LAUSR

Trackside communication and signal infrastructure (TCSI) plays an important role in the safe operation of a high-speed railway system. However, it is a challenge to inspect such infrastructure using a vision-based system because of the uneven illumination and various reflection properties of the TCSI surfaces. This paper puts forward a visual inspection system installed on an inspection car for TCSI. The visual inspection system first captures the trackside images using the image acquisition system. Then, an image processing method using a varying-scale Retinex algorithm is implemented so that the visual inspection system can enhance the contrast of these trackside images. The method changes the size of the Gaussian kernel adaptively according to the image details in order to prevent halo artifacts and graying-out effects inherent in many image enhancement algorithms. By comparison with several state of the art methods, varying-scale Retinex is validated to overcome the local inhomogeneous brightness of images and make those images more suitable for browsing and analysis for inspectors. Composed of the image acquisition system and varying-scale Retinex, the visual inspection system is installed on many inspection cars in China for performing visual inspection.