Open pit mine environment monitoring method and environment monitoring system

Abstract

The invention discloses an open-pit mine environment monitoring method and an environment monitoring system, and relates to the field of environment monitoring; the method comprises collecting open-pit mine fire coal dust images and making them into a data set; using part of the data set as a training set; building a YOLO training model, and inputting the training set into the training model for training to obtain a fire coal dust recognition model; collecting images of positions to be detected in real time, and filtering out noise in the images; inputting the images of positions to be detected into the fire coal dust recognition model for recognition, and the fire coal dust recognition model outputs a recognition result, thereby realizing the recognition of fire coal dust; compared with the existing open-pit mine manual monitoring, the method can effectively save labor costs and improve the efficiency of environmental monitoring.

Description

Technical Field

[0001] The present invention relates to the field of environmental monitoring, and in particular to an open-pit mine environmental monitoring method and an environmental monitoring system. Background Art

[0002] Mineral resources are an important material basis for my country's economic and social development. The maintenance of mining development order and the protection and restoration of open-pit mine environment are important components of promoting ecological civilization. Adhering to the basic national policy of saving resources and protecting the environment, establishing a monitoring system that reflects the entire process of mineral resource development environment, including resource consumption, environmental damage, environmental restoration and ecological protection, and carrying out all-weather monitoring of all elements of mineral resource development environment have always been important requirements of national mining administration. Existing open-pit mines use manual monitoring. Manual identification of coal dust is labor-intensive and inefficient, and a more intelligent solution is needed. Summary of the invention

[0003] The purpose of the present invention is to provide an open-pit mine environment monitoring method and an environment monitoring system to solve the problem that the existing open-pit mine adopts manual monitoring, and the manual identification of coal dust is labor-intensive and inefficient.

[0004] According to a first aspect of the present disclosure, the present invention provides an open-pit mine environment monitoring method, the method comprising:

[0005] Step S1, collecting open-pit coal dust images and making them into a data set; part of the data set is used as a training set;

[0006] Step S2, building a YOLO training model, and inputting the training set into the training model for training to obtain a coal dust recognition model;

[0007] Step S3, collecting an image of the position to be detected in real time and filtering out noise in the image;

[0008] Step S4, inputting the image of the position to be detected into the fire coal dust recognition model for recognition, and the fire coal dust recognition model outputs a recognition result, thereby realizing the recognition of fire coal dust.

[0009] In an exemplary embodiment of the present disclosure, step S1 includes the following steps:

[0010] Step S1.1, obtaining an open-pit mine on-site video;

[0011] Step S1.2, using the ffmpeg tool to capture the acquired video into frames of images;

[0012] Step S1.3, use the data annotation tool labelme to annotate the coal dust in the image and generate an xml file in VOC format;

[0013] Step S1.4, use Python to convert the annotated file into the txt file format required by the YOLO model; then read all the images and annotation files, and match their file names one by one; randomly divide them into training set, validation set and test set according to 7:2:1; write the number of nc categories and the file addresses of the training set, validation set and test set under the data.yaml file; finally, store the completed data set in the server.

[0014] In an exemplary embodiment of the present disclosure, step S2 includes the following steps:

[0015] Step S2.1, use anaconda on the image computing server to pull the python library required by the YOLO model in the requirement.txt file; install cuda and cudnn on the image computing server, configure the environment variables of cuda and cudnn, and use GPU to accelerate the operation of the YOLO model;

[0016] Step S2.2, preprocessing the training set: using Mosaic data enhancement to stitch through random scaling, random cropping, and random arrangement, so that the ratio of the width and height of the target bounding box to the width and height of the image is less than 0.1 or the square root of the ratio of the area of ​​the target bounding box to the area of ​​the image is less than 0.03.

[0017] Step S2.3, download the pre-trained weights of the YOLO model; adjust the parameters of the YOLO model multiple times; optimize the network model: select the depth and width of the network model to control the model size; train the pre-processed data set through the pre-trained weight parameters, and finally obtain the optimal network training weight parameters.

[0018] In an exemplary embodiment of the present disclosure, step S3 includes the following steps:

[0019] Step S3.1, transmitting the video data collected from the open-pit mine to a multi-channel real-time video analysis system for streaming processing to accelerate the video encoding and decoding process;

[0020] Step S3.2, using OpenCV to convert video data into image data;

[0021] Step S3.3, processes the image data of the video frame frame by frame through OpenCV, wherein the image data processing is specifically as follows: first, grayscale the color image of each frame to generate a black and white grayscale image; then, binarize the grayscale image; the purpose of image data processing is to convert the color image into a binary image, in which process the noise in the image is filtered out, so that the boundary between the coal dust and the background in the image data is more obvious; at the same time, interference factors such as some parts of the image are filtered out.

