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

Guodong Sun; Yang Zhang; Hanbing Tang; Huiming Zhang; Moyun Liu; Daxing Zhao

doi:10.1117/1.OE.57.5.053114

25 May 2018 Railway equipment detection using exact height function shape descriptor based on fast adaptive Markov random field

Guodong Sun, Yang Zhang, Hanbing Tang, Huiming Zhang, Moyun Liu, Daxing Zhao

Author Affiliations +

Optical Engineering, Vol. 57, Issue 5, 053114 (May 2018). https://doi.org/10.1117/1.OE.57.5.053114

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.

Citation Download Citation

Guodong Sun, Yang Zhang, Hanbing Tang, Huiming Zhang, Moyun Liu, and Daxing Zhao "Railway equipment detection using exact height function shape descriptor based on fast adaptive Markov random field," Optical Engineering 57(5), 053114 (25 May 2018). https://doi.org/10.1117/1.OE.57.5.053114

Received: 8 March 2018; Accepted: 10 May 2018; Published: 25 May 2018

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available