A Vision-Based Method for the Inspection of Missing Rail Fasteners

Computer vision for railway safety
Computer Vision, Machine Learning, Web Development
Sep 2016–Apr 2017

Quick Summary

  • Visual inspection of rail fasteners is crucial to rail safety. However, the traditional method in which railway staffs manually inspect the conditions of fasteners is time-consuming and prone to error.
  • In this project, I formulated a computer vision algorithm to promote rail safety by automatically assessing rail fasteners/clips from photos taken with cameras installed under rail inspection trains
  • Machine learning (SVM) was used to classify between images with intact and missing fasteners.
  • Published and presented at the IEEE International Conference on Signal and Image Processing Applications 2017 (ICSIPA2017) in Kuching, Malaysia.

My Roles

  • Solo Project: Prepared the dataset, Formulated the algorithm for localization and detection.
  • Worked under the advisement of Dr. Thanarat H. Chalidabhongse and Sangsan Leelhapantu

Details

Team Tae Prasongpongchai (Me)
Tools OpenCV, ­Vue.js
Purpose Senior Project, Computer Engineering at Chulalongkorn University, Adviser - Dr. Thanarat Chalidabhongse
Timeline Sep 2016–Apr 2017

Publication

T. Prasongpongchai, T. H. Chalidabhongse and S. Leelhapantu, “A vision-based method for the detection of missing rail fasteners,” 2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), Kuching, 2017, pp. 419-424.

See publication in IEEE Xplore »