Title :
Mean-shift background image modelling
Author :
Piccardi, Massimo ; Jan, Z.
Author_Institution :
Comput. Vision Res. Group, Univ. of Technol., Sydney, NSW, Australia
Abstract :
Background modelling is widely used in computer vision for the detection of foreground objects in a frame sequence. The more accurate the background model, the more correct is the detection of the foreground objects. In this paper, we present an approach to background modelling based on a mean-shift procedure. The mean shift vector convergence properties enable the system to achieve reliable background modelling. In addition, histogram-based computation and the new concept of local basins of attraction allow us to meet the stringent real-time requirements of video processing.
Keywords :
image sequences; object detection; video signal processing; foreground object detection; frame sequence; histogram-based computation; mean shift vector convergence; mean-shift background image modelling; video processing; Application software; Australia; Bandwidth; Computational efficiency; Computer vision; Convergence; Histograms; Object detection; Smoothing methods; Surveillance;
Conference_Titel :
Image Processing, 2004. ICIP '04. 2004 International Conference on
Print_ISBN :
0-7803-8554-3
DOI :
10.1109/ICIP.2004.1421844