A Study on the Selection of ROI and Trace Under the Multiple Object Environments

  • Gwangseok Lee
  • Gangin Hur
  • Youngsub Kim
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 235)


This paper is for the trace technology of the object after choosing a specific object as ROI (region of interest) about the object detection with background separation technique and the detected object. Here, the modified AMF is proposed as an effective background separation technique. This method allows to choose ROI region effectively against the image including a variety of objects, by the combination of covariance matrix using regional dispersion size after separating the background and object with the improved AMF. In the result, the modified AMF is strong on noise like the minute movement from illumination change in aspect of pixel accuracy. CAMShift algorithm against selected ROI region is used to trace the detected object more effectively. As a result, it is found that processing time increases.


Background separation Selection of ROI BGS algorithm Modified AMF Object trace using CAMShift Covariance descriptor 


  1. 1.
    Aggarwal JK, Cai O (1999) Human motion analysis. Comput Vis Image Underst 73(3):428–440Google Scholar
  2. 2.
    Hu W, Tan T, Wang L, Maybank S (2004) A survey on visual surveillance of object motion and behaviors. Syst Man Cybern Part C 34(3):334–352Google Scholar
  3. 3.
    Stauffer C, Grimsion W (1999) Adaptive background mixture models for real-time tracking. CVRP99 2:252Google Scholar
  4. 4.
    Oliver N, Rosario B, Pentland A (2000) A Bayesian computer vision system for modeling human interactions. IEEE PAMI, 22:831–843Google Scholar
  5. 5.
    Wren CR, Azarbayejani A, Darrell T, Pentland AP (1997) Pfinder: real-time tracking of the human body. IEEE PAMI 19(7):780–785Google Scholar
  6. 6.
    Zivkovic Z, van der Heijden, F (2006) Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recogn Lett 27(7)773–780Google Scholar
  7. 7.
    McFarlane N, Schofield C (1995) Segmentation and tracking of piglets in images. MVA 8:187–193Google Scholar
  8. 8.
    Calderara S, Melli R, Prati A, Cucchiara R (2006) Reliable background suppression for complex scene. In: VSSN06, pp 211–214Google Scholar
  9. 9.
    Cucchiara R, Grana C, Piccardi M, Prati AA (2003) Detecting moving objects, ghost, and shadows in video streams. IEEE PAMI 25(10):1337–1342Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  1. 1.Department of Electronics EngineeringGyeongnam National University of Science and TechnologyJinjuKorea
  2. 2.Department of Electronics EngineeringDong-A UniversityBusanKorea

Personalised recommendations