Abstract

Derailments take place when a train runs off its rails and are seriously hazardous to human safety. Most of the Railway Track defects which lead to derailment are detected manually by trained human operators walking along the track. To overcome this difficulty, an Automatic Railway Track Derailment Inspection System using Machine Vision Algorithm to detect the cracks in the railway track is proposed here. The input image is decomposed by Gabor filter and texture features were extracted using Segmentation based Fractal Texture Analysis (SFTA) and the features are classified as defect and defect free classes using AdaBoost Classifier. The proposed algorithm is tested on a set of real time samples collected and the classification rate obtained was satisfactory.

Authors

S. Arivazhagan, R. Newlin Shebiah, J. Salsome Magdalene, G. Sushmitha
Mepco Schlenk Engineering College, India

Keywords

Crack Detection, Gabor Wavelets, Texture Analysis, AdaBoost Classifier