Safety early warning method, device and electronic equipment

Abstract

A safety warning method, device and electronic equipment relate to the field of data processing. In the method, multiple mining area images of a mining area are obtained; personnel features and vehicle features in the mining area images are extracted; the corresponding target personnel objects are determined according to the personnel features, and the corresponding target vehicle objects are determined according to the vehicle features; based on the warning objects in each preset warning scene, the personnel warning area and the vehicle warning area are determined; the corresponding personnel running trajectory is determined, and the vehicle running trajectory is determined; the personnel running trajectory is matched with the personnel warning area, and it is determined whether the personnel object enters the personnel warning area, and whether the vehicle object enters the vehicle warning area; if it is determined that the personnel object enters the personnel warning area or the vehicle object enters the vehicle warning area, a warning message is sent to the warning management platform. The technical solution provided by the present application is implemented to realize real-time monitoring and warning of personnel and vehicles in the mining area, and improve the efficiency of supervision.

Description

Technical Field

[0001] The present application relates to the field of data processing, and specifically to a security warning method, device and electronic equipment. Background Art

[0002] With the continuous expansion of mining scale and the increasing complexity of the operating environment, mining safety production faces more and more risks and challenges. Improper behavior and illegal operations of personnel and vehicles in mining areas, such as crossing the boundary and entering dangerous areas, have become one of the main causes of safety accidents.

[0003] At present, the safety management of relevant mining areas mainly relies on manual inspections. Once a safety accident occurs, it is often difficult to detect and control it in the first place. Therefore, there are problems in the relevant technologies such as slow response speed and untimely warning, which leads to low supervision efficiency.

[0004] Therefore, there is an urgent need for a safety early warning method, device and electronic equipment. Summary of the invention

[0005] The present application provides a safety warning method, device and electronic equipment to achieve real-time monitoring and warning of personnel and vehicles in mining areas, thereby improving supervision efficiency.

[0006] In a first aspect of the present application, a safety warning method is provided, the method comprising: acquiring multiple mining area images of a mining area; extracting personnel features and vehicle features in the mining area images; determining a corresponding target personnel object according to the personnel features, and determining a corresponding target vehicle object according to the vehicle features; acquiring a preset warning scene in the mining area, the preset warning scene comprising a warning period, a warning object and a warning area, the warning object comprising a personnel object and a vehicle object; based on the warning objects in each of the preset warning scenes, determining a personnel warning area for the target personnel object and a vehicle warning area for the target vehicle object; determining a corresponding personnel running trajectory according to the personnel features, and determining a vehicle running trajectory according to the vehicle features; matching the personnel running trajectory with the personnel warning area to determine whether the personnel object enters the personnel warning area, and matching the vehicle running trajectory with the vehicle warning area to determine whether the vehicle object enters the vehicle warning area; if it is determined that the personnel object enters the personnel warning area or the vehicle object enters the vehicle warning area, sending a warning message to a warning management platform.

[0007] By adopting the above technical solution, by acquiring the mine area image, extracting the personnel characteristics and vehicle characteristics, determining the target personnel object and the target vehicle object, obtaining the preset warning scene, determining the personnel warning area and the vehicle warning area, and matching the personnel running trajectory and the vehicle running trajectory with the warning area, it is judged whether to enter the warning area, thereby realizing real-time monitoring and early warning of personnel and vehicles in the mine area. This method can automatically and timely discover the abnormal behavior and location of personnel and vehicles without manual duty and judgment, thereby improving the efficiency and accuracy of early warning. At the same time, by presetting different early warning scenes and early warning areas, more refined and personalized safety management can be achieved for different risk factors and working environments, reducing accident hazards and losses. When the early warning situation is detected, the early warning information is quickly sent to the management platform to maximize the real-time and accuracy of the mine operation and improve the supervision efficiency.

[0008] Optionally, the extracting of personnel features and vehicle features in the mining area image specifically includes: performing a preprocessing operation on the mining area image to obtain a target mining area image, the preprocessing operation including image denoising and image enhancement; performing target detection on the target mining area image using a target detection algorithm to obtain personnel objects and vehicle objects; extracting personnel position coordinates and appearance features corresponding to the personnel objects as the personnel features, and extracting vehicle position coordinates and license plate numbers corresponding to the vehicle objects as vehicle features.

[0009] By adopting the above technical solution, the quality and clarity of the mining area images can be improved by preprocessing the mining area images with image denoising and image enhancement, providing more accurate and reliable input data for subsequent target detection and feature extraction. The target detection algorithm is used to analyze the preprocessed target mining area images, and the personnel objects and vehicle objects in the mining area images are automatically identified without manual labeling and intervention, which greatly improves efficiency and accuracy. By extracting the personnel position coordinates and appearance features of the personnel objects, the real-time position of the personnel objects in the mining area can be accurately located, and identity recognition and behavior analysis can be performed through appearance features. By extracting the vehicle position coordinates and license plate number of the vehicle object, the running trajectory of the vehicle in the mining area can be tracked in real time, and the vehicle can be identified according to the license plate number. These extracted feature information provides key data support for subsequent target tracking, trajectory analysis, and early warning judgment links, and is the basis for realizing intelligent and precise safety early warning.

[0010] Optionally, determining the corresponding target person object based on the personnel characteristics, and determining the corresponding target vehicle object based on the vehicle characteristics, specifically includes: performing cluster analysis on the personnel characteristics to form different personnel clusters; performing identity recognition on each of the personnel clusters, and comparing through a preset personnel identity feature library to determine the target person object corresponding to the personnel cluster; matching the vehicle characteristics with a preset vehicle information library to obtain the target vehicle object corresponding to the vehicle characteristics.

