A mining card count method, device, equipment and storage medium

Abstract

The application discloses a kind of mine card count method, device, equipment and storage medium of material pouring.It includes: obtaining the monitoring video stream of mine card material pouring scene;Image recognition model is used to image recognition to obtain identification parameter, wherein the identification parameter includes the start action of material pouring, the end action of material pouring and the mine truck mark of material pouring;According to the identification parameter, the material pouring times of each mine card in the monitoring video stream are counted.Through the camera deployed in the work scene, the monitoring video stream of mine card material pouring scene is obtained, and the material pouring times of mine card are counted by image recognition, so as to effectively reduce the cost of work, and reduce the error caused by manual.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and in particular, to a mining card dumping counting method, device, equipment and storage medium. BACKGROUND

[0002] Industrialization and the construction of intelligent mines both need to reduce manual operation steps and digitize production information. In particular, when mining cards are dumped, the number of times of dumping of the mining cards usually needs to be counted in order to determine the progress of the project. At present, when mining cards are dumped, manual counting is generally used; or a ground scale is installed at a specified position, and when the mining card passes through the ground scale, the ground scale is used to automatically count,

[0003] However, when manual counting is used to count the number of times of dumping of the mining cards, counting errors are usually caused by obstructions or human factors. When the ground scale is used, additional costs are required, and the position of the ground scale is fixed after installation, which is not convenient for counting the number of times of dumping of the mining cards in various scenes. Therefore, the existing mining card dumping technology cannot meet the actual needs of users. SUMMARY

[0004] The present application provides a mining card dumping counting method, device, equipment and storage medium to accurately count the number of times of dumping of the mining cards.

[0005] According to a first aspect of the present application, a mining card dumping counting method is provided, comprising:

[0006] obtaining a monitoring video stream of a mining card dumping scene;

[0007] using an image recognition model to perform image recognition on the monitoring video stream to obtain recognition parameters, wherein the recognition parameters include a dumping start action, a dumping end action and a mining truck mark that is dumping;

[0008] counting the number of times of dumping of each mining card in the monitoring video stream according to the recognition parameters.

[0009] According to another aspect of the present application, a mining card dumping counting device is provided, comprising: a monitoring video stream obtaining module configured to obtain a monitoring video stream of a mining card dumping scene;

[0010] an image recognition module configured to use an image recognition model to perform image recognition on the monitoring video stream to obtain recognition parameters, wherein the recognition parameters include a dumping start action, a dumping end action and a mining truck mark that is dumping;

[0011] a mining card dumping counting module configured to count the number of times of dumping of each mining card in the monitoring video stream according to the recognition parameters.

[0012] According to another aspect of the present application, there is provided an electronic device comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein

[0015] the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method according to any one of the embodiments of the present application.

[0016] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the method according to any one of the embodiments of the present application when executed.

[0017] The technical solution of the embodiments of the present application reduces the cost of the operation and reduces the error caused by manual operation by deploying a camera in the operation scene, obtaining a monitoring video stream of the dump scene of the mine card, and counting the dump times of the mine card by means of image recognition.

[0018] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0020] Figure 1 is a flow chart of a mine card dump counting method according to the first embodiment of the present application;

[0021] Figure 2 is a flow chart of a mine card dump counting method according to the second embodiment of the present application;

[0022] Figure 3 is a structural schematic diagram of a yolox network according to the first embodiment of the present application;

[0023] Figure 4 is a structural schematic diagram of a mine card dump counting device according to the third embodiment of the present application;

[0024] Figure 5 is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0027] Embodiment one

[0028] Figure 1 A flowchart of a counting method for ore card pouring is provided for the first embodiment of the present application. The present embodiment can be applied to the counting of ore card pouring. The method can be executed by a counting device for ore card pouring, which can be realized in the form of hardware and / or software. As shown in the figure, the method comprises: Figure 1

[0029] Step S101, acquiring a monitoring video stream of the ore card pouring scene.

[0030] Specifically, in the present embodiment, a camera will be deployed in the ore card pouring scene, and the ore card pouring scene will be photographed by the deployed camera. The photographed monitoring video stream is sent to the terminal in a wireless transmission manner. When the ore card pouring scene sending position changes, only the installation position of the camera needs to be adjusted, which greatly reduces the cost compared with the deployment of the weighbridge.

