Image and Graphics, International Conference on (2009)
Xi'an, Shanxi, China
Sept. 20, 2009 to Sept. 23, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICIG.2009.124
This paper presents approach for an automated surveillance system which performs human detection and tracking across multiple non-overlapping cameras. Emphasis is put at single camera level where motion based segmentation is achieved using optical flow estimation. Feature matching and region-based shape descriptors are used for tracking. The proposed approach then extends feature and region-based shape matching across fields of view (FOV) of multiple non-overlapping cameras in order to obtain inter-camera correspondences. Evaluation of the system was performed in different scenarios which verify that the proposed method can efficiently perform video motion tracking with high processing speeds.
computer vision, surveillance, pattern recognition, image analysis, image processing
M. O. Mehmood and A. Khawaja, "Multi-camera Based Human Tracking with Non-overlapping Fields of View," Image and Graphics, International Conference on(ICIG), Xi'an, Shanxi, China, 2009, pp. 313-318.