Abstract
With the rapid development of high-speed railways today, CRTSII type track slabs have caused diseases due to their own structural aging and various external factors. This paper presents a crack detection method for track slabs in complex environments. Due to the uneven illumination in the nighttime, the shooting environment is complex and shadows are easily generated. Firstly, the histogram equalization is used to reduce the effect of uneven illumination on the detection of cracks. Secondly, the improved Canny edge detection algorithm is used to draw a continuous crack profile with adaptive dual thresholds. Then, an algorithm based on the contour of the fracture shape is used to extract the fracture characteristics and achieve accurate crack location. Finally, a criterion for determining the level of cracking faults based on the width of cracks is proposed. The algorithm can effectively improve the accuracy of track plate crack detection under complex environment, quantify the level of crack disease, and provide maintenance basis for track maintenance personnel. Experimental results show that the method has high robustness and accuracy.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call