[0031] ​It should be noted that the monitoring video stream obtained in the embodiment can be a specified time length, that is, the number of times of material dumping of the mine truck in a specified time range is counted, for example, the specified time length can be 1 hour. Of course, the embodiment is only an example and does not limit the specific value of the specified time length. The user can set it according to the actual situation.

[0032] In step S102, an image recognition model is used to perform image recognition on the monitoring video stream to obtain recognition parameters.

[0033] Optionally, the image recognition model is used to perform image recognition on the monitoring video stream to obtain recognition parameters, including: performing image recognition on the monitoring video stream, starting a first counter when a material dumping action is detected in a first specified frame; determining that a material dumping start action is obtained when it is determined by the first counter that the material dumping action is detected in a first specified number of frames starting from the first specified frame; starting a second counter when the material dumping action disappears in a second specified frame, and determining that a material dumping end action is obtained when it is determined by the second counter that the material dumping action disappears in a second specified number of frames starting from the second specified frame; and determining the mine truck tag that dumps material according to the frames between the material dumping start action and the material dumping end action.

[0034] Specifically, after receiving the monitoring video stream sent by the camera, a pre-trained image recognition model can be used to perform image recognition on the monitoring video stream to obtain the material dumping start action, the material dumping end action, and the mine truck tag that dumps material. In the embodiment, the optical flow information and the inter-frame timing information in the monitoring video stream are not read, and only the image level is used to complete the recognition of the material dumping behavior. Two state judgments are mainly set: the material dumping start action and the material dumping end action, and the target objects of image recognition mainly include: the truck tag and the material dumping action. From the recognition of the material dumping action, if the action lasts for a corresponding time, the material dumping start action is judged. The truck tag information recognized is counted when the material dumping action starts. In order to prevent interference of other truck tags, it is necessary to judge whether the truck tag recognition box is in the material dumping action recognition box. When the material dumping action disappears and lasts for a corresponding time, the material dumping end action is judged. By counting the truck tag information detected during this period, the mine truck that completes the material dumping action is determined, and the material dumping count of the mine truck is incremented by one.

[0035] In one specific implementation, the acquired monitoring video stream with a time length of 1 hour is subjected to image recognition by a pre-trained image recognition model. When the pouring action is recognized in the 2nd frame in the video stream, a first counter is started, and the recognition result of each frame after the 2nd frame is counted. When it is determined that the pouring action is detected in the following 75 frames, the pouring start action is determined to be acquired. The time length of processing 75 frames is basically 3 seconds. When it is determined that the pouring action lasts for 3 seconds, the pouring start action is determined to be acquired. In addition, when the pouring action disappears in the 100th frame in the video stream, a second counter is started, and the recognition result of each frame after the 100th frame is counted. When it is determined that the pouring action disappears in the following 100 frames, the pouring end action is determined to be acquired. When both the pouring start action and the pouring end action are present, it is determined that one pouring is completed. In the actual process of pouring by the mining truck, there may be a situation of illegal operation by the driver, i.e., only the pouring start action is present, and the pouring end action is not completed, i.e., the mining truck is driven away without the hopper being flat. In this case, only the pouring start action is present, and it is not determined that one pouring is completed.

[0036] Optionally, the mining truck license plate performing the pouring is determined according to the frames between the pouring start action and the pouring end action, including: performing license plate recognition on the frames between the pouring start action and the pouring end action; using a third counter to count the number of times of the license plate appearing; determining a target license plate corresponding to the maximum counting number in the third counter, and taking the target license plate as the mining truck license plate performing the pouring.

