Abstract
In this paper, we describe a system on automatically tracking people in indoor environment. Parametric Estimation methods are adopted in training images to obtain means and covariance of the background pixels. They are processed in pixel classification step to extract moving people and eliminate their shadows. Our tracking algorithm consists of two levels: region level and blob level. The region level tracks a whole human by utilizing the position information of the detected persons. The EM algorithm is adopted at the blob level to segment human image into different parts. When region level tracking fails, the system switches to blob-level tracking. Average Bhattacharyya distances between corresponding blobs of consecutive frames are calculated to get the correct match between different regions. Potential applications of the proposed algorithm include HCI and visual surveillance. Experimental results are given to demonstrate the robustness and efficiency of our algorithm.
This work is funded by research grants from the NSFC(Grant No. 59825105) and the Chinese Academy of Sciences.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Reference
Q. Cai and J.K. Aggarwal, “Tracking Human Motion Using Multiple Cameras,” Proc. Int.l Conf. Pattern and Recognition, pp. 68–72, Vienna, Austria, Aug. 1996.
Q. Cai and J.K. Aggarwal, “Tracking Human Motion in Structured Environments Using a Distributed-Camera System”, IEEE Tran. PAMI, Vol 21, No. 12, November 1999.
I. Haritaoglu, D. Harwook, and H. Davis, “W4: Who, What, When, Where: A Real-Time System for Detecting and Tracking People”. 1998.
C.R. Wren, A. Azarbayejani, T. Darrell and A. Pentland, “Pfinder: Real-time Tracking of Human Body”. IEEE Transactions on Pattern Analysis and Machine Intelligence, July 1997, vol 19,no 7, pp. 780–185.
H.Z. Sun, T. Feng and T.N. Tan, “Robust extraction of moving objects from image sequences”. In Proceedings of ACCV2000.
T. Horprasert, D. Harwood, L. S. Davis, “A Robust Background Substraction and Shadow Detection”. In Proceedings of ACCV2000.
M.D. Alder, “An Introduction to Pattern Recognition: Statistical, Neural Net and Syntactic Methods of Getting Robots to See”, http://ciips.ee.uwa.edu.au/~mike/PatRec/node95.html, September 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sun, H., Yang, H., Tan, T. (2000). Multi-level Human Tracking. In: Tan, T., Shi, Y., Gao, W. (eds) Advances in Multimodal Interfaces — ICMI 2000. ICMI 2000. Lecture Notes in Computer Science, vol 1948. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-40063-X_45
Download citation
DOI: https://doi.org/10.1007/3-540-40063-X_45
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41180-2
Online ISBN: 978-3-540-40063-9
eBook Packages: Springer Book Archive