Research On Automatic Rail Crack Detection System Based On Image Processing

Recent years, Chinese railway has made a huge progress of development. The increasing railway mileage and the rising speed have made an important contribution to the economic construction. At the same time, the railway traffic accidents continue to occur, which has made a serious impact on the safety of passengers. Therefore, to ensure good condition of the railway track is an important guarantee for safe transportation. At present, railway safety inspection in most areas of our country is mainly relying on manual method which is of low efficiency and poor reliability. For some area, the inspection has used semi-automatic methods but is still time-consuming. In this thesis, an automatic detection system of the rail flaw is introduced, which can automatically detect several types of defects on railway and ensure the train safety.In practical engineering applications, two main parts are needed to be monitored, railway and track plate. Based on these practical needs, a set of automatic defect detection system is designed, to detect the track plate crack, which is divided into three parts:(1) The hardware part. With CCD camera installed on the bottom of the high-speed train, the image of entire rail track is captured while trains traveling, and saved using a real-time algorithm.(2) Automatic detection section. After obtaining an image, we have designed a set of algorithms to achieve the detection of various defects and use the C++ language to implement the procedures.(3) Defects playback section. In this part, by manual inspection, the false defects are deleted, leaving the defects which are needed to be fixed.This thesis make a detailed presentation on the second part of the system, using edge detection, image preprocessing, mask process, true and false crack distinguish, to achieve the detection and localization of defects, and using several methods to optimize the design of whole software system. Tests confirmed that the system is able to timely and effectively discover a variety of defects to ensure the safety of high-speed trains.