Method, device and computer equipment for detecting foreign matter emission during vehicle weighing

Abstract

The present application relates to a method, device, computer equipment, storage medium and computer program product for detecting the behavior of vehicles discharging foreign objects during weighing. The method comprises: obtaining surveillance video of the material shipping area, and performing vehicle detection and tracking; when a transport vehicle enters the foreign object detection area, determining the circumscribed rectangular area of the current frame detection frame area and the historical frame retention area of the transport vehicle as the current frame passing area; performing a first foreign object detection on the current frame image of the target area in the current frame passing area, and if the first foreign object detection result indicates that the target foreign object is detected, performing a second foreign object detection on the current frame control image of the target area; judging whether the transport vehicle has the behavior of discharging foreign objects during weighing based on the first foreign object detection result and the second foreign object detection result. The use of this method can improve the efficiency and accuracy of detecting the behavior of vehicles discharging foreign objects during weighing, thereby improving the supervision effect of cheating in weighing during the material shipping process.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, computer equipment, storage medium, and computer program product for detecting the behavior of vehicles discharging foreign objects during weighing. Background Art

[0002] Coal mining, metallurgy, building materials, grain and other industries usually use a floor scale system for weighing and measuring when shipping materials. The transport vehicle is weighed before loading to obtain the tare weight, and then weighed again after loading to obtain the gross weight. The difference between the two is the net weight, which will be used for order accounting.

[0003] Since there is usually a certain distance between the weighbridge and the loading location, in actual applications, cheating methods have occurred, such as adding water to the water tank or hiding heavy objects such as stones before the vehicle is tare-weighed, and draining water or discharging other hidden heavy objects before the gross weight, thereby affecting the net weight value and causing losses to the shipper. In related technologies, in order to supervise such cheating behaviors, manual monitoring can be used to check whether the vehicle has discharged foreign objects between two weighings. However, this consumes a lot of manpower and has low inspection efficiency. Especially when the material shipping area is large and there are many transport vehicles, it is easy to miss or misdetect due to insufficient manpower or manual fatigue. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for detecting the behavior of vehicles emitting foreign objects during weighing in order to address the above-mentioned technical problems. This can improve the efficiency and accuracy of detecting the behavior of vehicles emitting foreign objects during weighing, thereby improving the supervision effect of weighing cheating during the material shipment process and reducing the losses of the shipper.

[0005] In a first aspect, the present application provides a method for detecting the emission of foreign matter from a vehicle during weighing. The method comprises:

[0006] Obtain surveillance video of the material shipping area, and perform vehicle detection and tracking on the surveillance video to obtain the position of the transport vehicle in each frame of the surveillance video image;

[0007] When the transport vehicle enters the foreign object detection area, the circumscribed rectangular area of the current frame detection frame area and the historical frame retention area of the transport vehicle in the current frame monitoring video image is determined as the current frame travel area of the transport vehicle; the historical frame retention area is the intersection area of the historical frame detection frame area and the foreign object detection area or the area in the historical frame travel area where no foreign object detection is performed;

[0008] Performing a first foreign object detection on a current frame image of a target area in the current frame passing area to obtain a first foreign object detection result; if the first foreign object detection result indicates that the target foreign object is detected, performing a second foreign object detection on a current frame control image of the target area to obtain a second foreign object detection result;

[0009] It is determined whether the transport vehicle has discharged foreign objects during weighing according to the first foreign object detection result and the second foreign object detection result.

[0010] In one embodiment, performing a first foreign object detection on the current frame image of the target area in the current frame passing area to obtain a first foreign object detection result includes:

[0011] Determine an area in the current frame passing area other than the current frame detection frame area as a target area;

[0012] A first foreign object detection is performed on the current frame image of the target area to obtain a first foreign object detection result.

[0013] In one embodiment, performing a first foreign object detection on the current frame image of the target area in the current frame passing area to obtain a first foreign object detection result includes:

[0014] Dividing the area of the current frame passing area, excluding the current frame detection frame area, into a plurality of peripheral sub-areas according to the boundary lines of the detection frame, and determining the peripheral sub-areas in each of the peripheral sub-areas that meet the preset resolution requirements as the target area;

[0015] A first foreign object detection is performed on the current frame image of the target area to obtain a first foreign object detection result.

