Study on Vision based Object Detection Algorithm for Passenger' s Safety in Railway Station

철도 승강장 승객안전을 위한 비전기반 물체 검지 알고리즘 연구

  • 오세찬 (한국철도기술연구원, 차세대전동차연구단) ;
  • 박성혁 (한국철도기술연구원, 차세대전동차연구단) ;
  • 정우태 (한국철도기술연구원, 차세대전동차연구단)
  • Published : 2008.06.12

Abstract

Advancement in information technology have enabled applying vision sensor to railway, such as CCTV. CCTV has been widely used in railway application, however the CCTV is a passive system that provide limited capability to maintain safety from boarding platform. The station employee should monitor continuously CCTV monitors. Therefore immediate recognition and response to the situation is difficultin emergency situation. Recently, urban transit operators are pursuing applying an unattended station operation system for their cost reduction. Therefore, an intelligent monitoring system is need for passenger's safety in railway. The paper proposes a vision based monitoring system and object detection algorithm for passenger's safety in railway platform. The proposed system automatically detects accident in platform and analyzes level of danger using image processing technology. The system uses stereo vision technology with multi-sensors for minimizing detection error in various railway platform conditions.

Keywords