Traditional Approaches in Background Modeling for Static Cameras

• Published in: Background Modeling and Foreground Detection for Video Surveillance pp. 23 - 76
• Format: Book Chapter
• Language: English
• Published: Chapman and Hall/CRC 2015
• Subjects: Background Maintenance; MO; Background Model; SVDD; Gradual Illumination; GNN; Foreground Detection; Foreground Mask; Camera Jitter; Ground Truth Images; SVR; Ti Ti; Background Subtraction; Background Image; RGB Color Space; Background Subtraction Algorithms; Foreground Objects; Original Test Image; Ten Si Ty; Background Subtraction Methods; Dynamic Backgrounds; Background Initialization; Subspace Learning
• DOI: 10.1201/b17223-7

Bt+1 (x, y) = (1− α)Bt (x, y) + αIt (x, y) (1.1) where α is the learning rate which is a constant in [0, 1]. Bt and It are the background and the current image at time t, respectively. The main disadvantage of this scheme is that the value of pixels classified as foreground are used in the computation of the new background and so polluted the background image. To solve this problem, some authors used a selective maintenance scheme that consists of updating the new background image with different learning rate depending on the previous classification of a pixel into foreground or background:Bt+1 (x, y) = (1− α)Bt (x, y) + αIt (x, y) (1.2) if (x, y) is backgroundBt+1 (x, y) = (1− β)Bt (x, y) + βIt (x, y) (1.3) if (x, y) is foregroundCamerasHere, the idea is to adapt very quickly a pixel classified as background and very slowly a pixel classified as foreground. For this reason, β << α and usually β = 0. So the Equation (1.3) becomes:Bt+1 (x, y) = Bt (x, y) (1.4)But the problem is that erroneous classification may result in a permanent incorrect background model. This problem can be addressed by a fuzzy adaptive scheme which takes into account the uncertainty of the classification. This can be achieved by graduating the update rule using the result of the foreground detection such as in [18].