阅读说明：本技术 一种用于矿山井下智能识别系统 (Underground intelligent identification system for mine ) 是由 张会柱 王海君 吴庆娟 于 2021-05-11 设计创作，主要内容包括：一种用于矿山井下智能识别系统,系统分为三层,煤矿层、国家矿山局层以及监察监管部门层,煤矿层主要由流媒体服务器、AI分析装置、普通摄像仪、AI摄像仪组成,国家矿山局层主要由智能监控平台、流煤体服务器、FTP服务器组成,监控监管部门主要通过PC终端访问国家矿山局智能监控平台,总共包括Web端、智能监控平台、流煤体服务器(国家矿山局)、FTP服务器、流媒体服务器(矿山)、AI分析装置、AI摄像仪、普通摄像仪,所述智能监控平台部署在国家矿山局,作为整个系统的总调度和监控平台,负责接受和存储各矿提交的报警信息,负责协调FTP服务器提供上传报警图片和视频的显示和下载,负责协调流媒体服务器提供实时视频预览地址。(An intelligent identification system used in mine underground is divided into three layers, namely a coal mine layer, a national mine bureau layer and a monitoring and supervision department gate layer, wherein the coal mine layer mainly comprises a streaming media server, an AI analysis device, a common camera and an AI camera, the national mine bureau layer mainly comprises an intelligent monitoring platform, a coal fluid server and an FTP server, a monitoring and supervision department mainly accesses the intelligent monitoring platform of the national mine bureau through a PC terminal and totally comprises a Web terminal, an intelligent monitoring platform, a coal fluid server (national mine bureau), the FTP server, a streaming media server (mine), an AI analysis device, an AI camera and a common camera, the intelligent monitoring platform is deployed in the national mine bureau and is used as a master scheduling and monitoring platform of the whole system and is responsible for receiving and storing alarm information submitted by each mine and coordinating the FTP server to provide display and download of uploading alarm pictures and videos, and the server is responsible for coordinating the streaming media to provide the real-time video preview address.)

1. The utility model provides a be used for mine intelligence identification system in pit which characterized in that: the intelligent monitoring platform is deployed in the national mine bureau, serves as a general scheduling and monitoring platform of the whole system, is responsible for receiving and storing alarm information submitted by each mine, is responsible for coordinating the FTP server to provide uploaded alarm pictures and display and download of videos, and is responsible for coordinating the streaming media server to provide real-time video preview addresses; the AI analysis device is based on an ARM + DSP framework, mainly carries out the operation of various intelligent analysis algorithms, acquires images of a common camera in real time, carries out the detection of the entry of an analyst into a well, the detection of the entry and exit of a freight vehicle, the identification of the transport state and the detection of the movement and the shielding of the camera through a deep learning function, and uploads alarm information to a mine streaming media server in real time; the AI camera is provided with an intelligent analysis module, can perform well entry detection, freight vehicle in and out detection, transportation state identification and camera moving and shielding detection of analysts through a deep learning function besides the function of a common camera, and uploads alarm information to a mine streaming media server in real time.

2. The intelligent underground mine identification system according to claim 1, wherein: the Web end adopts a B/S architecture.

3. The intelligent underground mine identification system according to claim 1, wherein: the streaming coal body server (national mine bureau) is deployed in the national mine bureau and is responsible for receiving real-time videos uploaded by various mines, converting the videos into HTTP formats and providing the HTTP formats for supervision departments of various provinces to preview through web pages.

4. The intelligent underground mine identification system according to claim 1, wherein: the FTP server is deployed in the national mine bureau and is responsible for receiving alarm pictures and videos uploaded by the mine streaming media servers and providing viewing and downloading interfaces.

5. The intelligent underground mine identification system according to claim 1, wherein: the streaming media server (mine) is deployed in each mine and is responsible for receiving real-time alarm information, pictures and videos reported by the mine and AI analysis device and the AI camera and forwarding the real-time alarm information, pictures and videos to the intelligent monitoring platform of the national mine bureau and the FTP server in real time; and the system is responsible for carrying out proxy forwarding on video streams of all cameras of the mine to a stream coal body server of the national mine bureau so as to facilitate real-time checking of personnel of supervision departments of all provinces.

6. The intelligent underground mine identification system according to claim 1, wherein: the common camera integrates two-way audio processing, broadcasting, a photoelectric switch, WIFI, a twisted pair and the like into a main board, and is matched randomly. And functions of cascade connection, audio and video intercommunication and the like are supported, and an analysis image is provided for the AI analysis device.

Technical Field

The invention relates to the technical field of intelligent identification of mines, in particular to an underground intelligent identification system for a mine.

Background

Coal mines are areas where humans mine coal resources in coal-rich mining areas, and are generally divided into underground coal mines and opencast coal mines. When the coal seam is far from the ground surface, a tunnel is usually dug to the underground, so that the coal is a mineworker coal mine. When the coal seam is very close to the earth surface, the coal is generally excavated by directly stripping the earth surface, which is an open pit coal mine. The vast majority of coal mines in China belong to underground coal mines. The coal mine field which is shut down for a long time, is shut down and is closed in construction, illegal production organizing behaviors are caused, potential safety production hazards of the coal mine can be brought, and the existing coal mine can lack intelligent identification supervision devices to monitor the coal mine in real time and identify the internal conditions.

