基于图像识别的井下煤仓煤位监测系统设计  

Design of Coal Level Monitoring System for Underground Coal Bunker Based on Image Recognition

作　　者：徐慧琼[1] 王庆福[2] XU Huiqiong;WANG Qingfu(Shanxi Polytechnic College,Taiyuan 030006,China;Liaoning Academy of Governance,Shenyang 110161,China)

机构地区：[1]山西职业技术学院,太原030006 [2]辽宁行政学院,沈阳110161

出　　处：《煤炭技术》2022年第8期212-214,共3页Coal Technology

基　　金：山西省自然科学基金项目(201901D111056)。

摘　　要：对基于图像识别的井下煤仓煤位监测系统进行总体设计,系统由辅助光源、CCD相机、图像采集卡和计算机组成。对井下煤仓煤位检测原理进行分析,为提高图像准确度,决定采用双目相机,对双目相机采集的数据进行标定与校正,完成相机的内外参数矩阵、畸变矩阵的求取。通过FPGA芯片采用交互金字塔特征匹配算法对采集的图像进行处理,得到煤仓煤位数据,试验结果显示,此系统煤位检测的误差率在5%以内,可靠性较高。The overall design of coal level monitoring system for underground coal bunker based on image recognition is carried out. The system consists of auxiliary light source, CCD camera, image acquisition card and computer. The principle of coal level detection in underground coal bunker is analyzed. In order to improve the image accuracy, it is decided to use a binocular camera to calibrate and correct the data collected by the binocular camera. And the calculation of the camera’s internal and external parameter matrix and distortion matrix is completed. The FPGA chip is used to process the collected images through the interactive pyramid feature matching algorithm,and the coal level data of the warehouse is obtained. The test results show that the error rate of the coal level detection of this system is within 5%, and the reliability is high.

关 键 词：图像识别 实时监测 煤仓煤位 相机标定 交互金字塔特征匹配 

分 类 号：TD76[矿业工程—矿井通风与安全]