Motion-based background subtraction using adaptive kernel density estimation
Ankush Mittal, Nikos Paragios A · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2004
Background modeling is an important component of many vision systems. Existing work in the area has mostly addressed scenes that consist of static or quasi-static structures. When the scene exhibits a persistent dynamic behavior in time, such an assumption is violated and detection performance deteriorates. In this paper, we propose a new method for the modeling and subtraction of such scenes. Towards the modeling of the dynamic characteristics, optical flow is computed and utilized as a feature in a higher dimensional space. Inherent ambiguities in the computation of features are addressed by using a data-dependent bandwidth for density estimation using kernels. Extensive experiments demonstrate the utility and performance of the proposed approach.
Cited by 590 works. doi:10.1109/cvpr.2004.1315179
Authors
References
- An Iterative Image Registration Technique with an Application to Stereo Vision
- Determining optical flow
- Determining Optical Flow
- Pfinder: real-time tracking of the human body
- Performance of optical flow techniques
- A computational framework and an algorithm for the measurement of visual motion
- Using adaptive tracking to classify and monitor activities in a site
- Image Segmentation in Video Sequences: A Probabilistic Approach
- Non-parametric Model for Background Subtraction
- Wallflower: principles and practice of background maintenance