[0016] In one embodiment, determining the peripheral sub-region that meets the preset resolution requirement among the peripheral sub-regions as the target region includes:

[0017] Determine the region with the largest area among the peripheral subregions as a candidate region;

[0018] If the area of the candidate region is greater than a preset threshold and the aspect ratio meets a preset requirement, the candidate region is determined as the target region.

[0019] In one embodiment, performing a second foreign body detection on the current frame control image of the target area to obtain a second foreign body detection result includes:

[0020] Update the image of the area except the historical frame retained area in the historical frame comparison image of the foreign object detection area according to the historical frame monitoring video image to obtain the current frame comparison image of the foreign object detection area;

[0021] An image of the target area is intercepted from the current frame comparison image of the foreign object detection area to perform a second foreign object detection to obtain a second foreign object detection result.

[0022] In one embodiment, determining whether the transport vehicle has discharged foreign objects during weighing based on the first foreign object detection result and the second foreign object detection result includes:

[0023] If the second foreign object detection result indicates that no target foreign object is detected, or that a target foreign object is detected and the size of the target foreign object is smaller than the size of the target foreign object in the first foreign object detection result, it is determined that the transport vehicle has discharged foreign objects by overweighing.

[0024] In one embodiment, the method further comprises:

[0025] When it is determined that the transport vehicle has discharged foreign objects during weighing, an image of the transport vehicle is captured from the current frame monitoring video image, and an alarm message is issued.

[0026] In a second aspect, the present application also provides a device for detecting the emission of foreign matter from a vehicle during weighing. The device comprises:

[0027] The tracking module is used to obtain surveillance video of the material shipping area, and perform vehicle detection and tracking on the surveillance video to obtain the position of the transport vehicle in each frame of the surveillance video image;

[0028] a determination module, configured to, when the transport vehicle enters the foreign object detection area, determine the circumscribed rectangular area of the current frame detection frame area and the historical frame retention area of the transport vehicle in the current frame monitoring video image as the current frame passing area of the transport vehicle;

[0029] a detection module configured to perform a first foreign object detection on a current frame image of a target area in the current frame passing area to obtain a first foreign object detection result; and if the first foreign object detection result indicates that a target foreign object has been detected, perform a second foreign object detection on a current frame control image of the target area to obtain a second foreign object detection result;

[0030] A judgment module is used to judge whether the transport vehicle has discharged foreign objects during weighing according to the first foreign object detection result and the second foreign object detection result.

[0031] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described in the first aspect when executing the computer program.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0033] In a fifth aspect, the present application further provides a computer program product, comprising a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.

[0034] The above-mentioned method, apparatus, computer equipment, storage medium, and computer program product for detecting the discharge of foreign objects by vehicles during weighing are described. The method detects and tracks vehicles using surveillance video from a material shipping area to identify the location of each transport vehicle. When a transport vehicle enters a foreign object detection area, the current frame detection frame area and the circumscribed rectangular area of the historical frame retention area are determined as the current frame travel area of the transport vehicle. The current frame image of the travel area is then subjected to foreign object detection. If a foreign object is detected, the foreign object detection result is compared with the foreign object detection result of the current frame control image of the travel area. The historical frame retention area is the intersection of the historical frame detection frame area and the foreign object detection area, or an area in the historical frame travel area where foreign object detection was not performed. The circumscribed rectangular area of the current frame detection frame area and the historical frame retention area can cover the area the transport vehicle passed through. The control image of the travel area is obtained based on historical frame surveillance video images and can reflect the ground conditions before the transport vehicle passed through the area. If foreign objects are present on the ground after the transport vehicle passes through the area, but no foreign objects or only a smaller amount of foreign objects are present on the ground before the vehicle passes through, it can be determined that the transport vehicle has discharged foreign objects during weighing. Compared with manual supervision, this solution can improve the efficiency and accuracy of detecting vehicle weighing and discharging foreign objects, thereby improving the supervision effect of weighing cheating during material shipment and reducing losses to shippers. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 1 is a flow chart of a method for detecting the emission of foreign matter from a vehicle during weighing in one embodiment;

[0036] Figure 2a This is a schematic diagram of the material shipping area in an example;

[0037] Figure 2b A schematic diagram of a travel area in an example;

[0038] Figure 2c A schematic diagram of the target area in an example;

[0039] Figure 2d A schematic diagram of a peripheral sub-region in an example;

[0040] Figure 31. A structural block diagram of a device for detecting the emission of foreign matter from a vehicle during weighing in accordance with an embodiment;

[0041] Figure 4 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0043] In one embodiment, Figure 1 As shown, a method for detecting the emission of foreign matter from a vehicle during weighing is provided. The method can be applied to computer equipment such as servers, and includes the following steps:

[0044] Step 102: Obtain surveillance video of the material shipping area, perform vehicle detection and tracking on the surveillance video, and obtain the position of the transport vehicle in each frame of the surveillance video.