[0022] In an exemplary embodiment of the present disclosure, step S4 is also included, using a laser pan-tilt platform to determine the location of coal dust.

[0023] In an exemplary embodiment of the present disclosure, step S5 is further included, setting an alarm threshold, and when fire coal or dust appears in the extracted real-time image and exceeds the set threshold, an alarm is issued.

[0024] In an exemplary embodiment of the present disclosure, it also includes an environmental parameter alarm; using wireless sensor equipment to monitor other environmental data of the open-pit mine, transmitting various values ​​to the server via wireless transmission, setting an alarm threshold, and when the detected environmental data exceeds the set threshold, an alarm is issued.

[0025] According to the second aspect of the present disclosure, the present application also provides an environment monitoring system, comprising:

[0026] The acquisition module is used to collect images of coal dust in open-pit mines and make them into a data set; part of the data set is used as a training set;

[0027] The training module is used to build a YOLO training model and input the training set into the training model for training to obtain a coal dust recognition model;

[0028] A real-time acquisition module is used to acquire images of the position to be detected in real time and filter out noise in the image;

[0029] The recognition module is used to input the image of the position to be detected into the fire coal dust recognition model for recognition, and the fire coal dust recognition model outputs the recognition result, thereby realizing the recognition of fire coal dust.

[0030] According to a third aspect of the present disclosure, 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 any of the methods described in the first aspect when executing the computer program.

[0031] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, any of the methods described in the first aspect above is implemented.

[0032] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements any of the methods described in the first aspect above.

[0033] The beneficial effects of the present invention are as follows: the present invention provides an open-pit mine environment monitoring method and an environment monitoring system, which can identify fire coal and dust through the YOLO model according to the video data stream of the open-pit mine site, and quickly locate the fire coal and dust position according to the laser pan / tilt; and issue an early warning for fire coal dust exceeding the threshold through the monitoring and early warning module. Compared with the existing open-pit mine manual monitoring, it can effectively save labor costs and improve the efficiency of environmental monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the process of the present invention.

[0035] Figure 2 This is a schematic diagram of the image after annotation in step S1.3 of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0037] It should be noted that the open-pit mine environmental monitoring method provided in the embodiment of the present application may be executed by an environmental monitoring system, which may be implemented as part or all of a computer device through software, hardware, or a combination of software and hardware. The computer device may be a server or a terminal, wherein the server mentioned above may refer to a single server or a server cluster composed of multiple servers, and the terminal mentioned above may be a desktop computer, a tablet computer, a laptop computer, or a smart phone, etc. The embodiment of the present application does not limit the specific type of the terminal. In the following method embodiments, the execution subject is a computer device as an example for explanation.

[0038] Example 1

[0039] Please refer to Figure 1 , which shows a flow chart of an open-pit mine environment monitoring method provided by an embodiment of the present application, such as Figure 1 As shown, the open-pit mine environment monitoring method comprises the following steps:

[0040] Step S1, collecting open-pit coal dust images and making them into a data set; part of the data set is used as a training set.

[0041] Step S2: build a YOLO training model, and input the training set into the training model for training to obtain a coal dust recognition model.

[0042] Step S3, collecting images of the position to be detected in real time and filtering out noise in the images.

[0043] Step S4, inputting the image of the position to be detected into the fire coal dust recognition model for recognition, and the fire coal dust recognition model outputs a recognition result, thereby realizing the recognition of fire coal dust.

[0044] Preferably, the step S1 specifically includes the following steps:

[0045] Step S1.1, installing industrial cameras in various corners of the open-pit mine, and using the industrial cameras to obtain on-site videos of the open-pit mine;

[0046] Step S1.2, using the ffmpeg tool to capture the acquired video into frames of images;

[0047] Step S1.3, install the data annotation tool labelme, annotate the coal dust in the image through the visual operation interface, and generate an XML file in VOC format; it should be noted that when annotating the coal dust in the image through the labelme tool, it is necessary to annotate along the edge of the coal dust and mark all the information of the coal dust in the box (such as Figure 2 as shown).

