摘要
为解决矿山相似模拟场的靶点坐标的实时批处理问题,提出基于机器视觉的靶点多圆检测和坐标快速反馈方法。首先对模拟采掘面均匀布设靶点,连续采集模拟场高清图像数据;引入Canny边缘检测和Hough梯度法捕捉多圆靶点中心位置,建立多圆靶点坐标像素阵列;建立相似模拟场对实际矿山坍塌状况的映射模型,实现靶点像素场位移实时反馈。测试结果表明,相比传统散斑法,采用多圆检测法和像素场位移反馈法,能更有效解决矿山相似模拟场的多靶点坐标实时反馈和位移监测,检测速度快,为相似模拟场应力研究提供新的思路。
In order to solve the problem of real-time batch processing of target coordinates in mine similar simulation field,a method of target multi circle detection and coordinate fast feedback based on machine vision was proposed.Firstly,the targets wereuniformly arranged on the simulated mining face,and the high-definition image data of the simulated field were continuously collected.Canny edge detection and Hough gradient method were introduced to capture the centre position of multi circular targets,and the coordinate pixel array of multi circular targets was established.The mapping model of similar simulation field to the actual mine collapse condition was established to realize the real-time feedback of target pixel field displacement.The results show that using multi-circle detection method and pixel field displacement feedback method,the multi-target coordinate real-time feedback and displacement monitoring of mine similar simulation field can be realized more quickly.The research provides a new idea for the study of similar simulated field stress.
作者
龚平顺
洪炎
GONG Pingshun;HONG Yan(School of Electrical and Information Engineering,Anhui University of Science and Technology,Huainan,232001,China)
出处
《华北科技学院学报》
2022年第3期54-60,共7页
Journal of North China Institute of Science and Technology
基金
安徽理工大学创新基金项目(2021CX2071)。
关键词
多圆检测
像素场位移
机器视觉
相似模拟场
multi-circle detection
pixel field displacement
photogrammetry
similar simulation field
