Solution for Safety Supervision of Underground Personnel_Smart Energy Solution_Solution_Xian Xitu Zhiguang Intelligent Technology Co., Lt

Smart Energy Solution

Smart Manufacturing Solution

Smart Education Solution

Solution Overview

The underground personnel safety monitoring plan takes "3D facial recognition technology" as the core, and combines the personnel positioning system to realize accurate identity verification of underground staff, on-duty management, and closed-loop management of hidden dangers. This plan targets the prominent pain points of coal mines ,including complex underground environments, fraudulent shift duty, difficult traceability of hidden dangers. Adopting contactless biometric technology, it ensures authentic on-duty attendance, attendance verification in high-risk areas, and real-time data synchronization, so as to improve the overall level of mine safety production. It promotes the management transformation from "post-incident accountability" to "proactive

Solution for Safety Supervision of Underground Personnel

Solution Architecture

The solution adopts a "terminal-edge-cloud" collaborative architecture to realize full-process closed-loop management for underground mines.

Terminal Devices: Intrinsically safe and explosion-proof 3D facial recognition devices in key underground areas (such as wellheads, working faces, and high-risk locations)for personnel identity verification and attendance recording. The equipment supports hybrid deployment to cover underground supervision bling spots.

Edge processing: The devices are integrated with an offline resume and transmission function, and interfaced with the personnel positioning platform, ensuring

Core Strengths

Technological Leadership

3D structured light facial recognition technology has high adaptability, can recognize black faces, is not affected by coal ash stains, has a recognition speed of less than 0.5 seconds, and is resistant to photo and mask attacks during live detection.

Management efficiency

Non contact recognition reduces manual intervention, with a single person travel time of less than 1 second; Automated data recording reduces management costs and improves the accuracy of quantitative statistics for shift management.

Compliance assurance

Comply with policies such as the "Regulations on Coal Mine Leaders Leading Work and Safety Supervision Inspection", provide complete logs and reports, and meet regulatory audit requirements.

System Integration

Support seamless integration with existing personnel positioning and warning platforms, break data silos, and achieve closed-loop management of hidden dangers (hidden danger registration → rectification assignment → on-site review → cancellation).

Related Products

2D Face SDK Andorid

The 2D Face SDK is a facial algorithm development toolkit designed for the Android operating system ;mobile phones, tablets, Android industrial computers, etc.1;. Its core is based on two-dimensional RGB images captured by mobile phone cameras, encapsulating a full set of algorithm capabilities such as face detection, recognition, comparison, liveness detection, and attribute analysis, and providing API interfaces that comply with Android development standards.

2D Face SDK LINUX

The 2D Face SDK (Software Development Kit) is a set of face-related algorithms and interfaces developed for the Linux operating system Built around two-dimensional images (RGB/grayscale images) to complete facial detection, recognition, analysis, and other functions. Developers can quickly integrate facial capabilities into Linux servers, embedded devices (such as Linux industrial computers, edge boxes), Linux desktop applications, and other products by calling the API interfaces provided by the SDK.

2D Face SDK for Windows

The 2D facial algorithm SDK is a standardized software development kit developed for the Windows operating system supporting and Windows 10/11. and Windows Server&# It encapsulates core face-related algorithms capabilities based on 2D images. Developers do not need to develop underlying algorithms from scratch, by simply calling the API interfaces provided by the SDK, they can quickly integrate face detection, recognition and analysis into Windows applications (such as desktop software, client programs, and industrial PC applications).

3D Face SDK Andorid

The 3D Face SDK (Android version) is a specialized software development toolkit for Android mobile devices, designed specifically for mobile 3D face related application scenarios. It integrates core capabilities such as face detection, 3D modeling, keypoint localization, liveness detection, and facial feature extraction. It is based on computer vision, deep learning, and 3D reconstruction technologies, adapted to the hardware features of the Android system (such as depth cameras, RGB cameras) and software ecosystem (Android 8.0 and above mainstream versions). Developers can quickly integrate high-precision and high stability 3D face processing capabilities in Android applications through simple API calls, without the need to develop underlying algorithms from scratch, greatly reducing the development threshold and cycle of mobile 3D face applications.