[0011] By adopting the above technical solution, through cluster analysis of the extracted personnel features, multiple features of the same person photographed at different times and locations can be classified to form a complete personnel identity and behavior trajectory. The clustered personnel identity is identified and compared with the preset personnel identity feature library to quickly and accurately determine the true identity of the personnel, verify their authority in the mining area, and provide reliable identity information for subsequent behavior analysis and early warning judgment. By matching the extracted vehicle features with the preset vehicle information library, the vehicle can be identified and verified from the license plate number to ensure the legality and safety of the vehicle, and prevent illegal or illegal vehicles from entering the mining area and causing potential accidents. At the same time, through the confirmation of vehicle identity, it also provides a reliable data basis for subsequent vehicle trajectory tracking and behavior analysis.

[0012] Optionally, based on the warning objects in each of the preset warning scenarios, determining a personnel warning area for the target personnel object and a vehicle warning area for the target vehicle object specifically includes: judging whether the current time is within the warning period; if it is determined that the current time is within the warning period, obtaining an electronic map of the mining area; marking the warning areas of the warning objects in each of the preset warning scenarios on the electronic map; matching the personnel position coordinates and the vehicle position coordinates with the warning areas respectively, to obtain the personnel warning area and the vehicle warning area.

[0013] By adopting the above technical solution, by specifying the warning area on the electronic map and combining it with real-time location data, this method can efficiently monitor and manage dynamic changes in the mining area. This visual processing method not only enables monitoring personnel to quickly understand the safety situation of the site, but also helps to automatically perform monitoring tasks and reduce human monitoring errors. By judging in real time whether people and vehicles are in the warning area, potential risks and violations can be discovered at the first time, and timely responses can be made to achieve flexible and efficient safety management.

[0014] Optionally, matching the personnel running trajectory with the personnel warning area to determine whether the personnel object has entered the personnel warning area specifically includes: determining whether the personnel running trajectory overlaps or intersects with the personnel warning area; if the personnel running trajectory overlaps or intersects with the personnel warning area, determining that the personnel object has entered the personnel warning area.

[0015] By adopting the above technical solution, by judging whether the personnel's running trajectory overlaps or intersects with the personnel warning area, it is possible to accurately judge whether the personnel has entered a dangerous area or a restricted area. This real-time, dynamic trajectory warning method can minimize the personnel's risk exposure time and the probability of accidents, and improve the pertinence and effectiveness of safety management.

[0016] Optionally, the acquiring of multiple mining area images includes: acquiring a current ambient light value; determining whether the current ambient light value is greater than a preset light threshold; if it is determined that the current ambient light value is greater than the preset light threshold, acquiring multiple mining area images in the form of visible light images; if it is determined that the current ambient light value is less than or equal to the preset light threshold, acquiring multiple mining area images in the form of infrared images.

[0017] By adopting the above technical solution, by obtaining the current ambient light value and comparing it with the preset light threshold, the mining area image acquisition mode can be adaptively selected according to the actual environmental conditions. In the case of sufficient light, the visible light image can obtain clear and colorful mining area scene information, which is convenient for the identification and tracking of personnel and vehicles. In the case of insufficient light or at night, switch to the infrared image mode, and use infrared thermal imaging technology to capture the thermal radiation signals of personnel and vehicles to achieve target detection and tracking under low light or no light conditions. This adaptive image acquisition method can ensure that high-quality and usable mining area image data can be obtained under different lighting conditions.

[0018] Optionally, determining the corresponding personnel movement trajectory based on the personnel characteristics specifically includes: tracking the target personnel object in multiple images of the mining area; obtaining the position coordinates of the target personnel object at different times; generating a motion path of the target personnel object based on the position coordinates of the target personnel object at different times; smoothing the motion path to remove noise and abnormal points in the motion path to obtain the personnel movement trajectory.

[0019] By adopting the above technical solution, by tracking the target personnel object in continuous mining area images, the position coordinates of the target personnel object at different times can be obtained to form a complete motion trajectory. This continuous tracking and position extraction method can truly and accurately reflect the movement process and behavior characteristics of personnel in the mining area scene, providing a reliable data basis for subsequent trajectory analysis and early warning judgment.

[0020] In a second aspect of the present application, a safety warning device is provided, which includes: an acquisition module and a processing module, wherein: the acquisition module is used to acquire multiple mining area images of a mining area; the processing module is used to extract personnel features and vehicle features in the mining area images; the processing module is also used to determine the corresponding target personnel object according to the personnel features, and determine the corresponding target vehicle object according to the vehicle features; the acquisition module is also used to acquire preset warning scenes in the mining area, the preset warning scenes include warning time periods, warning objects and warning areas, and the warning objects include personnel objects and vehicle objects; the processing module is also used to determine the warning objects for the preset warning scenes based on the warning objects in each of the preset warning scenes. The processing module is further used to determine the corresponding personnel running trajectory according to the personnel characteristics, and to determine the vehicle running trajectory according to the vehicle characteristics; the processing module is further used to match the personnel running trajectory with the personnel warning area to determine whether the personnel object enters the personnel warning area, and to match the vehicle running trajectory with the vehicle warning area to determine whether the vehicle object enters the vehicle warning area; the processing module is further used to send warning information to the warning management platform if it is determined that the personnel object enters the personnel warning area or the vehicle object enters the vehicle warning area.