[0037] It should be noted that in the case where the pouring start action and the pouring end action are both determined, although it can be determined that a pouring is completed, it is still necessary to determine which specific mine truck is pouring, and therefore vehicle identification will be performed on the frames between the pouring start action and the pouring end action, for example, vehicle identification is performed on the 123 frames between the 77th frame of the pouring start action and the 200th frame of the pouring end action, and the third counter is used to count the vehicle mark located in the vehicle identification frame. Since the vehicle mark of the mine truck that temporarily passes through the area may be captured in these frames, but in general, the number of frames captured by the vehicle mark of the mine truck that temporarily passes through the area is usually small, while the number of frames captured by the vehicle mark of the mine truck that is always located in the area and is pouring is usually large, for example, the third counter captures the vehicle mark 001 of the passing mine truck 8 times, but captures the vehicle mark 002 of the mine truck that is pouring 100 times, so in order to prevent interference from other vehicle marks, the target vehicle mark 002 corresponding to the maximum number of counts in the third counter is determined, and the target vehicle mark 002 is taken as the vehicle mark of the mine truck that is pouring. Thus, according to the pouring start action, the pouring end action, and the vehicle mark of the mine truck that is pouring, it can be determined that the mine truck with the vehicle mark 002 has completed a pouring. Of course, in this embodiment, only the pouring of the mine truck with the vehicle mark 002 is taken as an example for description, and the determination method of the other number of pourings of the mine truck with the vehicle mark 002 and the determination method of the number of pourings of other mine trucks are substantially the same, and therefore, the details are not described herein.

[0038] In step S103, the number of pourings of each mine truck in the monitoring video stream is counted according to the identification parameters.

[0039] Optionally, the number of pourings of each mine truck in the monitoring video stream is counted according to the identification parameters, including: determining the number of occurrences of the pouring start action and the pouring end action corresponding to the vehicle mark of the mine truck that is pouring in the monitoring video stream; and taking the number of occurrences as the number of pourings of the mine truck.

[0040] Specifically, for a monitoring video stream with a length of 1 hour, when it is determined through identification that the pouring start action corresponding to the vehicle mark 002 of the mine truck occurs 10 times, and the number of occurrences of the pouring end action is 10 times, it is determined that the mine truck with the vehicle mark 002 has performed 10 pourings. In addition, when it is determined through identification that the pouring start action corresponding to the vehicle mark 001 of the mine truck occurs 15 times, but the number of occurrences of the pouring end action is 14 times, it is determined that the driver of the mine truck with the vehicle mark 001 has performed a violation operation, and therefore it is determined that the mine truck with the vehicle mark 001 has performed 14 pourings.

[0041] Optionally, after the target vehicle mark is taken as the vehicle mark of the mine truck that is pouring, the first counter, the second counter, and the third counter are further cleared.

[0042] It should be noted that after each determination of the dump truck mark for dumping, in order to facilitate the next dumping statistics, the first counter for determining the dumping start action, the second counter for determining the dumping end action, and the third counter for dump truck mark statistics will be cleared, so as to facilitate the subsequent dumping statistics quickly and accurately, for example, after determining that the dump truck mark 002 of the dump truck completes a dumping in the first 200 frames of the monitoring video stream, the first counter, the second counter and the third counter are cleared, so as to facilitate the identification of the image frames after 200 frames in the monitoring video stream, to continue to count the dump truck dumping.

[0043] In the embodiment of the application, the camera is deployed in the working scene to obtain the monitoring video stream of the dump truck dumping scene, and the image recognition method is used to count the number of dump truck dumpings, thereby effectively reducing the cost of the work and reducing the error caused by manual operation.

[0044] Embodiment two

[0045] Figure 2 A flow chart of a dump truck dumping counting method is provided for the second embodiment of the application, and the specific process of obtaining the image recognition model is described based on the above-mentioned embodiment, as shown in the figure, the method comprises: Figure 2

[0046] Step S201, obtaining the monitoring video stream of the dump truck dumping scene.

[0047] Step S202, using the image recognition model to perform image recognition on the monitoring video stream to obtain the recognition parameters.

[0048] Optionally, using the image recognition model to perform image recognition on the monitoring video stream to obtain the recognition parameters comprises: performing image recognition on the monitoring video stream, starting the first counter when the dumping action is detected in the first specified frame; determining the dumping start action when the dumping action is detected in the first specified number of frames starting from the first specified frame through the first counter; starting the second counter when the dumping action disappears in the second specified frame, and determining the dumping end action when the dumping action disappears in the second specified number of frames starting from the second specified frame through the second counter; determining the dump truck mark for dumping according to the frames between the dumping start action and the dumping end action.

