Multiple Objection and Tracking based on Morphological Region Merging from Real-time Video Sequences

실시간 비디오 시퀀스로부터 형태학적 영역 병합에 기반 한 다중 객체 검출 및 추적

  • Published : 2007.02.28


In this paper, we propose an efficient method for detecting and tracking multiple moving objects based on morphological region merging from real-time video sequences. The proposed approach consists of adaptive threshold extraction, morphological region merging and detecting and tracking of objects. Firstly, input frame is separated into moving regions and static regions using the difference of images between two consecutive frames. Secondly, objects are segmented with a reference background image and adaptive threshold values, then, the segmentation result is refined by morphological region merge algorithm. Lastly, each object segmented in a previous step is assigned a consistent identification over time, based on its spatio-temporal information. The experimental results show that a proposed method is efficient and useful in terms of real-time multiple objects detecting and tracking.


Video Surveillance System;Moving Object Detection;Object Segmentation;Multiple Object Tracking


  1. N. Oliver, B. Rosario, and A Pentland, "A Bayesian Computer Vision System for Modeling Human Interaction," Int Conf. on Vision Systems, pp.255-272, 1999.
  2. C. R Wren, A Azarbayejani,T. Darrell, and A. Pentland, "TM Pinder: Realtime Tracking of the Human Body,"IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.19, No.7, pp.780-785, 1997.
  3. S. Niyogi and E. Adelson, "Ana!yzing Gait Spatiotemporal Surface," lEEE Workshop, pp.64-69, 1994.
  4. K. Sato and J. K. Aggarwal,"Tracking and Recognizing Two-person Interaction in Outdoor Image Sequences," IEEE Workshop on Multi-object, pp.87-94, 2001.
  5. M Quming and J K Aggarwal, "Tracking and Classîfying Moving Objects from Video," IEEE Intemational Workshop on PETS, 2001.
  6. A Lipton, H Fujiyoshi, and R Patil, "Moving Target Classîfying Moving Objects from Video," DARPA Image Understanding Workshop,1998.
  7. N. Paragíos and R Deriche, "Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Object," IEEE Transactions on Pattern Analysís and Machine Intelligence, Vol.22, No.3, pp.266-280, 2000.
  8. I. Haritaoglu, D. Harwood, and L. S. Davis, "Real-time Surveillance of People and Their Activities." lEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.22, No.3, pp.809-830, 2000.
  9. M Yokoyama and T. Poggio, "A Contour based Moving Object Detection and Tracking," IEEE Intemational Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2005.
  10. L. Li, W. Huang, L. Y. H Gu, and Q. Tian, "Foreground Object Detection in Changing Background based on Color co-occurrence Statistics," IEEE Workshop on Applications of Computer Vision, 2002
  11. C. Stauffer and W. E. L. Grimson, "Adaptive Background Mixture Models for Real-time Tracking," IEEE Conference Computer Vision and Pattern Recogniton. 1999.
  12. A. Mittal and N. Paragios, "Motion-based Background Subtraction using Adaptive Kemel Density Estimation," IEEE Conference Computer Vision and Pattem Recongnition,Vol.2, pp.302-309,2004.
  13. A Elgammal, D. Harwood, and L. Davis, "Non-pararnetric Malel for Background Subtraction," European Conference Computer Vision,Vol.ll, pp.751-767, 2000.
  14. J. L. Barron, D. J. Fleet, and S. S. Beauchemin, "Performance of optical Flow Techniques," Intemational Joumal Computer Vision, Vol. 12, No.1, pp.43-77, 1994.
  15. J. H. Duncan and T. C. Chou, "On the Detection of Motion and the Olmputation of Optical Flow," IEEE Transactions on Pattern Analysis and l'vIachine Intelligence, Vol.14, No.3, pp.346-352, 1992
  16. V. Caselles and B. Coll, "Snakes in Movement," SIAM Joumal Nurnerical Analysis, Vol.33, pp 2445-2456,1996.
  17. S. S. Beauchemin and J L. Barron, "The Computation of Optical Flow," ACM Comuting Surveys, 1995.
  18. J Sethian, Level Methods and Fast Marching,Methods, Cambridge Unviersity. Press, 1999.
  19. L. Qiu and L. Li, "Contour Extraction of Moving Object," IEEE Intemational Conference Pattern Hecognition, Vol 2, pp.1427-1432, 1998.
  20. N. Paragios and R Deriche, "Geodesic Active Contours and Level Scts for the Detection and Tracking for Moving Objects," IEEE Transactions on Pattem Analysis and Machine Intelligence, Vol.22, No.3, pp.266-280, 2000.
  21. 김준철, 박은종,이준환, "벡터 마디언을 이용한 비디오 영상의 온랴인 배정 추출" 정보처리학회 논문지, 저113권 B권, 제5호, pp,226-280, 2000.
  22. F .H. Cbeng and Y. L. Chen, "Real Time Multiple Objects Tracking and Identification based on Discrete Wavelet Transforrn," Pattern Hecognition, Vol.39, pp. 1126-1139, 2003.