[0021] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By acquiring images of the mining area, extracting personnel and vehicle features, determining the target personnel and vehicle objects, obtaining preset warning scenarios, determining personnel warning areas and vehicle warning areas, and matching personnel and vehicle running trajectories with warning areas, it is determined whether to enter the warning area, thereby achieving real-time monitoring and early warning of personnel and vehicles in the mining area. This method can automatically and timely detect abnormal behaviors and locations of personnel and vehicles without manual duty and judgment, thereby improving the efficiency and accuracy of early warning. At the same time, by presetting different early warning scenarios and early warning areas, more refined and personalized safety management can be achieved for different risk factors and operating environments, reducing accident hazards and losses. When an early warning situation is detected, the early warning information is quickly sent to the management platform to maximize the safety and continuity of mining operations.

[0024] 2. By preprocessing the mining area images with image denoising and image enhancement, the quality and clarity of the mining area images can be improved, providing more accurate and reliable input data for subsequent target detection and feature extraction. The target detection algorithm is used to analyze the preprocessed target mining area images, and the personnel and vehicle objects in the mining area images are automatically identified without manual labeling and intervention, which greatly improves efficiency and accuracy. By extracting the personnel position coordinates and appearance features of the personnel objects, the real-time position of the personnel objects in the mining area can be accurately located, and identity recognition and behavior analysis can be performed through appearance features. By extracting the vehicle position coordinates and license plate number of the vehicle object, the running trajectory of the vehicle in the mining area can be tracked in real time, and the vehicle can be identified according to the license plate number. These extracted feature information provides key data support for subsequent target tracking, trajectory analysis, and early warning judgment links, and is the basis for realizing intelligent and precise safety early warning.

[0025] 3. By clustering the extracted personnel features, multiple features of the same person photographed at different times and locations can be classified to form a complete personnel identity and behavior trajectory. By identifying the clustered personnel identity and comparing it with the preset personnel identity feature library, the true identity of the person can be quickly and accurately determined, and their authority in the mining area can be verified, providing reliable identity information for subsequent behavior analysis and early warning judgment. By matching the extracted vehicle features with the preset vehicle information library, the vehicle can be identified and verified from the license plate number to ensure the legality and safety of the vehicle, and prevent illegal or illegal vehicles from entering the mining area and causing potential accidents. At the same time, through the confirmation of vehicle identity, it also provides a reliable data basis for subsequent vehicle trajectory tracking and behavior analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flowchart of a safety warning method disclosed in an embodiment of the present application; Figure 2 It is a module schematic diagram of a safety warning device disclosed in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0027] Explanation of the reference numerals: 201, acquisition module; 202, processing module; 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0028] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0029] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0030] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0031] This application provides a safety warning method, referring to Figure 1 , Figure 1 1 is a flow chart of a security warning method provided in an embodiment of the present application. The method is applied to a server and includes steps S101 to S108, which are as follows: Step S101: Acquire multiple mining area images of a mining area.

[0032] In step S101, the current ambient light value is obtained; it is determined whether the current ambient light value is greater than a preset light threshold; if it is determined that the current ambient light value is greater than the preset light threshold, multiple images of the mining area in the form of visible light images are obtained; if it is determined that the current ambient light value is less than or equal to the preset light threshold, multiple images of the mining area in the form of infrared images are obtained.

[0033] Specifically, the server obtains the real-time ambient light value of the mining area, and the server communicates with the light sensor arranged in the mining area to receive the ambient light data collected by the light sensor in real time. After receiving the ambient light data sent by the light sensor, the server will parse and process the ambient light data to extract the current ambient light value. The current ambient light value is a number that represents the average light intensity of the current mining area. The server compares the current ambient light value with the preset light threshold. The preset light threshold is a reference value set according to the actual situation of the mining area and the image acquisition requirements, and is used to determine whether the current lighting conditions are suitable for collecting visible light images or infrared images. The preset light threshold can be determined through experimental testing and data analysis to ensure that clear and effective mining area images are obtained under different lighting conditions. This application does not limit this.

[0034] If the server determines that the current ambient light value is greater than the preset light threshold, it means that the light conditions in the current mining area are good and suitable for collecting visible light images. The server will then send instructions to the visible light camera, asking the camera to capture visible light images of the mining area and upload them to the server. The visible light camera is installed at a fixed location in the mining area or on a mobile device, and captures mining scene images within the visible spectrum through an optical lens and an image sensor. The captured visible light image is stored and transmitted in the form of a digital image file (such as JPEG, PNG, etc.). On the contrary, if the server determines that the current ambient light value is less than or equal to the preset light threshold, it means that the light in the current mining area is dark and the quality of the visible light image may be poor. At this time, the server will instead send instructions to the infrared camera to collect infrared images of the mining area. The infrared camera uses infrared thermal imaging technology to capture infrared radiation emitted or reflected by an object to form an image reflecting the temperature distribution of the object. In an environment with insufficient light, infrared images can provide clearer and more effective mining scene information.

[0035] For example, suppose the preset light threshold of an open-pit coal mine is set to 500 lux. When the light intensity in the mine reaches 800 lux during the day, the server will trigger the visible light camera to collect images; at night or in dark weather, when the light intensity drops to 300 lux, the server will switch to the infrared camera for image collection.

[0036] Step S102: extracting personnel features and vehicle features in the mining area image.

[0037] In step S102, a preprocessing operation is performed on the mining area image to obtain a target mining area image, wherein the preprocessing operation includes image denoising and image enhancement; a target detection algorithm is used to perform target detection on the target mining area image to obtain personnel objects and vehicle objects; the personnel position coordinates and appearance features corresponding to the personnel objects are extracted as the personnel features, and the vehicle position coordinates and license plate numbers corresponding to the vehicle objects are extracted as the vehicle features.

