Railway equipment detection using exact height function shape descriptor based on fast adaptive Markov random field

Abstract

This paper proposes a hierarchical feature-matching model for the typical faults detection, which is a big challenge in the trouble of a moving freight car detection system (TFDS) due to the constant color and complex background of images. The proposed model divides fault detection into two stages: image segmentation and parallel shape matching. In the process of segmentation, a fast adaptive Markov random field (FAMRF) algorithm is presented based on the image pyramid model and affinity propagation theory. In the process of shape matching, a shape descriptor named exact height function (EHF) is introduced on the basis of parallel dynamic programming. The experimental results indicate that the proposed hierarchical model combined with FAMRF and EHF can achieve automatic detection of an air brake system, bogie block key, and fastening bolt. The proposed model achieves high detection accuracy and great robustness, and it can be effectively applied to the fault detection in TFDS.