Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10341104 | Computers & Electrical Engineering | 2014 | 10 Pages |
Abstract
The detection and extraction of target blobs is implemented by an adaptive Gaussian mixture background modeling. Its computational complexity can be greatly reduced because of frame reconstruction and the flexibility of Gaussian mixture components. The unscented Kalman filter is used to dynamically predict the target position and estimate the tracking uncertainty. The target association combining homography transformation with hue histogram matching implements the identity of the same target in different views. For the same target, the confidence measure based on the target size and the tracking uncertainty is defined to achieve optimal node selection. And then the new camera node continues the target tracking and the next node selection process.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Networks and Communications
Authors
Yong Wang, Dianhong Wang, Wu Fang,