[0038] Specifically, the server performs preprocessing operations on the received mining area images to improve the image quality and create favorable conditions for subsequent target detection and feature extraction. The preprocessing operation mainly includes two aspects: image denoising and image enhancement. Image denoising refers to removing noise interference in the image, such as random noise or background noise introduced by sensor errors and environmental factors. The denoising methods used by the server include median filtering, Gaussian filtering, and wavelet transform. The server can reduce the impact of noise on target detection and feature extraction by smoothing and denoising the mining area images. The server uses image enhancement technology including histogram equalization, which can improve the accuracy of target detection and feature extraction by optimizing the visual effect of the mining area images. The target mining area image obtained after preprocessing will be input into the target detection algorithm for processing. The target detection algorithm can automatically identify and locate the target object from the target mining area image. The server uses Faster R-CNN and YOLO target detection algorithms to scan and analyze the target mining area image and identify the personnel and vehicle objects in the target mining area image. After identifying the personnel and vehicle objects, the server will further extract their feature information. For personnel objects, the server will record their location coordinates to indicate their spatial location in the mining area; at the same time, it will extract the appearance features of the personnel, such as body size and facial features, for subsequent personnel tracking and identification. For vehicle objects, in addition to recording their location coordinates, the server will also identify and extract the license plate number information. The license plate number is an important feature that uniquely identifies a vehicle. By performing character segmentation and recognition on the image of the license plate area, the vehicle's license plate number can be accurately obtained.

[0039] For example, suppose the server receives a visible light image of an open-pit coal mine. After preprocessing, the people and vehicles in the image become clearer and more prominent. The server then uses the Faster R-CNN algorithm to detect objects in the image and identifies three workers and two excavators in the image. For each person object, the server records its location coordinates and extracts appearance features such as clothing color (such as red overalls) and body size; for each excavator, the server records its location coordinates and identifies the license plate number.

[0040] Step S103: determining a corresponding target person object according to the person characteristics, and determining a corresponding target vehicle object according to the vehicle characteristics.

[0041] In step S103, the personnel features are clustered and analyzed to form different personnel clusters; identity recognition is performed on each of the personnel clusters, and a comparison is performed through a preset personnel identity feature library to determine the target personnel object corresponding to the personnel cluster; the vehicle features are matched with a preset vehicle information library to obtain the target vehicle object corresponding to the vehicle features.

[0042] Specifically, for personnel features, the server first performs cluster analysis on them. The server uses the extracted personnel features (such as appearance features) as data objects, calculates the similarity between personnel features (such as Euclidean distance, cosine similarity), and uses the K-means clustering algorithm to aggregate personnel features with high similarity together to form different personnel clusters. Through cluster analysis, the server can preliminarily divide the personnel in the mining area image into different individuals or groups. The server performs identity recognition on each personnel cluster, and identity recognition refers to determining the specific identity of the personnel represented by the personnel cluster. A preset personnel identity feature library is pre-built inside the server, and the preset personnel identity feature library stores the identity information and feature representations (such as facial feature vectors, appearance feature vectors, etc.) of all relevant personnel in the mining area. During recognition, the server compares the personnel features of the personnel cluster with the records in the preset personnel identity feature library one by one, and calculates the similarity between the personnel features and the features in the preset personnel identity feature library. If it is determined that the similarity between the personnel features of a certain personnel cluster and the features of a certain person in the preset personnel identity feature library is greater than the preset similarity threshold, the server will identify the personnel cluster as the corresponding personnel identity. The preset similarity threshold can be set according to actual needs, and this application does not limit this.

[0043] For vehicle features, the server's processing flow is similar to that of personnel features. The server will match the extracted vehicle features (mainly license plate numbers) with the preset vehicle information database. The preset vehicle information database stores the basic information of all vehicles in the mining area, such as license plate numbers and vehicle models. The server will compare the extracted license plate numbers with the records in the preset vehicle information database one by one. If a completely consistent record is found, the vehicle feature can be identified as the corresponding target vehicle object.

[0044] For example, the server performs cluster analysis on the personnel features in a certain frame of the mining area image and obtains three personnel clusters A, B, and C. Then, the server compares the personnel features of these three personnel clusters with the preset personnel identity feature library and finds that personnel cluster A highly matches "Zhang San" in the preset personnel identity feature library, personnel cluster B matches "Li Si", and personnel cluster C is a stranger. Therefore, the server identifies personnel cluster A as the target personnel object "Zhang San", personnel cluster B as "Li Si", and personnel cluster C is marked as "unknown person". For vehicle features, the server extracts the license plate number and matches it with the preset vehicle information library. It is found that the license plate number corresponds to an excavator belonging to the production department, so it is identified as the target vehicle object.

[0045] Step S104: obtaining a preset warning scenario in the mine area, wherein the preset warning scenario includes a warning period, a warning object, and a warning area, and the warning object includes a personnel object and a vehicle object.

