"Visual tracking based on compressive sensing and particle filter"
Title | "Visual tracking based on compressive sensing and particle filter" |
Publication Type | Conference Paper |
Year of Publication | 2015 |
Authors | W. Huang, J. Gu, X. Ma |
Conference Name | 2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE) |
Date Published | May 2015 |
Publisher | IEEE |
ISBN Number | 978-1-4799-5829-0 |
Accession Number | 15239766 |
Keywords | Classification algorithms, compressed sensing, compressive sensing theory, feature extraction, filtering algorithms, illumination variation, image classification, image filtering, particle filter, particle filtering (numerical methods), Particle filters, pose variation, pubcrawl170104, random projection, Sparse matrices, target tracking, visual tracking |
Abstract | A robust appearance model is usually required in visual tracking, which can handle pose variation, illumination variation, occlusion and many other interferences occurring in video. So far, a number of tracking algorithms make use of image samples in previous frames to update appearance models. There are many limitations of that approach: 1) At the beginning of tracking, there exists no sufficient amount of data for online update because these adaptive models are data-dependent and 2) in many challenging situations, robustly updating the appearance models is difficult, which often results in drift problems. In this paper, we proposed a tracking algorithm based on compressive sensing theory and particle filter framework. Features are extracted by random projection with data-independent basis. Particle filter is employed to make a more accurate estimation of the target location and make much of the updated classifier. The robustness and the effectiveness of our tracker have been demonstrated in several experiments. |
URL | https://ieeexplore.ieee.org/document/7129491 |
DOI | 10.1109/CCECE.2015.7129491 |
Citation Key | 7129491 |
- particle filter
- visual tracking
- target tracking
- Sparse matrices
- random projection
- pubcrawl170104
- pose variation
- Particle filters
- particle filtering (numerical methods)
- Classification algorithms
- image filtering
- image classification
- illumination variation
- filtering algorithms
- feature extraction
- compressive sensing theory
- compressed sensing