No abstract

Rail track surface defects detection is an important part of the monitoring of railroad safety. In this paper, rail track images obtained by detection system of rail track surface image are processed. Firstly, the Hough transform is applied to process the images of the track surface to locate and extract the image of the track surface, which overcomes the influence of incline and unfixed width of track surface images caused by vehicle vibration. Secondly, improved Sobel operator and area filter are used together to extract track surface defects from the original images. Finally, the defects images are classified based on circularity and length-width ratio of minimum enclosing rectangular of defects images.Results of experiments show that the algorithm can identify and classify the defects images of track surface. The minimum detection region in rail track surface is 0.0068 cm2.

No abstract

The first step of track surface detection based on contactless optical detection is to obtain the surface image. This paper introduces a vehicle-mounted image collecting system base on area-array camera. This system avoids image morphing and edge deformation of system base on linear-array camera.Camera could works in both frequently flash and persistent bright without influence image collecting and will not miss information of the rail track surface when vehicle keeps the speed of 342Km/h. The exposure time should be chosen according to railcar speed and maximum speed.

In the field of detecting for defects of railroad track surface, computer vision method for detection has been widely used. An online real-time image processing system for defects of railroad track surface is introduced in the paper. Results show that: if the number of pixels in each railroad track surface image is 512×240, the train speed can be 50 Km/h while the image processing system can real-time detect the railway track surface defects, the number of pixels in in each railroad track surface image is 320×250, the train speed can be 100 Km/h while the image processing system can real-time detect the railway track surface defects.