[0046] In step S104, the server needs to obtain the pre-set warning scene information in the mine area, including the warning period, warning object and warning area. The preset warning scene is defined and configured in advance by managers or experts according to the actual situation of the mine operation and the safety management requirements, and is intended to focus on monitoring and warning for specific time periods and objects. A warning scene configuration database or file is pre-set inside the server, and the database or file stores various warning scene definitions in the mine area. Each warning scene usually contains two key elements: the warning period and the warning object. The warning period refers to a specific time range that needs to be monitored, which can be a certain time period of the day (such as 2 am to 4 am) or certain dates in a week or month (such as every Saturday or the 1st of each month). The setting of the warning period takes into account the actual arrangement of mine operations, personnel shifts, and equipment maintenance factors, corresponding to some time windows with higher safety risks or fewer personnel. The server reads the warning period information in the warning scene and converts it into a time format that can be recognized by the computer. The warning object refers to the type of personnel or vehicle that needs to be monitored. For personnel objects, warning objects can be set according to the identity and role attributes of the personnel, such as "outsiders", "temporary workers", "maintenance personnel", etc. For vehicle objects, warning objects can be set according to the type, purpose, driving route and other attributes of the vehicle, such as "large mining trucks", "private cars", "blasting vehicles", etc. The server will read the warning object information in the warning scene and match it with the previously identified target personnel objects and target vehicle objects. The warning area refers to the specific area range that needs to be monitored, which is usually marked and defined on the electronic map of the mining area. The warning area can be one or more rectangular, polygonal, circular and other shaped areas, corresponding to certain specific locations or places in the mining area, such as mining areas, blasting areas, and dangerous areas. The server will read the warning area information in the warning scene, including the location coordinates and boundary description of the area, and use this area information in subsequent location matching and risk judgment.

[0047] For example, assume that there are three preset warning scenarios in the mining area: Warning period: 2:00 a.m. to 4:00 a.m. every day; Warning targets: all personnel and vehicles; Warning area: the entire mining area.

[0048] Warning period: all day every Saturday; Warning targets: outsiders and private cars; Warning areas: mine entrances and exits and parking lots.

[0049] Warning period: 9:00 to 11:00 a.m. on the 1st of each month; Warning targets: blasting vehicles; Warning areas: blasting operation areas.

[0050] Step S105: Based on the warning objects in each of the preset warning scenarios, a person warning area for the target person object and a vehicle warning area for the target vehicle object are determined.

[0051] In step S105, determine whether the current time is within the warning period; if it is determined that the current time is within the warning period, obtain an electronic map of the mining area; mark the warning areas of the warning objects in each of the preset warning scenarios on the electronic map; match the personnel position coordinates and the vehicle position coordinates with the warning areas respectively to obtain the personnel warning area and the vehicle warning area.

[0052] Specifically, the server will obtain the current time information in real time and compare it with the warning period in the preset warning scenario. The server will convert the current time into a specific time format (such as a Unix timestamp or date and time string), and then compare it with the start and end time of the warning period. If the current time falls within a warning period, it means that it is currently in a time window that requires key monitoring, and the server will trigger the subsequent warning area determination process; if the current time is not within any warning period, the server can temporarily ignore the judgment of the warning area and perform other monitoring tasks instead.

[0053] Once it is determined that the current time is within the warning period, the server will obtain an electronic map of the mining area from the database or file system. Electronic maps are usually stored in a digital form and contain the geographical information, topography, and road construction elements of the mining area. The server will locate the corresponding mining area on the electronic map based on the location information in the warning scene (such as the location coordinates of personnel and vehicles).

[0054] The server will mark the warning areas of the warning objects in each warning scenario on the electronic map. Since the definition of the warning scenario in step S104 already includes the information of the warning area, the server can directly extract the location coordinates and boundary descriptions of these warning areas and visually mark them on the electronic map. For example, for the warning objects "outsiders" and "private cars" in warning scenario 2, their warning areas are "mine entrance and exit" and "parking lot". The server will draw the boundaries of these two areas at the corresponding positions on the electronic map and mark them with different colors or patterns to distinguish them from other areas.

[0055] Finally, the server will match the position coordinates of the target person object and the target vehicle object with the warning area. The server will read the person position coordinates of each target person object and the vehicle position coordinates of each target vehicle object tracked in real time, and then compare the spatial positions of these coordinate points with the boundaries of the warning area. If the coordinate points of a person or vehicle fall within a warning area, it means that the person or vehicle is currently in an area that needs to be monitored. The server will mark it as being in a warning state and generate corresponding warning information (such as warning object ID, warning time, warning area, etc.); if the coordinate points of a person or vehicle are not in any warning area, it means that it is not currently within the key monitoring range, and the server can temporarily ignore its warning state.

[0056] Step S106: Determine the corresponding personnel running trajectory according to the personnel characteristics, and determine the vehicle running trajectory according to the vehicle characteristics.

[0057] In step S106, the target personnel object is tracked in multiple images of the mining area; the position coordinates of the target personnel object at different times are obtained; the motion path of the target personnel object is generated according to the position coordinates of the target personnel object at different times; the motion path is smoothed to remove noise and abnormal points in the motion path to obtain the movement trajectory of the personnel.

[0058] Specifically, the server determines the corresponding personnel running trajectory and vehicle running trajectory respectively according to the personnel characteristics and vehicle characteristics. For the determination of the personnel running trajectory, the server first needs to track the target personnel object in multiple continuous mining area images. Since the video surveillance system usually collects images at a certain frame rate (such as 25 frames per second), the server can obtain a series of time-continuous mining area images. The server will use the target tracking algorithm (such as Kalman filter, particle filter) to track each target personnel object frame by frame in these mining area images. During the tracking process, the server will obtain the pixel coordinates (U, V) of the target personnel object in each frame of the image in real time. These pixel coordinates are expressed in the form of an image coordinate system, and the server will record them to form a time series of position coordinate data. For example, the position coordinates of the target personnel object "Zhang San" in 100 consecutive frames of images may be: (100, 200), (105, 203), (110, 205), ..., (150, 220).