[0048] Step S1.4, use python to convert the annotated file into the txt file format required by the YOLO model; then read all the images and annotation files, and match their file names one by one; randomly divide them into training set, validation set and test set according to 7:2:1. Write the number of nc categories and the file addresses of the training set, validation set and test set in the data.yaml file. Finally, store the completed data set in the server.

[0049] Preferably, the step S2 specifically includes the following steps:

[0050] Step S2.1: Install anaconda on the image computing server, and use anaconda to pull the python library required by the YOLO model in the requirement.txt file. Install cuda and cudnn on the image computing server, configure the environment variables of cuda and cudnn, and use GPU to accelerate the operation of the YOLO model.

[0051] Step S2.2, preprocess the training set: use Mosaic data enhancement to stitch through random scaling, random cropping, and random arrangement, so that the distribution of small targets whose width and height ratio of the target bounding box to the image is less than 0.1 or the square root of the ratio of the target bounding box area to the image area is less than 0.03 is more even.

[0052] Step S2.3, download the pre-trained weights of the YOLO model. Adjust some parameters of the YOLO model multiple times, such as: initial learning rate, final learning rate, warm-up learning rate epoch, learning rate warm-up initial momentum, learning rate warm-up paranoid learning rate. And optimize the network model: select the depth and width of the network model to control the model size. Train the pre-processed data set with the pre-trained weight parameters, and finally obtain the optimal network training weight parameters.

[0053] Preferably, the step S3 specifically includes the following steps:

[0054] Step S3.1, the video data collected from the open-pit mine is transmitted to a multi-channel real-time video analysis system (such as the Deepstream platform) for streaming processing to accelerate the video encoding and decoding process.

[0055] Step S3.2, using OpenCV (Open Source Computer Vision Library) to convert the video data into image data, OpenCV refers to the open source computer vision library.

[0056] Step S3.3, processes the image data of the video frame frame by frame through OpenCV, wherein the image data processing is specifically as follows: first, grayscale the color image of each frame to generate a black and white grayscale image; then, binarize the grayscale image; the purpose of image data processing is to convert the color image into a binary image, in which process the noise in the image is filtered out, so that the boundary between the coal dust and the background in the image data is more obvious; at the same time, some interference factors in the image are filtered out (the threshold is set by setting the binarization function to remove the interference of some factors such as open-pit mines).

[0057] Furthermore, the open-pit mine environment monitoring method of the present invention may also include:

[0058] Step S4, using the laser gimbal to determine the position of the coal dust; specifically, using the angle and acceleration information of the high-precision gyroscope to drive the motor, so that the camera and laser transmitter on the laser gimbal can point and lock the target in the inertial space unchanged, achieving target locking and automatic tracking, thereby locking and tracking the position of the coal dust in real time.

[0059] Furthermore, the open-pit mine environment monitoring method of the present invention may also include:

[0060] Step S5, setting an alarm threshold, when the extracted real-time image shows coal or dust and exceeds the set threshold, an alarm is issued. The alarm function of this method mainly refers to transmitting the image feature information extracted by the computing server to the alarm system, and the alarm system sends an alarm message to the on-site equipment, thereby realizing the alarm function. The specific implementation is as follows: For example, Java is used to process Kafka messages to realize the alarm function, image features are extracted in OpenCV, and the features are transmitted to the Deepstream framework of the multi-channel real-time analysis system. Deepstream sends the features of each frame in the form of a Kafka message sequence to Java for subsequent reasoning. Java processes and feeds back two commands based on the feature information: one is to feed back to Deepstream to save the problematic image; the other is to prompt the on-site equipment whether to alarm.

[0061] Furthermore, the above-mentioned open-pit mine environment monitoring method of the present invention may also include: environmental parameter alarm; specifically, using wireless sensor equipment to monitor other environmental data of the open-pit mine, for example, installing a ZL7000 meteorological sensor, and collecting information of 7 elements including wind speed, wind direction, atmospheric pressure, atmospheric temperature, relative humidity, rainfall and total solar radiation at the mine site through the meteorological sensor. The ZL7000 meteorological sensor is divided into two modes: broadcast mode and question-and-answer mode. The broadcast mode sends real-time meteorological information data, and the question-and-answer mode can output meteorological data within a specified interval according to demand. For another example, a shutter box all-in-one sensor is installed, and a total of 3 environmental information items including noise, PM2.5 and PM10 are obtained through the shutter box all-in-one sensor. Using a shutter box plastic disc to combine multiple sensors can effectively cope with extreme climatic conditions. First, the register address of each sensor is configured, and then the real-time value of each sensor can be obtained by reading the value of the Modbus register address, and one or more register values ​​can be read each time.

