A hierarchical approach to robust background subtraction using color and gradient information
- 27 August 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 11, 22-27
- https://doi.org/10.1109/motion.2002.1182209
Abstract
We present a background subtraction method that uses multiple cues to detect objects robustly in adverse conditions. The algorithm consists of three distinct levels, i.e., pixel level, region level and frame level. At the pixel level, statistical models of gradients and color are separately used to classify each pixel as belonging to background or foreground. In the region level, foreground pixels obtained from the color based subtraction are grouped into regions and gradient based subtraction is then used to make inferences about the validity of these regions. Pixel based models are updated based on decisions made at the region level. Finally, frame level analysis is performed to detect global illumination changes. Our method provides the solution to some of the common problems that are not addressed by most background subtraction algorithms, such as fast illumination changes, repositioning of static background objects, and initialization of background model with moving objects present in the scene.Keywords
This publication has 10 references indexed in Scilit:
- Analysis and detection of shadows in video streams: a comparative evaluationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The systematic design and analysis cycle of a vision system: a case study in video surveillancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A statistical approach to background subtraction for surveillance systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Detection and location of people in video images using adaptive fusion of color and edge informationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Integrating intensity and texture differences for robust change detectionIEEE Transactions on Image Processing, 2002
- A Bayesian computer vision system for modeling human interactionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Learning patterns of activity using real-time trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- W/sup 4/: real-time surveillance of people and their activitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Wallflower: principles and practice of background maintenancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Pfinder: real-time tracking of the human bodyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997