Abstract
Background subtraction is a common technique used for motion tracking. It involves segmenting the foreground from the background in a given set of video frames. Background subtraction as proposed by Stauffer-Grimson [1] models each pixel using a mixture of Gaussians. The parameters of the Gaussian model are adaptive, and can adjust to gradual changes in image intensity over time. But in cases when the lighting change in the captured video sequence is sudden, like when the camera's automatic gain control (AGC) self adjusts the intensity of the overall image, such model based methods of background subtraction fail to adapt quickly to such a sudden change in image intensity. We propose a technique to automatically estimate the extent of camera AGC, and then use the information to add an additional block into any model based method such as the Stauffer-Grimson method to compensate for camera AGC while doing background subtraction.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