[0059] Since the mining area image is a two-dimensional projection of three-dimensional space, the pixel coordinates cannot directly represent the position of the target personnel object in the actual space. In order to convert the pixel coordinates into three-dimensional space coordinates (X, Y, Z), the server combines the internal and external parameters and depth information of the camera, and uses binocular vision ranging, structured light ranging, laser ranging and other algorithms for coordinate conversion. By analyzing the parallax information of multiple cameras or actively projecting light, the depth distance D between the target personnel object and the camera is obtained. Then, the server can convert the pixel coordinates (U, V) and depth distance D into three-dimensional space coordinates (X, Y, Z) based on the internal parameter matrix and external parameter matrix of the camera. The conversion formula is as follows: [X, Y, Z, 1]=inv(R)*inv(K)*[U, V, 1]*D Among them, K is the intrinsic parameter matrix of the camera, which contains the focal length and principal point coordinate information; R is the extrinsic parameter matrix of the camera, which contains the rotation and translation information of the camera; inv() represents the matrix inversion operation.

[0060] Through coordinate conversion, the server can obtain the three-dimensional spatial coordinates (X, Y, Z) of the target person object in each frame of the mining area image. These coordinates are connected in time sequence to form the movement path of the target person object. For example, the movement path of the target person "Zhang San" in 100 consecutive frames of images may be: (X1, Y1, Z1), (X2, Y2, Z2), ..., (X100, Y100, Z100).

[0061] According to the acquired position coordinate time series, the server can generate the motion path of the target personnel object. The motion path is a trajectory curve formed by connecting a series of position coordinate points in chronological order, which reflects the movement process of the target personnel in the mining area. The server will connect the points in the position coordinate sequence in chronological order to form a continuous motion path. Since there may be certain errors and noise in the image acquisition, target detection and tracking process, the generated motion path may have some abnormal points or jagged fluctuations. In order to obtain a smoother and more accurate personnel movement trajectory, the server also needs to smooth the motion path. The server uses the moving average filtering method to remove noise and abnormal points in the trajectory by performing local averaging, weighted smoothing or curve fitting on the position coordinate points on the motion path, and obtain a smooth and continuous personnel movement trajectory.

[0062] The server's processing flow for determining the vehicle's trajectory is the same as that for the personnel's trajectory. The server also needs to track the target vehicle object in the continuous mining area images, obtain its position coordinate sequence, generate the motion path, and perform trajectory smoothing to finally obtain a smooth and continuous vehicle trajectory.

[0063] Step S107: Match the personnel running trajectory with the personnel warning area to determine whether the personnel object enters the personnel warning area, and match the vehicle running trajectory with the vehicle warning area to determine whether the vehicle object enters the vehicle warning area.

[0064] In step S107, it is determined whether the personnel running trajectory overlaps or intersects with the personnel warning area; if the personnel running trajectory overlaps or intersects with the personnel warning area, it is determined that the personnel object enters the personnel warning area.

[0065] Specifically, for the matching of personnel running trajectory and personnel warning area, the server first needs to represent both in the same three-dimensional spatial coordinate system. The personnel warning area has been defined and stored in the form of polygons, circles, cubes, etc. in the electronic map of the mining area. The vertex coordinates or center coordinates of these shapes have been referenced to the unified spatial coordinate system of the mining area. The personnel running trajectory is composed of a series of three-dimensional coordinate points connected in time sequence. The format of the coordinate points is (X, Y, Z), which represents the specific spatial position of the personnel at a certain moment. In order to determine whether the personnel running trajectory coincides with or intersects with the personnel warning area, the server traverses each coordinate point on the personnel running trajectory and converts it to the same spatial coordinate system of the mining area in the electronic map; the server checks whether each coordinate point on the personnel running trajectory falls within the personnel warning area or intersects with the boundary of the personnel warning area. If the server detects that a coordinate point on the personnel running trajectory falls within the personnel warning area or intersects with the boundary of the personnel warning area, it can be determined that the target personnel object has entered the personnel warning area. For the matching of vehicle running trajectory and vehicle warning area, the server's processing flow is similar to that of personnel. The server also needs to compare each coordinate point on the vehicle's running track with the spatial position of the vehicle warning area to determine whether each three-dimensional coordinate point on the vehicle's running track falls within the warning area or intersects with the boundary. Once an intersection or inclusion relationship is detected, it indicates that the vehicle object has entered the vehicle warning area.

[0066] Step S108: If it is determined that the person object enters the person warning area or the vehicle object enters the vehicle warning area, a warning message is sent to the warning management platform.

[0067] In step S108, when the server detects that a person object enters the person warning area or determines that the vehicle object enters the vehicle warning area, the generation process of the warning information will be immediately triggered. The server will automatically extract relevant data information, such as the ID, warning time, and warning location of the warning object according to the pre-configured warning rules and templates, and combine this information into a structured warning information. After the server generates the warning information, it will send it to the warning management platform through the network interface. The warning management platform is usually a centralized information system that is responsible for receiving, storing, analyzing and displaying various types of warning information, and providing convenient query, statistics and decision support functions for managers.