Disclosure of Invention

The invention mainly aims to provide an underground intelligent identification system for a mine, which is used for overcoming the defects in the prior art;

in order to solve the technical problems, the invention provides the following technical scheme:

an intelligent identification system used in mine underground is divided into three layers, namely a coal mine layer, a national mine bureau layer and a monitoring and supervision department gate layer, wherein the coal mine layer mainly comprises a streaming media server, an AI analysis device, a common camera and an AI camera, the national mine bureau layer mainly comprises an intelligent monitoring platform, a coal fluid server and an FTP server, a monitoring and supervision department mainly accesses the intelligent monitoring platform of the national mine bureau through a PC terminal and totally comprises a Web terminal, an intelligent monitoring platform, a coal fluid server (national mine bureau), the FTP server, a streaming media server (mine), an AI analysis device, an AI camera and a common camera, the intelligent monitoring platform is deployed in the national mine bureau and is used as a master scheduling and monitoring platform of the whole system and is responsible for receiving and storing alarm information submitted by each mine and coordinating the FTP server to provide display and download of uploading alarm pictures and videos, the server is responsible for coordinating the streaming media to provide a real-time video preview address; the AI analysis device is based on an ARM + DSP framework, mainly carries out the operation of various intelligent analysis algorithms, acquires images of a common camera in real time, carries out the detection of the entry of an analyst into a well, the detection of the entry and exit of a freight vehicle, the identification of the transport state and the detection of the movement and the shielding of the camera through a deep learning function, and uploads alarm information to a mine streaming media server in real time; the AI camera is provided with an intelligent analysis module, besides the function of a common camera, the AI camera can perform the well entry detection of analysts, the detection of freight vehicles entering and leaving a factory, the identification of the transport state and the movement and shielding detection of the camera through the deep learning function, and upload the alarm information to the mine streaming media server in real time;

optionally, the Web end adopts a B/S architecture;

optionally, the streaming coal body server (national mine administration) is deployed in the national mine administration, and is responsible for receiving real-time videos uploaded by various mines, converting the videos into HTTP formats, and providing the HTTP formats to supervision and supervision departments of various provinces for previewing through web pages;

optionally, the FTP server is deployed in the national mine bureau and is responsible for receiving alarm pictures and videos uploaded by the mine streaming media servers and providing viewing and downloading interfaces;

optionally, the streaming media server (mine) is deployed in each mine, and is responsible for receiving real-time alarm information, pictures and videos reported by the mine and the AI analysis device and the AI camera, and forwarding the real-time alarm information, pictures and videos to the intelligent monitoring platform of the national mine bureau and the FTP server in real time; the system is responsible for carrying out proxy forwarding on video streams of all cameras of the mine to a stream coal body server of the national mine bureau so as to facilitate real-time checking of personnel of supervision departments of all provinces;

optionally, the common camera integrates two-way audio processing, broadcasting, a photoelectric switch, WIFI, a twisted pair and the like into a main board, matches arbitrarily, supports functions of cascading, audio and video intercommunication and the like, and provides an analysis image for an AI analysis device;

has the advantages that: the invention carries out real-time monitoring observation on internal operation conditions and access personnel by arranging the AI camera and the common camera at fixed points in a coal mine, uploads the information in time and feeds back the information to send alarm information, realizes remote monitoring on key sites and key equipment, develops a unified intelligent supervision platform, remotely monitors the access personnel, the total number of people and the start-stop state of related equipment of the mine by using technical means such as informatization, intellectualization, video identification and the like, intelligently analyzes abnormal conditions, realizes automatic alarm and information push, is convenient for a supervision department to carry out targeted verification on the mine by using analysis results, and strictly prevents illegal production behaviors of illegal organizations of the mine from being shut down for a long time.

Drawings

FIG. 1 is a schematic diagram of the control system apparatus architecture of the present invention;

FIG. 2 is a schematic flow chart of a control system according to the present invention;

