A rail detection algorithm for accurate recognition of train fuzzy video

The research follows the mainstream physics and network system architecture. Aiming at the problem of poor data processing ability and poor robustness of traditional trajectory detection algorithms, a trajectory detection method that can be accurately extracted from the fuzzy video of a locomotive is proposed. Firstly, in order to ensure the accuracy of rail detection of trains in complex environments and improve the safety of driverless driving, the video image captured by on-board camera is stored as RGB video frame set, and then processed as single-channel greyscale image carrier set; Secondly, after the initial colour and brightness treatment, the redundant and useless noise features in the greyscale image carrier set still exist. After secondary Gaussian filtering and de-noising, canny operator is used to detect the track edge details of interest; Finally, the rail area is taken as the interested target for Hough line detection, the background subtraction method of adaptive mixed Gaussian background modelling is introduced, the structure element function and the morphologyEx theory of morphological transformation function are introduced, and the left and right tracks are fitted after the calculation and judgement of pixel coordinates. Algorithm for visual tracking experiments show that, rail detection algorithm has already meet need to detect rails in low-quality videos recorded by the on-board cameras of different models of trains at different speed. It not only can process large quantity of data from the on-board camera videos in real time, but also can accurately detect the target rails adaptively where rail conditions are complex with obstructive objects, which shows that this algorithm has very robust performance.