[0068] For example, image acquisition equipment is set up at key locations in the mining area, such as intersections, main transportation roads, loading and unloading yards, and parking lots to obtain monitoring images. Through image recognition algorithms, the characteristics of people (such as helmets and work clothes) and vehicles (such as license plates and vehicle models) in the picture can be automatically extracted, and compared with the preset personnel identity feature library and the preset vehicle information library to identify each target person object and target vehicle object. On this basis, a series of differentiated warning scenarios can be preset according to the safety risk levels of different areas. For example, in the loading and unloading operation area, any non-operating personnel are strictly prohibited from entering. Once a person is found to have mistakenly entered, an alarm will be triggered immediately; while in crowded areas such as parking lots, people wearing complete safety equipment can be allowed to pass. At the same time, the specific type of each vehicle can be identified, such as coal trucks, earth-moving trucks, etc. Based on this, independent driving areas are planned for different models, and an immediate warning will be issued once a vehicle is found to have crossed the line. After entering the real-time monitoring state, the dynamic trajectory of each target person object and target vehicle object is continuously tracked in the background, and it is determined in real time whether they have entered the pre-set warning area. For example, when a truck enters a pedestrian-restricted zone, or a worker mistakenly enters a dangerous area where loading and unloading operations are ongoing, the server will immediately push warning information to on-site managers and the remote dispatch center to ensure that effective measures are taken as soon as possible.

[0069] Reference Figure 2The present application also provides a safety warning device, which is a server, and the server includes an acquisition module 201 and a processing module 202, wherein: the acquisition module 201 is used to acquire multiple mining area images of the mining area; the processing module 202 is used to extract personnel features and vehicle features in the mining area images; the processing module 202 is also used to determine the corresponding target personnel object according to the personnel features, and determine the corresponding target vehicle object according to the vehicle features; the acquisition module 201 is also used to acquire the preset warning scene in the mining area, the preset warning scene includes the warning period, the warning object and the warning area, and the warning object includes the personnel object and the vehicle object; the processing module 202 is also used to determine the corresponding target personnel object according to the personnel features, and determine the corresponding target vehicle object according to the vehicle features; the acquisition module 201 is also used to obtain ... processing module 202 is also used to determine the corresponding target personnel object according to the personnel features, and determine the corresponding target vehicle object according to the vehicle features; the processing module 202 is also used to determine the corresponding target personnel object according to the personnel features, and determine the corresponding target vehicle object according to the vehicle features; the processing module 202 is also used to determine the corresponding target personnel object according to the personnel features, and determine the corresponding target vehicle object according to the vehicle features; the processing module 202 is also used to determine the corresponding target personnel object according to the personnel features, and determine the corresponding The warning object in the warning scene determines the personnel warning area for the target personnel object and the vehicle warning area for the target vehicle object; the processing module 202 is also used to determine the corresponding personnel operation trajectory according to the personnel characteristics, and determine the vehicle operation trajectory according to the vehicle characteristics; the processing module 202 is also used to match the personnel operation trajectory with the personnel warning area to determine whether the personnel object enters the personnel warning area, and match the vehicle operation trajectory with the vehicle warning area to determine whether the vehicle object enters the vehicle warning area; the processing module 202 is also used to send warning information to the warning management platform if it is determined that the personnel object enters the personnel warning area or the vehicle object enters the vehicle warning area.

[0070] In a possible implementation, the processing module 202 extracts personnel features and vehicle features in the mining area image, specifically including: the processing module 202 performs a preprocessing operation on the mining area image to obtain a target mining area image, the preprocessing operation includes image denoising and image enhancement; the processing module 202 uses a target detection algorithm to perform target detection on the target mining area image to obtain personnel objects and vehicle objects; the processing module 202 extracts the personnel position coordinates and appearance features corresponding to the personnel objects as personnel features, and extracts the vehicle position coordinates and license plate number corresponding to the vehicle object as vehicle features.

[0071] In a possible implementation, the processing module 202 determines the corresponding target person object based on the person characteristics, and determines the corresponding target vehicle object based on the vehicle characteristics, specifically including: the processing module 202 performs cluster analysis on the person characteristics to form different person clusters; the processing module 202 performs identity recognition on each person cluster, compares it with a preset person identity feature library, and determines the target person object corresponding to the person cluster; the processing module 202 matches the vehicle characteristics with the preset vehicle information library to obtain the target vehicle object corresponding to the vehicle characteristics.

[0072] In a possible implementation, the processing module 202 determines a personnel warning area for a target personnel object and a vehicle warning area for a target vehicle object based on the warning objects in each preset warning scenario, specifically including: the processing module 202 determines whether the current time is within the warning period; if the processing module 202 determines that the current time is within the warning period, the acquisition module 201 acquires an electronic map of the mining area; the processing module 202 marks the warning areas of the warning objects in each preset warning scenario on the electronic map; the processing module 202 matches the personnel position coordinates and the vehicle position coordinates with the warning area respectively to obtain the personnel warning area and the vehicle warning area.

[0073] In one possible implementation, the processing module 202 matches the personnel movement trajectory with the personnel warning area, and the processing module 202 determines whether the personnel object enters the personnel warning area, specifically including: the processing module 202 determines whether the personnel movement trajectory overlaps or intersects with the personnel warning area; if the personnel movement trajectory overlaps or intersects with the personnel warning area, the processing module 202 determines that the personnel object enters the personnel warning area.

[0074] In a possible implementation, the acquisition module 201 acquires multiple mining area images of the mining area, specifically including: the acquisition module 201 acquires the current ambient light value; the processing module 202 determines whether the current ambient light value is greater than a preset light threshold; if the processing module 202 determines that the current ambient light value is greater than the preset light threshold, then multiple mining area images in the form of visible light images are acquired; if the processing module 202 determines that the current ambient light value is less than or equal to the preset light threshold, then multiple mining area images in the form of infrared images are acquired.

[0075] In a possible implementation, the processing module 202 determines the corresponding personnel movement trajectory based on the personnel characteristics, specifically including: the processing module 202 tracks the target personnel object in multiple mining area images; the acquisition module 201 acquires the position coordinates of the target personnel object at different times; the processing module 202 generates the motion path of the target personnel object based on the position coordinates of the target personnel object at different times; the processing module 202 smoothes the motion path, removes noise and abnormal points in the motion path, and obtains the personnel movement trajectory.

