Track Line Recognition Based on Morphological Thinning Algorithm

Abstract

In the field of intelligent driving of freight trains, determining the track line ahead of the train is an important function in the autopilot technology of such trains. Combining the characteristics of freight railway tracks, we conduct an in-depth analysis of the shortcomings of object detection technology in extracting track lines and propose an improved Zhang–Suen (ZS) thinning theory for a railway track line recognition algorithm. Through image preprocessing and single pixel thinning steps, a continuous track line is obtained and then processed by a denoising algorithm to obtain a complete track line. Experimental results show that the track extracted by our method has good continuity and less noise. It can simultaneously perform track detection on straight roads, curves and turnouts, and is suitable for changing weather conditions such as sunny daytime, mild rainy daytime, cloudy daytime, night with lamp lighting and night without lamp lighting conditions.

Rail‐Lane Extraction Based on Cutting‐Edge Deep Neural Networks and Graph‐Based Segmentation

“…Based on an ego-perspective image captured from a front camera of a train, an obstacle, which is a frontal object with a collision risk, is detected. The collision risk is assessed in that whether the frontal object is in the train pathway, which is predicted by the rail-track detection [9][10][11][12][13][14][15][16][17]. To accurately assess the collision risk, the railtrack detection must be enhanced.…”

Research of ESPI Stripe Skeleton Line Extraction Based on Improved Fast Parallel Algorithm

“…The traditional refinement algorithms mainly include mathematical morphology refinement [4], ZS refinement [5], OPTA refinement [6] and Hilditch refinement [7], which are applied in many fields, among which the classical Hilditch refinement adopts serial processing, which is suitable for various shapes of electron scattering interference fringe maps, and is widely used, with the disadvantage of the presence of more burrs and breaks.…”