[0049] Step S203, obtaining the initial sample image of the dump truck dumping.

[0050] ​Specifically, the historical video data is filtered in the embodiment, specifically, all the pouring actions of the mining cards in the historical video data are cut, and the number of pouring times of different mining cards is counted and classified for subsequent model test. The ratio of the test set and the training set is set to 1:3. Then the historical video is frame extracted using a tool to obtain initial sample images.

[0051] In step S204, the initial sample images are data augmented to obtain training sample images.

[0052] Optionally, the initial sample images are data augmented to obtain training sample images, including: converting the initial sample images into augmented sample images in a specified manner, wherein the specified manner includes cutting, rotating and flipping; and performing different levels of fogging processing on the augmented sample images to obtain training sample images, wherein the number and format of the training sample images are more than those of the initial sample images.

[0053] Therefore, the complexity of the outdoor operation environment of the mining card in the mine and the small amount of training data, the number of initial sample images may be small, or there may be incomplete coverage of working conditions, for example, the situation that the vehicle logo is not clear due to daytime, night, vehicle shielding and other rain and fog weather is not fully reflected. Therefore, in order to ensure the diversity of the sample, the initial sample images are converted into augmented sample images in the cutting, rotating and flipping manner, and then the augmented sample images are transformed by opencv, and certain fogging, blurring, reducing brightness and resolution and other operations are performed to obtain training sample images, so as to simulate the rain and fog and night environment encountered in actual operation, and to improve the robustness of the algorithm as much as possible.

[0054] In step S205, the training sample images are used to train the yolox network to obtain an image recognition model.

[0055] Specifically, after obtaining the mining card pouring training sample images with sufficient quantity and containing various working condition scenes, the training sample images are used to train the yolox network to obtain an image recognition model. For example, Figure 3 The structure of the yolox network is shown in FIG. 1. Figure 3The yolox network shown mainly consists of three parts, which are CSPDarknet, PAFPN and YOLOXHEAD. Among them, CSPDarknet is the backbone feature extraction network of yolox, which has three outputs, each of which will be input to a specific part of PAFPN for further feature fusion processing. Each output here represents different scale information of the Darknet network. PAFPN is the enhanced feature extraction network of yolox, which mainly performs feature fusion on the three different scale inputs of the pre-module CSPDarknet, which is a multi-scale information fusion process. The last module of yolox is the HEAD part, which is mainly the classifier and regressor of yolox. HEAD judges the output feature maps of PAFPN in three scales, corresponds to the object features in the label, and gets the final output. Classification and regression are completed in the convolution module CBS of HEAD.

[0056] Among them, the training sample images obtained in the embodiment are used to train the yolox network to obtain an image recognition model, and test data are used to test the image recognition model obtained by training to determine the recognition error of the image recognition model. When the error determined by the test meets the accuracy requirement, the obtained image recognition model is used for subsequent image recognition of the monitoring video stream.

[0057] Step S206, count the number of times of pouring material of each mine truck in the monitoring video stream according to the recognition parameter.

[0058] Optionally, counting the number of times of pouring material of each mine truck in the monitoring video stream according to the recognition parameter comprises: determining the number of times of occurrence of the pouring material start action and the pouring material end action corresponding to the mine truck mark that pours material in the monitoring video stream; and taking the number of times of occurrence as the number of times of pouring material of the mine truck.

[0059] Optionally, after the target vehicle mark is taken as the mine truck mark that pours material, the method further comprises: clearing the first counter, the second counter and the third counter.