[0062] The specific mining environment data values ​​are measured by the above two sensors, and the various values ​​are transmitted to the server through the 4G Internet of Things traffic card.

[0063] Furthermore, the present invention monitors the mine environment through a background management system. The multivariate data of the environmental monitoring system and the machine vision monitoring system are used to form a system environmental monitoring network in the mine, and the basic pollution characteristics of noise, temperature, and wind in the mine environment are identified, providing a basic monitoring technology solution for the next step of environmental governance.

[0064] The environmental monitoring management system conducts comprehensive statistics on wind speed, wind direction, atmospheric pressure, atmospheric temperature, relative humidity, rainfall, total solar radiation, noise, PM2.5, PM10 and other sensor data monitored by fixed and mobile environmental monitoring base stations. The statistics of information mainly include the following statistical functions: ① Statistical query of high-precision meteorological information of three elements (temperature, humidity, air pressure) and five elements (temperature, humidity, wind speed, wind direction, rainfall) in the daily, monthly and annual dimensions; ② Statistical query of high-precision meteorological information of 8 elements in the next 24 hours; ③ Query the noise, temperature, wind force and other meteorological data of fixed and mobile single base stations.

[0065] The machine vision monitoring system mainly displays the coal dust identified by the Deepstream real-time video stream artificial intelligence analysis platform, YOLO target detection model system, and image recognition algorithm system in real time.

[0066] The backend management system mainly includes user management, authority management, data management, system management, configuration management of environmental monitoring base stations and visual recognition monitoring. User management mainly provides the functions of adding, modifying, deleting and viewing users of the system to the relevant departments and business personnel involved in the enterprise. The authority management system mainly manages the authority of system users, and the authority is mainly divided into super administrators, system administrators, department administrators, and ordinary users. Super administrators and system administrators can add, modify and delete the authority of ordinary users, and the authority modification and deletion records will be stored in the system log. System management mainly includes the management of system menus, data backup, log records, data import and export and other functions. Add, modify and delete operations will be recorded in the log system.

[0067] The environmental monitoring base station configuration management function is mainly to provide basic configuration expansion management functions for adding fixed or mobile environmental monitoring base stations in the future. In addition, it can also modify the existing fixed or mobile environmental monitoring base stations. This configuration management function can only be operated by super administrators, and non-professional staff have no authority to operate it. At the same time, the operation records will also be recorded in the log system.

[0068] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed 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 part of the steps or stages in other steps.

[0069] Example 2

[0070] Based on the same inventive concept, the embodiment of the present application also provides an environmental monitoring system for implementing the open-pit mine environmental monitoring method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more environmental monitoring system embodiments provided below can refer to the limitations of the open-pit mine environmental monitoring method above, and will not be repeated here.

[0071] In one embodiment, an environmental monitoring system includes:

[0072] The acquisition module is used to collect open-pit mine coal dust images and make them into a data set; part of the data set is used as a training set.

[0073] The training module is used to build the YOLO training model and input the training set into the training model for training to obtain a coal dust recognition model.

[0074] The real-time acquisition module is used to acquire the image of the position to be detected in real time and filter out the noise in the image.

[0075] The recognition module is used to input the image of the position to be detected into the fire coal dust recognition model for recognition, and the fire coal dust recognition model outputs the recognition result, thereby realizing the recognition of fire coal dust.

[0076] Furthermore, the above-mentioned open-pit mine environment monitoring system of the present invention can also include: a coal dust position positioning module, which uses a laser pan-tilt head to determine the position of the coal dust; specifically, the angle and acceleration information of the high-precision gyroscope is used to drive the motor, so that the direction and locking target of the camera and laser transmitter carried on the laser pan-tilt head remain unchanged in the inertial space, achieving target locking and automatic tracking, thereby locking and tracking the position of the coal dust in real time.

[0077] Furthermore, the above-mentioned open-pit mine environment monitoring system of the present invention may also include: a coal fire and dust monitoring alarm module; used to set an alarm threshold, and when coal fire or dust appears in the extracted real-time image and exceeds the set threshold, an alarm is issued. The alarm function of this method mainly refers to transmitting the image feature information extracted by the operation server to the alarm system, and the alarm system sends an alarm message to the on-site equipment, thereby realizing the alarm function. The specific implementation is as follows: For example, Java is used to process Kafka messages to realize the alarm function, image features are extracted in OpenCV, and the features are transmitted to the Deepstream framework of the multi-channel real-time analysis system. Deepstream sends the features of each frame in the form of a Kafka message sequence to Java for subsequent reasoning. Java processes and feeds back two commands based on the feature information: one is to feed back to Deepstream to save the problematic image; the other is to prompt the on-site equipment whether to alarm.