[0076] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0077] The present application also provides an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0078] The communication bus 302 is used to realize the connection and communication between these components.

[0079] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0080] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0081] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0082] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a security early warning method.

[0083] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call an application program storing a security warning method in the memory 305, and when executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0084] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments.

[0085] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0087] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0088] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0090] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0091] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A safety early warning method, characterized in that: The method comprises: Acquire multiple mine area images of the mine area; Extracting personnel features and vehicle features in the mining area image; Determine a corresponding target person object according to the person characteristics, and determine a corresponding target vehicle object according to the vehicle characteristics; Acquire a preset warning scenario in a mine area, wherein the preset warning scenario includes a warning period, a warning object, and a warning area, wherein the warning object includes a personnel object and a vehicle object; Based on the warning objects in each of the preset warning scenarios, determining a personnel warning area for the target personnel object and a vehicle warning area for the target vehicle object; Determine the corresponding personnel running track according to the personnel characteristics, and determine the vehicle running track according to the vehicle characteristics; Matching the personnel running trajectory with the personnel warning area to determine whether the personnel object has entered the personnel warning area, and matching the vehicle running trajectory with the vehicle warning area to determine whether the vehicle object has entered the vehicle warning area; If it is determined that the person object enters the person warning area or the vehicle object enters the vehicle warning area, a warning message is sent to the warning management platform.

2. The method according to claim 1, characterized in that: The extracting of personnel features and vehicle features from the mining area image specifically includes: Performing a preprocessing operation on the mining area image to obtain a target mining area image, wherein the preprocessing operation includes image denoising and image enhancement; Using a target detection algorithm to perform target detection on the target mining area image to obtain personnel objects and vehicle objects; The person position coordinates and appearance features corresponding to the person object are extracted as the person features, and the vehicle position coordinates and license plate number corresponding to the vehicle object are extracted as the vehicle features.

3. The method according to claim 1, characterized in that The determining a corresponding target person object according to the person characteristics, and determining a corresponding target vehicle object according to the vehicle characteristics, specifically includes: Performing cluster analysis on the personnel characteristics to form different personnel clusters; Perform identity recognition on each of the personnel clusters, compare them with a preset personnel identity feature library, and determine the target personnel object corresponding to the personnel cluster; The vehicle features are matched with a preset vehicle information database to obtain a target vehicle object corresponding to the vehicle features.

4. The method according to claim 2, characterized in that: The determining of a personnel warning area for the target personnel object and a vehicle warning area for the target vehicle object based on the warning objects in each of the preset warning scenarios specifically includes: Determine whether the current time is within the warning period; If it is determined that the current time is within the warning period, obtaining an electronic map of the mining area; Marking the warning area of ​​the warning object in each of the preset warning scenarios on the electronic map; The personnel position coordinates and the vehicle position coordinates are matched with the warning area respectively to obtain the personnel warning area and the vehicle warning area.

5. The method according to claim 1, characterized in that The matching of the personnel running trajectory with the personnel warning area to determine whether the personnel object enters the personnel warning area specifically includes: Determine whether the running trajectory of the person overlaps or intersects with the person warning area; If the running trajectory of the person coincides with or intersects with the person warning area, it is determined that the person object enters the person warning area.

6. The method according to claim 1, characterized in that The obtaining of multiple mining area images of the mining area specifically includes: Get the current ambient light value; Determine whether the current ambient light value is greater than a preset light threshold; If it is determined that the current ambient light value is greater than the preset light threshold, acquiring a plurality of images of the mining area in the form of visible light images; If it is determined that the current ambient light value is less than or equal to the preset light threshold, a plurality of images of the mining area in the form of infrared images are acquired.

7. The method according to claim 1, characterized in that Determining the corresponding personnel running trajectory according to the personnel characteristics specifically includes: Tracking the target person object in a plurality of images of the mining area; Obtaining the position coordinates of the target person object at different times; Generating a motion path of the target person object according to the position coordinates of the target person object at different times; The motion path is smoothed to remove noise and abnormal points in the motion path, so as to obtain the movement trajectory of the person.

8. A safety warning device, characterized in that: The device comprises an acquisition module (201) and a processing module (202), wherein: The acquisition module (201) is used to acquire a plurality of mining area images of a mining area; The processing module (202) is used to extract the features of people and vehicles in the mining area image; The processing module (202) is further used to determine a corresponding target person object according to the person characteristics, and to determine a corresponding target vehicle object according to the vehicle characteristics; The acquisition module (201) is further used to acquire a preset warning scene in a mine area, wherein the preset warning scene includes a warning period, a warning object, and a warning area, and the warning object includes a person object and a vehicle object; The processing module (202) is further used to determine a personnel warning area for the target personnel object and a vehicle warning area for the target vehicle object based on the warning objects in each of the preset warning scenarios; The processing module (202) is further used to determine the corresponding person's running track according to the person's characteristics, and to determine the vehicle's running track according to the vehicle's characteristics; The processing module (202) is further used to match the person's running trajectory with the person's early warning area to determine whether the person object has entered the person's early warning area, and to match the vehicle's running trajectory with the vehicle early warning area to determine whether the vehicle object has entered the vehicle early warning area; The processing module (202) is further configured to send warning information to a warning management platform if it is determined that the person object has entered the person warning area or if it is determined that the vehicle object has entered the vehicle warning area.

9. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303) and a network interface (304), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images