[0045] In implementation, surveillance cameras (either monocular cameras like gun cameras or multi-camera arrays) can be set up in material shipping areas (such as coal yards and mines) to capture surveillance video. The server can use object detection and tracking technology to detect and track vehicles in each frame of the surveillance video or every few frames, obtaining the position of each transport vehicle within each frame, typically as the coordinates of a rectangular detection box. Object detection can utilize the YOLOv8 neural network model. A frame of surveillance video is input into the detection model for processing, and the model outputs the coordinates of the detection box for each transport vehicle (such as a truck) detected in the image. The vehicle detection model can be pre-trained with a dataset containing trucks so that it can identify the location of trucks in the image. Tracking technology can utilize the ByteTrack multi-object tracking model. ByteTrack leverages the similarity between detection boxes and tracking trajectories to remove background from low-scoring detection results while retaining high-scoring detection results. This allows the identification of true objects (difficult samples such as occlusion and blur), thereby reducing missed detections and improving trajectory consistency.

[0046] Step 104 : When the transport vehicle enters the foreign object detection area, the circumscribed rectangular area of the current frame detection frame area and the historical frame retention area of the transport vehicle in the current frame monitoring video image is determined as the current frame passing area of the transport vehicle.

[0047] Among them, after the transport vehicle is weighed at the pico scale node in the material shipping area, it drives to the material loading area and then drives to the gross scale node for weighing. All areas that the transport vehicle may pass through during the process can be designated as foreign object detection areas. The vehicle may discharge foreign objects in this area to cheat on weighing. Figure 2a As shown, the foreign body detection area consists of two parts. It can be understood that Figure 2a The layout of the nodes is for illustration only. Usually, vehicles do not travel in a straight line in the foreign object detection area. In order to disperse traffic and increase the utilization rate of regional space, the layout of the nodes can be used to allow vehicles to make turns during driving to extend the driving path.

[0048] The server can determine whether the transport vehicle has entered the foreign object detection area based on the position information of the transport vehicle in the video image and the position information of the foreign object detection area. If the vehicle detection frame intersects with the foreign object detection area, it can be determined that the transport vehicle has entered the foreign object detection area. For the current frame monitoring video image, its corresponding historical frame monitoring video image refers to the video image of the previous frame for vehicle detection and tracking (depending on the number of interval frames of vehicle detection). For ease of description, the historical frame monitoring video image in this embodiment refers to the previous frame monitoring video image, and accordingly, the historical frame retained area is the intersection area of the detection frame area of the transport vehicle in the previous frame monitoring video image and the foreign object detection area (if the vehicle completely enters the foreign object detection area, the intersection area is the detection frame area; if it partially enters the foreign object detection area, the intersection area is the partial detection frame area), or the area in the travel area of the previous frame monitoring video image where no foreign object detection is performed, which at least includes the intersection area of the detection frame area of the transport vehicle in the previous frame and the foreign object detection area.

[0049] Since the passing area includes the detection frame area of the vehicle in the frame image, and the detection frame area is blocked by the vehicle, it is impossible to detect whether the vehicle has discharged foreign objects in the detection frame area based on the current frame video image, so the area is retained for detection in subsequent frame video images. In addition, in order to improve the detection accuracy, the server can only perform foreign object detection on the local passing area that meets certain conditions in the current frame (see below for details, no further description is given here), so that the passing area that has not been detected for foreign objects can be retained so that accurate foreign object detection can be performed after accumulating through multiple frames (the vehicle has been driving for a period of time) until the conditions are met. As mentioned above, vehicles usually do not travel in a straight line, so using the circumscribed rectangular area of the detection frame and the reserved area as the passing area can cover the areas where the vehicle may travel through and avoid missed detection. Since there may be multiple transport vehicles, in order to avoid obstruction and interference from other transport vehicles and to accurately match the detected foreign objects with the vehicles, this solution accumulates the reserved area in the previous frame's passing area and the current frame's detection frame area as the current frame's passing area for foreign object detection, rather than accumulating all areas that the vehicle passes through in the foreign object detection area and then performing foreign object detection uniformly. Therefore, this solution has higher detection accuracy.

