Image segmentation algorithm for wheel set measuring based on region growing

Abstract

High speed railway develops rapidly in recent years in China. Wheel set is the major running components of a train. Online measurement of wheel set wear parameters is important for the train safety. A method of wheel sets' wear online measurement based on structure light imaging and image analysis was proposed. A new image segmentation algorithm of wheel set based on region growing was put forward based on characteristics of wheel set images. According to the characteristics of wheel set images acquired in different circumstance, proper seed and appropriate growth standard was determined. After growth processing, the whole tread profile images were extracted. By processing number of images, the proposed algorithm eliminated effectively the interferences in the image acquisition and extracted whole wheel set profile curve from varied background.