论文部分内容阅读
针对带式输送机胶带在运行过程中易出现跑偏的情况,提出了一种基于计算机视觉的输送带跑偏监测方法。首先将视频监控中采集到的视频图像设置感兴趣区域(Region of Interest,ROI)以减少计算量,同时对ROI进行图像预处理。然后采用改进的Canny边缘检测算法得到ROI边缘二值图像,利用累计概率霍夫变换(Progressive Probabilistic Hough Transform,PPHT)提取输送带边缘直线特征,最后根据所得直线特征来判断输送带是否跑偏。
Aiming at the deviation of belt conveyor tape during operation, a method of belt deviation monitoring based on computer vision is proposed. Firstly, the Region of Interest (ROI) of the video images collected in the video surveillance is set to reduce the computational load, meanwhile the image preprocessing of the ROI is performed. Then the improved Canny edge detection algorithm is used to get the binary image of the ROI edge. The edge of the belt is extracted by the Progressive Probabilistic Hough Transform (PPHT), and finally the straight line characteristics of the belt are used to judge whether the conveyor belt runs off.