[0050] Step 106 , performing a first foreign object detection on the current frame image of the target area in the current frame passing area to obtain a first foreign object detection result. If the first foreign object detection result indicates that the target foreign object is detected, performing a second foreign object detection on the current frame control image of the target area to obtain a second foreign object detection result.

[0051] Among them, the target area can be the entire area or part of the area in the current frame. For example, the image of the area where the current frame passes can be intercepted from the current frame surveillance video image and input into a pre-trained foreign body detection model for foreign body detection. If the target foreign body is detected, the image of the target area can be intercepted from the current frame control image of the foreign body detection area for foreign body detection, and then the foreign body detection results of the two can be compared. The foreign body detection model can adopt the yolov8 neural network model. The foreign body can be a water stain, a stone or other object. The corresponding foreign body detection model can be trained in advance using a sample image containing the relevant foreign body. It can be understood that if the target area is the entire area, the retained area of the current frame (as the historical frame retained area corresponding to the next frame) is the intersection area of the current frame detection frame area and the foreign body detection area.

[0052] The current frame comparison image of the foreign object detection area can reflect the ground conditions before the transport vehicle passed through the area. It can be obtained based on the historical frame video images before the current frame, for example, it can be the previous frame video image or the superposition of multiple historical frame video images. Specifically, for the first frame video image in which a vehicle is detected entering the foreign object detection area, its comparison image can be the previous frame video image before the vehicle entered the area. It can be understood that the historical frame reserved area corresponding to the first frame video image is empty, so the current frame travel area corresponding to the first frame image is the intersection of the vehicle detection frame area and the foreign object detection area, and this intersection area is also the reserved area of the first frame image. Then, the image outside the reserved area position in the comparison image of the first frame image can be updated with the image information in the first frame image, while the image within the reserved area position is not updated. The image thus superimposed serves as the comparison image corresponding to the second frame image. Similarly, the comparison image of the subsequent frame image is obtained by updating the image outside the reserved area in the comparison image of the previous frame image.

[0053] Step 108 , judging whether the transport vehicle has discharged foreign objects during weighing based on the first foreign object detection result and the second foreign object detection result.

[0054] In implementation, if the first foreign object detection result is that no foreign object is detected, it can be determined that the transport vehicle currently does not have the behavior of discharging foreign objects by weighing, and monitoring and detection can continue. If a foreign object is detected in a certain frame in the area where the transport vehicle passes, the control image of the area where it passes is detected. If no foreign object is detected in the control image, or the size of the detected foreign object (such as the size of the detection frame) is smaller than the size of the foreign object in the current frame image of the area where it passes, that is, additional foreign objects appear after the vehicle passes, it can be determined that the transport vehicle currently has the behavior of discharging foreign objects by weighing. If the size and position of the foreign object detected in the control image are the same as the size and position of the foreign object detected in the current frame image of the area where it passes, it can be determined that the transport vehicle currently has the behavior of discharging foreign objects by weighing. Furthermore, in the case of determining that the transport vehicle has the behavior of discharging foreign objects by weighing, the server can intercept the image of the transport vehicle from the current frame monitoring video image and issue an alarm message to facilitate supervision of cheating in weighing.

[0055] The above-mentioned method for detecting the discharge of foreign objects by vehicles during weighing is to detect and track vehicles through the surveillance video of the material shipping area, identify the position of each transport vehicle, and when a transport vehicle enters the foreign object detection area, determine the circumscribed rectangular area of the current frame detection frame area and the historical frame retention area of the transport vehicle as the current frame travel area of the transport vehicle, and then perform foreign object detection on the current frame image of the travel area. If a foreign object is detected, the foreign object detection result is compared with the foreign object detection result of the current frame control image of the travel area. The historical frame retention area is the intersection area of the historical frame detection frame area and the foreign object detection area or the area in the historical frame travel area where foreign object detection is not performed. The circumscribed rectangular area of the current frame detection frame area and the historical frame retention area can cover the area passed by the transport vehicle, and the control image of the travel area is obtained based on the historical frame surveillance video image, which can reflect the ground conditions before the transport vehicle passed through the area. If there are foreign objects on the ground after the transport vehicle passes through the area, but there are no foreign objects or only a smaller amount of foreign objects on the ground before passing through, it can be determined that the transport vehicle has discharged foreign objects during weighing. Compared with manual supervision, this solution can improve the efficiency and accuracy of detecting vehicle weighing and discharging foreign objects, thereby improving the supervision effect of weighing cheating during material shipment and reducing losses to shippers.

