Research On Monitoring Method For Abnormal State Of Coal Mine Belt Conveyor Based On Vision

Video surveillance is an important means of security.In recent years,video monitoring technology is widely used in coal mine production and provides technical support for the coal mine safety production.At present,the video surveillance system of mine in our country is mainly based on manual monitoring,which people often appear omission phenomenon.With the development of computer vision technology,coal mine intelligent video surveillance will replace artificial monitoring ways to realize the real-time automatic surveillance of abnormal state.Belt conveyor is the most widely used transportation equipment in mine production,which is prone to various faults in long time and high strength.And it's also a key point of coal mine video monitoring.This paper puts forward the monitoring method of mine belt conveyor abnormal condition based on visual technology,and in order to realize the intelligent control of belt conveyor.This article mainly includes the following contents:According to poor image captured by coal mine monitoring system underground such as low contrast,uneven illumination and a lot of noise.In this paper,an effective coal mine underground images enhancement method was proposed,which was single scale Retinex algorithm based on the simultaneous denoising of the weighted guided filter.First,the low frequency components of the image were estimated by the weighted guided filter,which replaces the Gaussian filter in Retinex algorithm.Second,denoising processing of the high frequency components of the image by using the weighted guided filter.Finally,we can obtain enhanced image by the log domain conversion to real field.Due to conveyor belt easily deviate during operation,the belt deviation monitoring method based on the computer vision is proposed.Firstly,the Region of Interest(ROI)in video surveillance is set to reduce the amount of calculation,and the image preprocessing is performed on the ROI.Then the improved Canny edge detection algorithm is used to get the ROI edge binary image,and the linear feature of conveyor belt edge is extracted by using the cumulative probability Hough transform.Finally,According to the linear features to determine whether the conveyor belt deviation.In view of the situation that the belt conveyor is easy to slip in the course of transporting material,a new method for detecting the slipping of belt conveyor based on OpenCV is put forward.Firstly,by using the background difference method and the connected region labeling method to detect the moving objects on the conveyor belt.Secondly,the minimum circumscribed rectangle is used to obtain the target aspect ratio,and the trajectory tracking method based on the centroid feature is used to obtain the displacement of the moving objects and corresponding time intervals.Finally,using the velocity equation to obtain the speed of the conveyor belt,hence whether the fault slip during acceleration.After a lot of experiments and a comprehensive analysis of the experimental data,the experimental results show that based on the visual technology of mine belt conveyor under abnormal condition monitoring method can realize the automatic monitoring of the deviation and slip fault.It is of great significance to improve the information level of coal mine safety monitoring in china...