[0060] The behavior recognition algorithm mainly based on image recognition is trained in the embodiment, corresponding data augmentation operations are performed on the training data to cope with complex working conditions, and the image recognition result is counted and judged through an additional counting judgment algorithm. The behavior recognition algorithm mainly based on image recognition is trained, specifically, the yolox network is used to frame recognition of the video, and the counting judgment algorithm is used to count and judge the image recognition result through the recognition result of the limited frame image, so that the dump truck dump recognition counting is completed in a low-cost manner. The counting judgment algorithm is used to count and judge the image recognition result, that is, the recognition results of multiple images are analyzed, various possible recognition interference items are excluded, and the start and end of the dump truck dump action are judged, and the vehicle logo of the dump truck is recognized, and the final dump times of each vehicle are counted. The training data is subjected to corresponding data augmentation operations, considering the complexity of the mine dump truck outdoor operation environment and the small amount of training data. When the training data set required for algorithm production is made, certain fogging, blurring, reducing brightness and resolution and the like are performed on the data set to simulate the rain, fog and night environment encountered in actual operation, and the robustness of the algorithm is improved as much as possible. In addition, in order to increase the amount of training data, cutting, rotation and flipping and the like are also used for data augmentation.

[0061] The embodiment of the present application acquires the monitoring video stream of the dump truck dump scene by deploying a camera in the working scene, and counts the dump times of the dump truck by means of image recognition, thereby effectively reducing the cost of the work and reducing the error caused by manual operation. The initial sample data is subjected to corresponding data augmentation operations to obtain training sample images, thereby improving the training recognition accuracy of the image recognition model.

[0062] Embodiment three

[0063] Figure 4 A structure schematic diagram of a dump truck dump counting device provided by the third embodiment of the present application is shown in FIG. 3. Figure 4 As shown in the figure, the device comprises a monitoring video stream acquisition module 310, an image recognition module 320 and a dump truck dump counting module 330.

[0064] The monitoring video stream acquisition module 310 is used to acquire the monitoring video stream of the dump truck dump scene;

[0065] The image recognition module 320 is used to acquire the recognition parameters by image recognition of the monitoring video stream by using the image recognition model, wherein the recognition parameters include the dump start action, the dump end action and the dump truck logo;

[0066] The dump truck dump counting module 330 is used to count the dump times of each dump truck in the monitoring video stream according to the recognition parameters.

[0067] Optionally, the device further comprises an image recognition model training module configured to obtain initial sample images of the ore truck dumping;

[0068] The initial sample images are data-augmented to obtain training sample images.

[0069] The training sample images are used to train the yolox network to obtain the image recognition model.

[0070] Optionally, the image recognition module is configured to perform image recognition on the monitoring video stream, and start a first counter when a dumping action is detected in a first specified frame;

[0071] When the first counter determines that the dumping action is detected in a first specified number of frames starting from the first specified frame, it is determined that the dumping start action is obtained.

[0072] When the second counter is started when the dumping action disappears in a second specified frame, and the second counter determines that the dumping action disappears in a second specified number of frames starting from the second specified frame, it is determined that the dumping end action is obtained.

[0073] The frame between the dumping start action and the dumping end action is determined to obtain the ore truck logo.

[0074] Optionally, the image recognition module is further configured to perform logo recognition on the frames between the dumping start action and the dumping end action.

[0075] The third counter is used to count the number of times the logo appears.

[0076] The target logo corresponding to the maximum number of times counted in the third counter is determined as the ore truck logo that performs the dumping.

[0077] Optionally, the ore truck dumping counting module is configured to determine the number of times the dumping start action and the dumping end action corresponding to the ore truck logo that performs the dumping appear in the monitoring video stream.

[0078] The number of times is used as the number of times the ore truck dumps.

[0079] Optionally, the device further comprises a counter cleaning module configured to clear the first counter, the second counter, and the third counter.

[0080] Optionally, the image recognition model training module is configured to perform format conversion on the initial sample images according to a specified manner to obtain augmented sample images, wherein the specified manner includes cropping, rotating, and flipping.

[0081] The augmented sample images are subjected to different levels of fogging to obtain training sample images, wherein the number and format of the training sample images are more than those of the initial sample images.

[0082] The counting device for the reversed ore card provided by the embodiment of the present application can execute the counting method for the reversed ore card provided by any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0083] Embodiment Four

[0084] Figure 5 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0085] As Figure 5 shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0086] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, a speaker, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0087] The processor 11 can be various general and / or special purpose processing components having processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the ore pass spill count method.