[0056] In one implementation, the first foreign object detection in step 106 includes the following steps: determining the area other than the current frame detection frame area in the current frame passing area as the target area; performing the first foreign object detection on the current frame image of the target area to obtain a first foreign object detection result.

[0057] In this embodiment, foreign object detection can be performed on the area other than the detection frame area in the current frame's passing area, that is, foreign object detection is not performed on the detection frame area, so as to avoid wasting computing resources by detecting the vehicle-occluded area. It can be understood that the area in the current frame's passing area where no foreign object detection is performed is the intersection area of the detection frame area and the foreign object detection area, which is the reserved area of the current frame and will be used as the historical frame reserved area corresponding to the next frame of video image, so as to determine the passing area of the next frame when executing step 104. Figure 2b As shown in the figure, D i is the detection box area of the current frame (i-th frame), D i-1 is the detection frame area (reserved area) of the i-1th frame. There is a partial overlap between the two. The blue rectangular box is the circumscribed rectangular area of the two, which is the area passed by the current frame. i The area outside is the target area in the current frame passing area, such as Figure 2c The L-shaped frame area shown is a red line (it can be understood that the L-shape is only an example, and in other examples, the target area may be of other shapes).

[0058] In another implementation, the first foreign object detection in step 106 includes the following steps: dividing the area in the current frame passing area except the current frame detection frame area into multiple peripheral sub-areas according to the boundary lines of the detection frame, and determining the peripheral sub-areas in each peripheral sub-area that meet the preset resolution requirements as the target area; performing the first foreign object detection on the current frame image of the target area to obtain the first foreign object detection result.

[0059] In this embodiment, the area in the passing area except the detection frame area of the current frame can be divided into multiple peripheral sub-areas according to the boundary lines of the detection frame. Figure 2d In the example, the detection box D i The boundary line is extended to intersect with the boundary of the passing area, and the L-shaped frame area is divided into three rectangular areas S1, S2, and S3. The three rectangular areas can be used as peripheral sub-areas respectively, or the two rectangular areas (S1+S2) and S3 can be used as peripheral sub-areas, or the two rectangular areas (S2+S3) and S1 can be used as peripheral sub-areas, or the two rectangular areas (S1+S2) and (S2+S3) can be used as peripheral sub-areas, that is, the peripheral sub-areas can have an intersection. The server can determine the peripheral sub-area that meets the preset resolution requirements in each peripheral sub-area as the target area for foreign body detection. Since the input image of the foreign body detection model is required to be a rectangular image and has certain requirements on the resolution, the passing area outside the detection frame area is usually not a rectangular area (such as L-shaped or other shapes). Therefore, if foreign body detection is performed on all areas outside the detection frame, the detection area needs to be divided and the input model needs to be input multiple times for detection. Moreover, if the resolution of the detection area is too low or the difference between the width and height is large (the aspect ratio is too large or too small, usually the aspect ratio needs to meet 3:1 or 4:1), it will affect the model detection results. Therefore, this embodiment can further improve the accuracy of foreign body detection by performing foreign body detection on the areas that meet the resolution requirements in the peripheral sub-areas of the rectangle.

[0060] Specifically, the area with the largest area among the surrounding sub-areas can be determined as the candidate area. If the area of the candidate area is greater than a preset threshold and the aspect ratio meets the preset requirements, the candidate area is determined as the target area. For areas that do not meet the requirements, they are retained for cumulative detection with subsequent frame images. That is, the retained area of the current frame usually includes the current frame detection frame area and the surrounding sub-areas that have not been detected (excluding the intersection with the target area). Figure 2d In the example, if the surrounding sub-region (S1+S2) is the target region, then (D i+ S3) is the reserved area of the current frame. Since the surrounding sub-areas are divided according to the detection frame boundary, the reserved area is a rectangular area. Then, the circumscribed rectangular area of the reserved area and the detection frame area of the next frame can be determined as the passing area of the next frame. The reserved area is accumulated so that foreign object detection can be performed only after the detection requirements are met, thereby improving the accuracy of foreign object detection.

