Research on Positioning Method of Coal Mine Mining Equipment Based on Monocular Vision

In view of the insufficient characteristics and depth acquisition difficulties encountered in the process of uniocular vision measurement, the posture measurement scheme of tunneling equipment based on uniocular vision was proposed in this study. The positioning process of coal mine tunneling equipm...

Full description

Saved in:
Bibliographic Details
Published in:Energies (Basel) 2022-11, Vol.15 (21), p.8068
Main Authors: Yu, Rui, Fang, Xinqiu, Hu, Chengjun, Yang, Xiuyu, Zhang, Xuhui, Zhang, Chao, Yang, Wenjuan, Mao, Qinghua, Wan, Jicheng
Format: Article
Language:English
Subjects:
3D reconstruction
Algorithms
Analysis
Cameras
Coal industry
Coal mines
Coal mining
Coordinates
equipment position
intelligent tunneling
Mathematical models
Methods
Mineral industry
Mining equipment
Mining industry
Mining machinery
Monocular vision
Pose estimation
Position measurement
Robots
Tunneling
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In view of the insufficient characteristics and depth acquisition difficulties encountered in the process of uniocular vision measurement, the posture measurement scheme of tunneling equipment based on uniocular vision was proposed in this study. The positioning process of coal mine tunneling equipment based on monocular vision was proposed to extract the environmental features and match the features, and the RANSAC algorithm was used to eliminate the pair of mismatching points. This was done to solve the optimized matching pair and realize the pose estimation of the camera. The pose solution model based on the triangulation depth calculation method was proposed, and the PNP solution method was adopted based on the three-dimensional spatial point coordinates so as to improve the visual measurement accuracy and stability and lay the foundation for the 3D reconstruction of the roadway. This was done to simulate the downhole environment to build an experimental verification platform for monocular visual positioning. The experimental results showed that the position measurement accuracy of the uniocular visual roadheader positioning method within 60 mm and 1.3° could realize the accurate registration of the point cloud in the global coordinate system. The time required for the whole monocular visual positioning was only 179 ms, so it had good real-time performance.
ISSN:1996-1073
1996-1073
DOI:10.3390/en15218068