Authors:
C. Gabard
1
;
C. Achard
2
;
L. Lucat
1
and
P. Sayd
1
Affiliations:
1
CEA and LIST, France
;
2
UPMC Univ Paris 06, France
Keyword(s):
MOG, SMOG, SGMM, Background Subtraction, Tracking, Foreground and Object Detection.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Applications and Services
;
Camera Networks and Vision
;
Color and Texture Analyses
;
Computer Vision, Visualization and Computer Graphics
;
Features Extraction
;
Geometry and Modeling
;
Image and Video Analysis
;
Image-Based Modeling
;
Motion, Tracking and Stereo Vision
;
Optical Flow and Motion Analyses
;
Pattern Recognition
;
Segmentation and Grouping
;
Shape Representation and Matching
;
Software Engineering
;
Tracking and Visual Navigation
;
Video Surveillance and Event Detection
Abstract:
Background subtraction is often one of the first tasks involved in video surveillance applications. Classical methods only use temporal modelling of the background pixels. Using pixel blocks with fixed size allows robust detection but these approaches lead to a loss of precision. We propose in this paper a model of the scene which combines a temporal and local model with a spatial model. This whole representation of the scene both models fixed elements (background) and mobile ones. This allows improving detection accuracy by transforming the detection problem in a two classes classification problem.