[0061] Accordingly, the reference image of the foreign object detection area needs to be updated based on the reserved area. Specifically, the server can retain the image of the reserved area in the current frame's reference image and update the image information outside the reserved area with the image information of the corresponding position in the current frame's video image, obtaining a reference image corresponding to the next frame's video image for use during the second foreign object detection in step 106. That is, the current frame's reference image can be obtained by updating the image of the area in the previous frame's reference image, excluding the reserved area, based on the previous frame's surveillance video image. Thus, each frame's reference image will retain an image of the area the vehicle passed through before foreign object detection was performed, accurately reflecting the ground conditions before the vehicle passed through that area, thereby ensuring the accuracy of the foreign object detection results.

[0062] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0063] Based on the same inventive concept, embodiments of the present application also provide a device for detecting foreign matter emissions from vehicles during weighing, which is used to implement the aforementioned method for detecting foreign matter emissions from vehicles during weighing. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the device for detecting foreign matter emissions from vehicles during weighing provided below can be found in the aforementioned method for detecting foreign matter emissions from vehicles during weighing, and will not be repeated here.

[0064] In one embodiment, Figure 3 As shown, a detection device 300 for the behavior of discharging foreign matter during vehicle weighing is provided, comprising: a tracking module 301, a determination module 302, a detection module 303 and a judgment module 304, wherein:

[0065] The tracking module 301 is used to obtain the surveillance video of the material shipping area, and perform vehicle detection and tracking on the surveillance video to obtain the position of the transport vehicle in each frame of the surveillance video image.

[0066] The determination module 302 is used to determine the current frame detection frame area and the circumscribed rectangular area of the historical frame retention area of the transport vehicle in the current frame monitoring video image as the current frame passing area of the transport vehicle when the transport vehicle enters the foreign object detection area.

[0067] The detection module 303 is used to perform a first foreign object detection on the current frame image of the target area in the current frame passing area to obtain a first foreign object detection result. If the first foreign object detection result indicates that the target foreign object is detected, a second foreign object detection is performed on the current frame control image of the target area to obtain a second foreign object detection result.

[0068] The judgment module 304 is configured to judge whether the transport vehicle has discharged foreign objects during weighing according to the first foreign object detection result and the second foreign object detection result.

[0069] In one embodiment, the detection module 303 is further used to: determine the area other than the current frame detection frame area in the current frame passing area as the target area; perform a first foreign object detection on the current frame image of the target area to obtain a first foreign object detection result.

[0070] In one embodiment, the detection module 303 is also used to: divide the area of the current frame passing area except the current frame detection frame area into multiple peripheral sub-areas according to the boundary lines of the detection frame, and determine the peripheral sub-areas in each of the peripheral sub-areas that meet the preset resolution requirements as the target area; perform a first foreign object detection on the current frame image of the target area to obtain a first foreign object detection result.

[0071] In one embodiment, the detection module 303 is further configured to determine the region with the largest area among the peripheral sub-regions as a candidate region; if the area of the candidate region is greater than a preset threshold and the aspect ratio meets a preset requirement, the candidate region is determined as a target region.

[0072] In one embodiment, the detection module 303 is further used to: update the area image of the historical frame control image of the foreign object detection area except the historical frame retained area according to the historical frame monitoring video image to obtain the current frame control image of the foreign object detection area; intercept the image of the target area from the current frame control image of the foreign object detection area to perform a second foreign object detection to obtain a second foreign object detection result.

[0073] In one embodiment, the judgment module 304 is also used to: if the second foreign object detection result indicates that the target foreign object is not detected, or the target foreign object is detected and the size of the target foreign object is smaller than the size of the target foreign object in the first foreign object detection result, then it is determined that the transport vehicle has over-weighed and discharged foreign objects.

[0074] In one embodiment, the device further includes an alarm module for capturing an image of the transport vehicle from the current frame monitoring video image and issuing an alarm message when it is determined that the transport vehicle has discharged foreign matter after weighing.

[0075] Each module in the aforementioned device for detecting foreign matter discharge during vehicle weighing can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a computer device's memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0076] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data required or generated for executing the above-mentioned method for detecting the emission of foreign matter from vehicles during weighing. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for detecting the emission of foreign matter from vehicles during weighing is implemented.