3D Face SDK LINUX

The 3D Face SDK for Linux platform is a software development toolkit developed for Linux operating systems (such as Ubuntu, CentOS, Debian, covering x86_64, ARM64 and other architectures). It integrates 3D face detection, modeling, recognition, liveness detection, point cloud analysis and other algorithms, and is provided in the form of static libraries (. a), dynamic libraries (. so) or source code (partially open source SDK). It supports mainstream Linux development languages such as C/C++(native), Python, Go, etc. Developers can quickly integrate 3D face capabilities into Linux servers, embedded devices, industrial computers and other applications, adapting to the multi threading, low resource consumption, open source ecology and other features of Linux.

3D Face SDK for Windows

The 3D Face SDK is a software development toolkit developed for Windows operating systems (Windows 10/11, Windows Server), which integrates core algorithms and interfaces for 3D face capture, modeling, detection, recognition, analysis, and more.

Object detection and classification

Locate and classify objects in images/videos (such as people, cars, non motorized vehicles, animals, objects, etc.). Typical algorithms/models: YOLO, Faster R-CNN, SSD, RetinaNet, EfficientDet, etc. Core competencies: Simultaneous detection of multiple categories, scales, and targets. Support detection of small targets, occluded targets, and dense targets. Can be used for security, transportation, retail, industrial, and robot perception.

Target Tracking (Multi Target Tracking MOT)

Continuously locate and associate the same target with its ID in consecutive video frames. Typical methods: DeepSORT, ByteTrack, StrongSORT, FairMOT, etc. Core ability: Maintain cross frame IDs and support re identification after occlusion. Suitable for passenger flow statistics, traffic flow statistics, behavior analysis, security deployment, and robot tracking.

Image Segmentation

Semantic segmentation: Classify each pixel in the image (roads, buildings, sky, vegetation, human body, etc.). Typical models: U-Net, DeepLab, SegFormer, etc. Applications: Autonomous driving perception, medical image segmentation, remote sensing image analysis, industrial defect area localization. Instance segmentation: not only categorizes, but also distinguishes different individuals within the same category (such as multiple people, multiple vehicles). Typical models: Mask R-CNN, SOLO, YOLACT, etc. Applications: Robot grasping, industrial sorting, security statistics, retail product recognition. Panoramic segmentation: semantic+instance fusion, making instances for "objects" and semantic for "background areas". Applications: autonomous driving, city perception, high-precision scene understanding.

Key Point/Attitude Estimation

Human pose estimation: Detecting key points of the human body (head, shoulders, elbows, wrists, hips, knees, ankles, etc.) and outputting skeletal structures. Typical models: OpenPose, HRNet, YOLO Pose, etc. Applications: Behavior analysis, fall detection, action recognition, fitness/sports action correction, human-computer interaction. Hand/limb key points: Hand 21 points, finger posture, gesture recognition. Applications: VR/AR interaction, sign language recognition, robot dexterity, and aerial control.

Application Scenarios

Underground shift management

Verify the situation of leaders leading shifts to work, eliminate proxy clock ins, and achieve "true performance and strict assessment".

Control of high-risk areas

Key areas such as mining workfaces and mechanical and electrical chambers are required to have personnel on duty for verification, reducing blind spots in supervision.

Hidden danger closed-loop management

Used for the hidden danger rectification process, the responsible person is associated with the 3D face to ensure that the rectification deadline and acceptance can be traced.

emergency response

Quickly verify the identity and location of underground personnel during disasters to support emergency rescue decisions.

Peak shift handover management

Respond to personnel entering and exiting the well in a centralized manner, intelligently dispatch and identify, and avoid congestion.

Implementation Case

Guizhou Tianlun Energy Shuicheng County Jiyuan Coal Mine

Deploying a safety supervision system for underground personnel, achieving precise control of on duty performance, and significantly reducing the accident rate.

Shandong Energy Group Beidou Tiandi

Covering multiple projects such as Shilaosu Coal Mine, the integration of personnel positioning and hazard management is achieved through 3D facial recognition technology.

Zhangji Coal Mine in Huainan, Anhui

After applying the system, the efficiency of personnel management has been improved by 50%, and the phenomenon of job substitution has been basically eliminated.

Smart Energy Solutions

Smart Energy Solution

Solution Overview

Solution Architecture