Abstract
This paper presents a framework to deal with occlusions when detecting people for the tracking in the image sequences of a stationary surveillance video camera. Unlike the cases of most existing techniques, people are in low-resolution and the detected foreground images are noisy. As the small sizes of target people make it difficult to build statistical shape or motion models, techniques proposed use simple features of the bounding boxes of target people such as position and size. Each foreground region in a bounding box is identified in independent, partially occluded, or completely occluded state, and the state is updated during tracking. Proposed technique is tested with an experiment of counting the number of pedestrians in a scene.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Collins, R.T., Lipton, A.J., Kanade, T.: Introduction to the Special Section on Video Surveillance. IEEE Trans. Pattern Analysis and Machine Intelligence 22(8), 745–746 (2000)
Wren, C.R., Azarbayejani, A., Darrell, T., Pentland, A.P.: Pfinder: Real-Time Tracking of the Human Body. IEEE Trans. Pattern Analysis and Machine Intelligence 19(7), 780–785 (1997)
Khan, S., Shah, M.: Tracking People in Presence of Occlusion. In: Proc. Asian Conf. Computer Vision (2000)
Haritaoglu, I., Harwood, D., Davis, L.S.: W4 Who? When? Where? What? A Real Time System for Detecting and Tracking People. In: Proc. Conf. Face and Gesture Recognition, pp. 222–227 (1998)
Sindhu, A.J., Morris, T.: A Region Based Approach to Tracking People Before, During, and After Occlusions. In: Proc. IASTED Conf. Visualization, Imaging and Image Processing (2004)
Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing Action at a Distance. In: Proc. IEEE Int. Conf. Computer Vision, pp. 726–733 (2003)
Heikkila, J., Silven, O.: A Real-Time System for Monitoring of Cyclists and Pedestrians. In: Proc. IEEE Workshop on Visual Surveillance, pp. 74–81 (1999)
Fujiyoshi, H., Lipton, A.: Real-time Human Motion Analysis by Skeletonization. In: Proc. IEEE Workshop on Application of Computer Vision, pp. 15–21 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Do, Y. (2005). Region Based Detection of Occluded People for the Tracking in Video Image Sequences. In: Gagalowicz, A., Philips, W. (eds) Computer Analysis of Images and Patterns. CAIP 2005. Lecture Notes in Computer Science, vol 3691. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11556121_102
Download citation
DOI: https://doi.org/10.1007/11556121_102
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28969-2
Online ISBN: 978-3-540-32011-1
eBook Packages: Computer ScienceComputer Science (R0)