Pixel-Wise Histograms for Visual Segment Description and Applications
In this work we present an overview of several methods that extract information from a video segment using pixel-wise histograms or pixel-wise probability distributions. We will show that most of these algorithms that have been presented in the literature are specific implementations of a more general approach. Finally, we will present some applications based on these ideas to video segment retrieval and target detection in surveillance applications with static and dynamic backgrounds. We present a visual segment descriptor based on pixel-wise histograms that outperforms similar reviewed methods. In this way we show the advantages on this approach for this kind of problems.
KeywordsBackground Modeling Machine Intelligence Video Segment Visual Content Dynamic Background
Unable to display preview. Download preview PDF.
- 6.Monnet, A., Mittal, A., Paragios, N., Ramesh, V.: Background modeling and subtraction of dynamic scenes. In: Proc. Int. Conf. Computer Vision, pp. 1305–1312 (2003)Google Scholar
- 7.Mittal, A., Paragios, N.: Motion based background subtraction using kernel density estimation. In: Proc. Computer Vision and Pattern Recognition (2004)Google Scholar