Abstract
Background modeling is a popular issue in computer vision society during the past few decades. We analyze the usual pixel-level approach and build an adaptive background mixture model with spatio-temporal samples called STS. These samples are described based on a joint domain-range formulation and the pixel is classified with a weight marginal probability density function. On-line update including proximal sample selection, parameter learning, and neighbor update are used to regulate the model to adapt to varying scenes. We perform a bootstrap modeling experiment, and results show that our method outperforms other widely adopted techniques which use only intensity or region description as pixel feature with higher F-measure on most datasets. And our method is a matched rival to combination methods which use both pixel intensity and region description.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.