[0088] In some embodiments, the ore pass spill count method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the ore pass spill count method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the ore pass spill count method by any other suitable means, such as by means of firmware.

[0089] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0090] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0091] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0092] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0093] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0094] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0095] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0096] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A counting method for dumping ore from mining trucks, characterized in that, include: Acquire monitoring video streams of mining truck unloading scenarios; An image recognition model is used to perform image recognition on the monitoring video stream to obtain recognition parameters, wherein the recognition parameters include the start action of unloading, the end action of unloading, and the logo of the mining truck performing the unloading; The number of times each mining card is dumped in the monitoring video stream is counted according to the identification parameters. The step of using an image recognition model to perform image recognition on the monitoring video stream to obtain recognition parameters includes: performing image recognition on the monitoring video stream, and activating a first counter when a material pouring action is detected in a first specified frame; When the first counter determines that a material rewinding action has been detected in a first specified number of frames starting from the first specified frame, then it is determined that a material rewinding start action has been obtained. When the material pouring action disappears in the second specified frame, the second counter is started. When the material pouring action disappears in the second specified number of frames starting from the second specified frame, the material pouring end action is determined to be obtained. The target of the mining truck performing the unloading is determined based on the frame between the unloading start action and the unloading end action; Determining the target of the mining truck performing the unloading based on the frame between the unloading start action and the unloading end action includes: Car logo recognition is performed on the frames between the start and end of the material pouring action. A third counter is used to count the number of times the car logo appears. The target vehicle logo corresponding to the maximum number of counts in the third counter is determined, and the target vehicle logo is used as the mining truck logo for unloading materials.

2. The method according to claim 1, characterized in that, Before using an image recognition model to perform image recognition on the surveillance video stream to obtain recognition parameters, the process also includes... Obtain the initial sample image of the mining truck unloading; Data augmentation is performed on the initial sample image to obtain training sample images; The image recognition model is obtained by training the YOLOx network using the training sample images.

3. The method according to claim 1, characterized in that, The step of counting the number of times each mining card is dumped in the monitoring video stream according to the identification parameters includes: Determine the number of times the unloading start action and the unloading end action occur corresponding to the mining truck logo in the monitoring video stream; The number of occurrences is taken as the number of times the mining card is emptied.

4. The method according to claim 1, characterized in that, After using the target vehicle logo as the logo for the mining truck being unloaded, the method further includes: The first counter, the second counter, and the third counter are cleared.

5. The method according to claim 2, characterized in that, The step of data augmentation of the initial sample image to obtain training sample images includes: The initial sample image is converted into an augmented sample image according to a specified method, wherein the specified method includes cropping, rotation, and flipping; The augmented sample images are subjected to different levels of fogging processing to obtain the training sample images, wherein the number and format of the training sample images are greater than those of the initial sample images.

6. A counting device for discharging ore from a mining truck, characterized in that, include: The monitoring video stream acquisition module is used to acquire the monitoring video stream of the mining truck unloading scene; The image recognition module is used to perform image recognition on the monitoring video stream using an image recognition model to obtain recognition parameters, wherein the recognition parameters include the material unloading start action, the material unloading end action, and the logo of the mining truck performing the material unloading; The mining truck unloading counting module is used to count the number of unloading operations of each mining truck in the monitoring video stream according to the identification parameters. The image recognition module is used to perform image recognition on the monitoring video stream, and to activate the first counter when a material pouring action is detected in the first specified frame; When the first counter determines that a material rewinding action has been detected in a first specified number of frames starting from the first specified frame, then it is determined that a material rewinding start action has been obtained. When the material pouring action disappears in the second specified frame, the second counter is started. When the material pouring action disappears in the second specified number of frames starting from the second specified frame, the material pouring end action is determined to be obtained. The target of the mining truck performing the unloading is determined based on the frame between the unloading start action and the unloading end action; The image recognition module is also used to recognize car logos in the frames between the start of the material pouring action and the end of the material pouring action; A third counter is used to count the number of times the car logo appears. The target vehicle logo corresponding to the maximum number of counts in the third counter is determined, and the target vehicle logo is used as the mining truck logo for unloading materials.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method of any one of claims 1-5.

Images