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.
Original language | English |
---|---|
Pages (from-to) | 3399-3402 |
Number of pages | 4 |
Journal | Proceedings - International Conference on Image Processing, ICIP |
Volume | 2 |
Publication status | Published - 2004 |
Externally published | Yes |
Event | 2004 International Conference on Image Processing, ICIP 2004 - , Singapore Duration: 18 Oct 2004 → 21 Oct 2004 |