[0078] Furthermore, the open-pit mine environment monitoring system of the present invention may also include: an environmental parameter alarm module; specifically, a wireless sensor device is used to monitor other environmental data of the open-pit mine, and an alarm threshold is set, and an alarm is issued when the detected environmental data exceeds the set threshold.

[0079] Each module in the above-mentioned environment monitoring system can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0080] In one embodiment, a computer device is provided, which may be a server. The computer device includes a processor, a memory, and a network interface connected via 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 network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a space division method is implemented.

[0081] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed 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 the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can 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 can include random access memory (RAM) or external cache memory, etc. As an 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 each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0082] The technical features of the above embodiments may 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.

[0083] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring an open-pit mine environment, characterized in that: The method comprises: Step S1, collecting open-pit coal dust images and making them into a data set; part of the data set is used as a training set; The step S1 comprises the following steps: Step S1.1, obtaining an open-pit mine on-site video; Step S1.2, using the ffmpeg tool to capture the acquired video into frames of images; Step S1.3, use the data annotation tool labelme to annotate the coal dust in the image and generate an xml file in VOC format; Step S1.4, use Python to convert the annotated file into the txt file format required by the YOLO model; then read all the images and annotation files, and match their file names one by one; randomly divide them into training set, validation set and test set according to 7:2:1; write the nc category number and the file address of the training set, validation set and test set under the data.yaml file; finally, store the completed data set in the server; Step S2, building a YOLO training model, and inputting the training set into the training model for training to obtain a coal dust recognition model; The step S2 comprises the following steps: Step S2.1, use anaconda on the image computing server to pull the python library required by the YOLO model in the requirement.txt file; install cuda and cudnn on the image computing server, configure the environment variables of cuda and cudnn, and use GPU to accelerate the operation of the YOLO model; Step S2.2, preprocessing the training set: using Mosaic data enhancement to stitch through random scaling, random cropping, and random arrangement, so that the ratio of the width and height of the target bounding box to the width and height of the image is less than 0.1 or the square root of the ratio of the area of ​​the target bounding box to the area of ​​the image is less than 0.

03. Step S2.3, download the pre-trained weights of the YOLO model; adjust the parameters of the YOLO model multiple times; optimize the network model: select the depth and width of the network model to control the model size; train the pre-processed data set through the pre-trained weight parameters, and finally obtain the optimal network training weight parameters; Step S3, collecting an image of the position to be detected in real time and filtering out noise in the image; The step S3 comprises the following steps: Step S3.1, transmitting the video data collected from the open-pit mine to a multi-channel real-time video analysis system for streaming processing to accelerate the video encoding and decoding process; Step S3.2, using OpenCV to convert video data into image data; Step S3.3, processing the image data of the video frame frame by frame through OpenCV, wherein the image data processing is specifically as follows: first, grayscale processing is performed on each frame of the image to generate a black and white grayscale image; then, the grayscale image is binarized; the purpose of the image data processing is to convert the color image into a binary image, in which process the noise in the image is filtered out, so that the boundary between the coal dust and the background in the image data is more obvious; at the same time, some interference factors in the image are filtered out; Step S4, inputting the image of the position to be detected into the coal dust recognition model for recognition, and the coal dust recognition model outputs the recognition result, thereby realizing the recognition of coal dust; using the laser pan-tilt to determine the position of the coal dust; specifically, using the angle and acceleration information of the high-precision gyroscope to drive the motor, so that the camera and laser transmitter carried on the laser pan-tilt can point to and lock the target in the inertial space unchanged, realizing target locking and automatic tracking, thereby locking and tracking the position of the coal dust in real time.

2. The open-pit mine environment monitoring method according to claim 1, characterized in that: The method further includes step S5 of setting an alarm threshold value, and when coal or dust appears in the extracted real-time image and exceeds the set threshold value, an alarm is issued.

3. The open-pit mine environment monitoring method according to claim 1, characterized in that: It also includes environmental parameter alarms; using wireless sensor equipment to monitor other environmental data of the open-pit mine, sending various values ​​to the server via wireless transmission, setting alarm thresholds, and issuing alarms when the detected environmental data exceeds the set thresholds.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

5. 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 3 are implemented.

Images