.png){kind=icon}
.png){kind=icon}
Return
Accelerated multi-feature based compressive sensing tracking
.png){kind=icon}
PRE
AI
DOI：10.1016/j.infrared.2015.05.017.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Based on the framework of multi-feature based compressive sensing tracking, a tracking algorithm with less recovery is designed to accelerate the tracking process. In the proposed framework, a multiple features composed target template and a trivial template which modules occlusion, interruption and noises are normalized to form a orthogonal dictionary. With this model, the sparsity is achieved via a compressive sensing approach without nonnegative constraints, then, instead of recovery, a residual between compressive sensed candidate and target is used to evaluate the likelihood of particle, the rationality of this replacement is proofed. To gain more robustness, the target template is adaptively updated according to the Bhattacharyya coefficients and the sparsity coefficients. (C) 2015 Elsevier B.V. All rights reserved.
Keywords:
Visual tracking
Compressive sensing
Multi-features
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
3.4
Papers:
5.8K
Citations:
1.2W
Organization
No organization information available