Gong-kuang zidonghua (Mar 2022)
Research on precise detection method of personnel in shearer operation area
Abstract
The current intelligent shearer has the functions of three-dimensional positioning, memory cutting and remote monitoring, but it lacks the detection and early warning protection function of personnel entering the shearer operation area by mistake. Therefore, the precise detection of personnel is one of the key problems to be solved urgently. Affected by the low illumination and complex working conditions of fully mechanized working face, the application of active anti-collision warning technology for coal mine electromechanical equipment based on laser, radio frequency, ultrasonic and other sensors is limited, and the anti-collision technology based on visible light sensor cannot meet the requirements of accuracy and stability. The system architecture of precise detection of personnel in shearer operation area based on infrared thermal imaging technology is built, and then the precise detection method of personnel is proposed. Aiming at the high intensity and uneven characteristics of the infrared image noise in fully mechanized working face, an improved multi-layer guided filter model based on Gauss mask-code is used to filter out infrared image noise effectively and retain the edge information. The moving foreground target motion information under dynamic background is extracted by optical flow method that based on Lucas-Kanade. The intuitionistic fuzzy C-means clustering algorithm based on the weight of local image information is used to segment the infrared image information of the shearer operation area so as to obtain the position information of the moving target. Based on the morphological weighted voting method, the extraction results of the moving target motion information and the infrared image information segmentation results are fused to realize the precise detection of personnel in the shearer operation area. The underground industrial test is carried out in 21208 fully mechanized working face of Gengcun Coal Mine. The results show that the average tracking deviation of the precise detection method for personnel in the shearer operation area is 0.106 5 pixel, the average overlap ratio is 96.10%, and the average single processing time is 0.490 8 s, which meet the needs of field application.
Keywords
