The Journal of Korea Institute of Information, Electronics, and Communication Technology (한국정보전자통신기술학회논문지)

Korea Information Electronic Communication Technology (한국정보전자통신기술학회)
권호 표지
DOI QR코드

DOI QR Code

A design and implementation of Intelligent object recognition system in urban railway

도시철도내 지능형 객체인식 시스템 구성 및 설계

  • Received : 2018.04.05
  • Accepted : 2018.04.20
  • Published : 2018.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The subway, which is an urban railway, is the core of public transportation. Urban railways are always exposed to serious problems such as theft, crime and terrorism, as many passengers use them. Especially, due to the nature of urban railway environment, the scope of surveillance is widely dispersed and the range of surveillance target is rapidly increasing. Therefore, it is difficult to perform comprehensive management by passive surveillance like existing CCTV. In this paper, we propose the implementation, design method and object recognition algorithm for intelligent object recognition system in urban railway. The object recognition system that we propose is to analyze the camera images in the history and to recognize the situations where there are objects in the landing area and the waiting area that are not moving for more than a certain time. The proposed algorithm proved its effectiveness by showing detection rate of 100% for Selected area detection, 82% for detection in neglected object, and 94% for motionless object detection, compared with 84.62% object recognition rate using existing Kalman filter.

도시철도인 지하철은 대중교통 수단 중의 핵심이라고 할 수 있다. 도시 철도는 항상 많은 승객들이 이용하다 보니 도난, 범죄, 테러 등의 심각한 문제에 늘 노출되어 있다. 특히 도시철도 환경 특성상 감시 범위가 넓게 분산되어 있고 감시 대상 범위가 급증하고 있어 기존 CCTV와 같은 수동적인 감시만으로는 종합적인 관리가 어려운 상황이다. 본 논문에서는 도시철도내 지능형 객체인식 시스템을 구성, 설계 방법 및 객체 인식 알고리즘을 제안하고자 한다. 제안하고자 하는 객체 인식시스템은 역사내 카메라 영상을 분석하여 승강장 및 대합실에서 제한구역내 접근이나, 방치 혹은 일정 시간 이상 움직이지 않는 물체가 있는 경우를 위험 상황으로 인지하고 신속하게 대응 할 수 있도록 하고자 하였다. 제안된 알고리즘은 기존 Kalman 필터를 이용한 객체 인식율 84.62%에 비해 지정지역 감지에 대해서는 100%, 방치된 물체 감지는 최소 82% 이상, 움직임이 없는 물체 감지에서는 94% 이상의 감지율을 나타내어 실효성을 입증하였다.

Keywords

References

  1. Jong Gyu Son, "A Study and Experimental Verification on Object Detection Method of Intelligent Integrated Monitoring System", Dept. of Electronic & Electrical Eng'ng, University of Seoul, Korea, 2012.
  2. J. S, Oh, "Motion-Based Background Image Extraction for Traffic Environment Analysis", Journal of information and communication convergence engineering, Vol. 13, No. 8, pp.1919-1925, 2013.
  3. D. Comaniciu and V. Ramesh , P. Meer, "Kernel-Based Tracking", IEEE trans. Pattern Analysis and Machine Intelligence, Vol. 25, No. 5, pp. 564-577, 2003. https://doi.org/10.1109/TPAMI.2003.1195991
  4. P. Azzari, L. Stefano, and A. Bevilacqua, "An effective real-time mosaicing algorithm apt to detect motion through background subtraction usinf a PTZ camera", IEEE Conf. Advanced Video and Signal-Based Surveillance, pp. 511-516, 2005.
  5. S. Lee, J. Kang, J. Shin, and J. Paik, (2007) "Hierarchical active shape model with motion prediction for real-time tracking of non-rigid object", IET Computer Vision, Vol. 1, No. 1, pp.17-24, 2007. https://doi.org/10.1049/iet-cvi:20045243
  6. S. H. Jung, J. H. Lee, "Measurement of the Traffic Congestion using Difference of Images in Intersection ", IEEK Summer Coference , pp. 801-802, 2008
  7. Wang, Yang, "Real-time moving vehicle detection with cast shadow removal in video based on conditional random field", Circuits and Systems for Video Technology, IEEE Transactions on Vol. 19, No. 3 pp. 437-441, 2009. https://doi.org/10.1109/TCSVT.2009.2013500
  8. S Xu, A Chang, "Robust Object Tracking Using Kalman Filters with Dynamic Covariance", Cornell University, 2014
  9. Sandipkumar M Vaniya, B. Bharathi, "Exploring object segmentation methods in visual surveillance for human activity recognition", Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC), pp.520-525, 2016.
  10. Salmane. Houssam, Khoudour. Louahdi, Ruichek. Yassine, "A Video-Analysis-Based Railway-Road Safety System for Detecting Hazard Situations at Level Crossings", IEEE transactions on intelligent transportation systems, v.16 no.2, pp.596-609, 2015. https://doi.org/10.1109/TITS.2014.2331347
  11. Salmane. H, Ruichek. Y, Khoudour. L, "A novel evidence based model for detecting dangerous situations in level crossing environments." Expert systems with applications v.41 no.3, pp.795-810, 2014. https://doi.org/10.1016/j.eswa.2013.08.010
  12. H. S. Park, "Active Object Tracking System for Intelligent Video Surveillance", Journal of The Korea Institute of Information & Electronic Communication Technology, v.7 no.2, pp.82-85, 2014. https://doi.org/10.17661/jkiiect.2014.7.2.082