[0077] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0078] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0079] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0080] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0081] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0082] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0083] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0084] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for detecting the emission of foreign matter from a vehicle during weighing, characterized in that: The method comprises: Obtain surveillance video of the material shipping area, and perform vehicle detection and tracking on the surveillance video to obtain the position of the transport vehicle in each frame of the surveillance video image; When the transport vehicle enters the foreign object detection area, the circumscribed rectangular area of the current frame detection frame area and the historical frame retention area of the transport vehicle in the current frame monitoring video image is determined as the current frame travel area of the transport vehicle; the historical frame retention area is the intersection area of the historical frame detection frame area and the foreign object detection area or the area in the historical frame travel area where no foreign object detection is performed; Performing a first foreign object detection on a current frame image of a target area in the current frame passing area to obtain a first foreign object detection result; if the first foreign object detection result indicates that the target foreign object is detected, performing a second foreign object detection on a current frame control image of the target area to obtain a second foreign object detection result; Determining whether the transport vehicle has discharged foreign objects during weighing based on the first foreign object detection result and the second foreign object detection result; The performing of a second foreign body detection on the current frame control image of the target area to obtain a second foreign body detection result includes: Update the image of the area except the historical frame retained area in the historical frame comparison image of the foreign object detection area according to the historical frame monitoring video image to obtain the current frame comparison image of the foreign object detection area; An image of the target area is intercepted from the current frame comparison image of the foreign object detection area to perform a second foreign object detection to obtain a second foreign object detection result.

2. The method according to claim 1, characterized in that The performing first foreign object detection on the current frame image of the target area in the current frame passing area to obtain a first foreign object detection result includes: Determine an area in the current frame passing area other than the current frame detection frame area as a target area; A first foreign object detection is performed on the current frame image of the target area to obtain a first foreign object detection result.

3. The method according to claim 1, characterized in that The performing first foreign object detection on the current frame image of the target area in the current frame passing area to obtain a first foreign object detection result includes: Dividing the area of the current frame passing area, excluding the current frame detection frame area, into a plurality of peripheral sub-areas according to the boundary lines of the detection frame, and determining the peripheral sub-areas in each of the peripheral sub-areas that meet the preset resolution requirements as the target area; A first foreign object detection is performed on the current frame image of the target area to obtain a first foreign object detection result.

4. The method according to claim 3, characterized in that The step of determining the peripheral sub-region that meets the preset resolution requirement among the peripheral sub-regions as the target region includes: Determine the region with the largest area among the peripheral subregions as a candidate region; If the area of the candidate region is greater than a preset threshold and the aspect ratio meets a preset requirement, the candidate region is determined as the target region.

5. The method according to claim 1, wherein The determining, based on the first foreign object detection result and the second foreign object detection result, whether the transport vehicle has discharged foreign objects during weighing includes: If the second foreign object detection result indicates that no target foreign object is detected, or that a target foreign object is detected and the size of the target foreign object is smaller than the size of the target foreign object in the first foreign object detection result, it is determined that the transport vehicle has discharged foreign objects by overweighing.

6. The method according to claim 1, characterized in that The method further comprises: When it is determined that the transport vehicle has discharged foreign objects during weighing, an image of the transport vehicle is captured from the current frame monitoring video image, and an alarm message is issued.

7. A device for detecting the emission of foreign matter from vehicles during weighing, characterized in that: The device comprises: The tracking module is used to obtain surveillance video of the material shipping area, and perform vehicle detection and tracking on the surveillance video to obtain the position of the transport vehicle in each frame of the surveillance video image; a determination module, configured to, when the transport vehicle enters the foreign object detection area, determine the circumscribed rectangular area of the current frame detection frame area and the historical frame retention area of the transport vehicle in the current frame monitoring video image as the current frame passing area of the transport vehicle; A detection module is configured to perform a first foreign object detection on a current frame image of a target area in the current frame passing area to obtain a first foreign object detection result; if the first foreign object detection result indicates that a target foreign object is detected, perform a second foreign object detection on a current frame control image of the target area to obtain a second foreign object detection result; wherein, performing the second foreign object detection on the current frame control image of the target area to obtain the second foreign object detection result comprises: updating an image of an area other than the historical frame retained area in the historical frame control image of the foreign object detection area according to a historical frame monitoring video image to obtain a current frame control image of the foreign object detection area; and intercepting an image of the target area from the current frame control image of the foreign object detection area to perform a second foreign object detection to obtain a second foreign object detection result; A judgment module is used to judge whether the transport vehicle has discharged foreign objects during weighing according to the first foreign object detection result and the second foreign object detection result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images