acquisition module 1001 is used to acquire the bagged material package image in real time and crop part of the edge; The detection module 1002 is used to input the cropped image into the DF-YOLOV5N network and output the classification result of the bagged material package; the DF-YOLOV5N network is obtained by improving the YOLOV5N target detection network, and the improvement includes using the Deformer-FatsterNet network to replace the backbone network of the YOLOV5N target detection network, and the Deformer-FatsterNet network includes the structure before the global average pooling layer in the FasterNet network, and the pooling layer SPPF is connected after the last partial convolution module; wherein the second and third convolution modules with a convolution kernel of 2×2 and a stride of 2 in the FasterNet network are replaced by deformable convolution modules.

[0058] The specific implementation of each module in this embodiment can refer to the above-mentioned embodiment 1, which will not be described one by one here; it should be noted that the system provided in this embodiment is only illustrated by the division of the above-mentioned functional modules. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure can be divided into different functional modules to complete all or part of the functions described above.

[0059] Embodiment 3: This embodiment provides a terminal device, which can be a computer. Fig.11As shown, it comprises a processor 1102, a memory, an input device 1103, a display 1104 and a network interface 1105 connected via a system bus 1101. The processor is used to provide computing and control capabilities. The memory comprises a non-volatile storage medium 1106 and an internal memory 1107. The non-volatile storage medium 1106 stores an operating system, a computer program and a database. The internal memory 1107 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the processor 1102 executes the computer program stored in the memory, the above-mentioned embodiment 1 is implemented based on the lightweight DF-YOLOV5N. The method for detecting bag breakage of bagged materials in real time is as follows: Get the bagged material package image in real time and crop some edges; The cropped image is input into the DF-YOLOV5N network, and the classification result of the bagged material package is output; the DF-YOLOV5N network is obtained by improving the YOLOV5N target detection network, and the improvement includes using the Deformer-FatsterNet network to replace the backbone network of the YOLOV5N target detection network, and the Deformer-FatsterNet network includes the structure before the global average pooling layer in the FasterNet network, and the pooling layer SPPF is connected after the last partial convolution module; wherein the second and third convolution modules with a convolution kernel of 2×2 and a stride of 2 in the FasterNet network are replaced by deformable convolution modules.

[0060] Embodiment 4: This embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for detecting bag breakage of bagged materials based on lightweight DF-YOLOV5N in the above embodiment 1 is implemented as follows: Get the bagged material package image in real time and crop some edges; The cropped image is input into the DF-YOLOV5N network, and the classification result of the bagged material package is output; the DF-YOLOV5N network is obtained by improving the YOLOV5N target detection network, and the improvement includes using the Deformer-FatsterNet network to replace the backbone network of the YOLOV5N target detection network, and the Deformer-FatsterNet network includes the structure before the global average pooling layer in the FasterNet network, and the pooling layer SPPF is connected after the last partial convolution module; wherein the second and third convolution modules with a convolution kernel of 2×2 and a stride of 2 in the FasterNet network are replaced by deformable convolution modules.

[0061] It should be noted that the computer-readable storage medium of the present embodiment may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0062] The above is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solution and inventive concept of the present invention within the scope disclosed by the present invention, which shall fall within the protection scope of the present invention.

Claims

1. A real-time detection method for bagged material breakage based on lightweight DF-YOLOV5N, characterized in that: The method comprises: Get the bagged material package image in real time and crop some edges; The cropped image is input into the DF-YOLOV5N network, and the classification result of the bagged material package is output; the DF-YOLOV5N network is obtained by improving the YOLOV5N target detection network, and the improvement includes using the Deformer-FatsterNet network to replace the backbone network of the YOLOV5N target detection network, and the Deformer-FatsterNet network includes the structure before the global average pooling layer in the FasterNet network, and the pooling layer SPPF is connected after the last partial convolution module; wherein the second and third convolution modules with a convolution kernel of 2×2 and a stride of 2 in the FasterNet network are replaced by deformable convolution modules.

2. The method for real-time detection of bagged material breakage according to claim 1, characterized in that: The improvement also includes reconstructing the neck network in the YOLOV5N target detection network, wherein the reconstructed neck network includes a convolution module, an upsampling module, and a deformable cross-level connection module, wherein the deformable cross-level connection module is a module obtained by replacing the standard convolution with a convolution kernel of 3×3 in the cross-level connection module of the original YOLOV5N neck with a deformable convolution; The data processing flow of the reconstructed neck network is as follows: The feature map output by the pooling layer SPPF in the Deformer-FatsterNet network is processed using a convolution module with a convolution kernel of 1×1 to obtain the feature map T1; The feature map T1 is processed by the upsampling module to obtain the feature map T2; The feature map T2 is concatenated with the feature map output by the penultimate partial convolution module in the Deformer-FatsterNet network and sent to the deformable cross-level connection module to obtain the feature map T3. The feature map T3 is processed using a convolution module with a convolution kernel of 3×3 to obtain a feature map T4; The feature map T4 is concatenated with the feature map T1 and sent to the deformable cross-level connection module to obtain the feature map T5; Output feature map T3 and feature map T5 to the head network.

3. The method for real-time detection of bag breakage of bagged materials according to any one of claims 1 and 2, characterized in that: Before the cropped image is input into the DF-YOLOV5N network, the DF-YOLOV5N network is also trained to detect the cropped image using the trained DF-YOLOV5N network.

4. The method for real-time detection of bag breakage of bagged materials according to claim 3, characterized in that: The training of the DF-YOLOV5N network includes: Get a dataset of bagged material images; Label the samples in the dataset; Perform data augmentation on samples in the labeled dataset to make the number of sample labels in each category close; The DF-YOLOV5N network is trained using data-enhanced samples.

5. The method for real-time detection of bag breakage of bagged materials according to claim 4, characterized in that: The data enhancement includes at least one method of rotation transformation, noise addition, brightness adjustment, mosaic, copy and paste, and contrast-limited adaptive histogram equalization.

6. The method for real-time detection of bag breakage of bagged materials according to claim 4, characterized in that: There are four types of marked categories: normal package, there is only one package in the marked box, and the package is full and has no holes; empty package, there is only one package in the marked box, and the package is flat; Stacked packages: there are two packages in the marked box, one of which is pressed underneath or squeezed next to it; broken packages: there is only one package in the marked box, and there is a hole in the package, and the shape is smaller than a normal package.

7. The method for real-time detection of bag breakage of bagged materials according to claim 4, characterized in that: The data set of bagged material package images is obtained, including: Take a video of the bagged material packages; Frames are extracted from the video and images of bagged materials are taken as samples in the dataset.

8. A real-time detection system for bagged material breakage based on lightweight DF-YOLOV5N, characterized in that: The system comprises: An acquisition module is used to acquire the bagged material package image in real time and crop some edges; The detection module is used to input the cropped image into the DF-YOLOV5N network and output the classification result of the bagged material package; the DF-YOLOV5N network is obtained by improving the YOLOV5N target detection network, and the improvement includes using the Deformer-FatsterNet network to replace the backbone network of the YOLOV5N target detection network, and the Deformer-FatsterNet network includes the structure before the global average pooling layer in the FasterNet network, and the pooling layer SPPF is connected after the last partial convolution module; wherein the second and third convolution modules with a convolution kernel of 2×2 and a stride of 2 in the FasterNet network are replaced by deformable convolution modules.

9. A terminal device, comprising a processor and a memory for storing a program executable by the processor, characterized in that: When the processor executes the program stored in the memory, the real-time detection method for bag breakage of bagged materials described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the real-time detection method for bag breakage of bagged materials according to any one of claims 1 to 7 is implemented.

Images