Detailed Description

The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

As shown in fig. 1-2, the device includes a Web end, an intelligent monitoring platform, a coal fluid server (national mine bureau), an FTP server, a streaming media server (mine), an AI analysis device, an AI camera, and a general camera, wherein the intelligent monitoring platform is deployed in the national mine bureau, serves as a general scheduling and monitoring platform of the whole system, and is responsible for receiving and storing alarm information submitted by each mine, coordinating the FTP server to provide display and download of uploaded alarm pictures and videos, and coordinating the streaming media server to provide a real-time video preview address; the AI analysis device is based on an ARM + DSP framework, mainly carries out the operation of various intelligent analysis algorithms, acquires images of a common camera in real time, carries out the detection of the entry of an analyst into a well, the detection of the entry and exit of a freight vehicle, the identification of the transport state and the detection of the movement and the shielding of the camera through a deep learning function, and uploads alarm information to a mine streaming media server in real time; the AI camera is provided with an intelligent analysis module, besides the function of a common camera, the AI camera can perform the well entry detection of analysts, the detection of freight vehicles entering and leaving a factory, the identification of the transport state and the movement and shielding detection of the camera through the deep learning function, and upload the alarm information to the mine streaming media server in real time; the Web end adopts a B/S architecture; the stream coal body server (national mine bureau) is deployed in the national mine bureau and is responsible for receiving real-time videos uploaded by various mines, converting the videos into HTTP formats and providing the HTTP formats for supervision departments of various provinces to preview through web pages; the FTP server is deployed in the national mine bureau and is responsible for receiving alarm pictures and videos uploaded by the mine streaming media servers and providing viewing and downloading interfaces; the streaming media server (mine) is deployed in each mine and is responsible for receiving real-time alarm information, pictures and videos reported by the mine and AI analysis device and the AI camera and forwarding the real-time alarm information, pictures and videos to the intelligent monitoring platform of the national mine bureau and the FTP server in real time; the system is responsible for carrying out proxy forwarding on video streams of all cameras of the mine to a stream coal body server of the national mine bureau so as to facilitate real-time checking of personnel of supervision departments of all provinces; the common camera integrates two-way audio processing, broadcasting, a photoelectric switch, WIFI, a twisted pair and the like on a main board, is matched randomly, supports the functions of cascade connection, audio and video intercommunication and the like, provides analysis images for an AI analysis device,

the working principle is as follows: identifying the personnel entering the well: and (3) installing AI cameras or common cameras and AI analysis devices at the wellhead of the main well and the auxiliary well which are shut down and not physically close the mine, and drawing a personnel invasion area in a picture. And when the personnel invade the picture, the AI device immediately generates an alarm signal and generates an alarm picture, labels the invader in the alarm picture through a rectangular frame and counts the number of the invaded personnel. The AI device uploads the alarm information and the alarm picture to a streaming media server of the mine in real time, and the streaming media server generates a JPG picture according to the rule of coal mine coding, camera coding, analysis type coding, number of people and current time plus JPG and uploads the JPG picture to a national platform through an FTP protocol. The national platform stores the data for later viewing and evidence obtaining;

freight vehicle identification: and (3) installing an AI camera or a common camera and an AI analysis device at the entrance and exit of the coal mine coal transportation vehicle with production stoppage and shutdown, and drawing a vehicle intrusion area in a picture. The method is characterized in that sample collection and training are carried out on commonly used freight vehicles, so that the AI device can automatically identify the freight vehicles entering and leaving the mine through a deep learning mechanism. When the freight vehicle enters the picture and invades, the AI device immediately generates an alarm signal and generates an alarm picture, and the passing freight vehicle is marked in the alarm picture through a rectangular frame and the number of the vehicles is counted. The AI device uploads the alarm information and the alarm picture to a streaming media server of the mine in real time, and the streaming media server generates a JPG picture according to the rule of coal mine coding, camera coding, analysis type coding, vehicle number and current time +. JPG and uploads the JPG picture to a national platform through an FTP protocol. The national platform stores the data for later viewing and evidence obtaining;

and (3) identifying the transportation state: an AI camera or a common camera and an AI analysis device are installed at the main wellhead of the coal mine for stopping production and stopping work, and sample collection and training are carried out on common transportation equipment, so that the AI equipment can automatically identify the common transportation equipment of the mine through a deep learning mechanism. When the transport equipment moves in the picture, the AI equipment immediately generates an alarm signal and generates an alarm picture, and the transport equipment is transported in the alarm picture through a rectangular frame. The AI device uploads the alarm information to a streaming media server of the mine in real time, and the streaming media server records a video file of 10 seconds according to the rule of coal mine coding, camera coding, analysis type coding and current time + mp4 and uploads the video file to a national platform through an FTP protocol. The national platform stores the data for later viewing and evidence obtaining;

the camera shelters from and moves angle identification information: the shielding detection function of the common camera and the AI camera is utilized to calibrate the shielding area on the picture of the camera, and the alarm is triggered when the shielding area exceeds the calibrated shielding area. Establishing communication with a camera through a streaming media server on a mine to acquire a shielding alarm signal, and uploading the alarm signal and a captured picture to an FTP server; a reference object is marked in a picture of the camera by using an AI camera or a common camera plus an AI analysis device, and an alarm signal is triggered when the position of the reference object in the picture changes. The AI device uploads the alarm information and the alarm picture to a streaming media server of the mine in real time, and the streaming media server generates a JPG picture according to the rule of coal mine coding, camera coding, analysis type coding and current time plus. The national platform stores the data for later viewing and evidence obtaining;

real-time video streaming: and adding RTSP addresses of all the camera instruments on the mine to a streaming media server, pushing the videos of all the camera instruments to the streaming media server of the national mine bureau by the streaming media server through an RTMP protocol, and viewing the real-time pictures of all the camera instruments by the supervision departments of various provinces through a web page.