Long-Term Tracking Based on Multi-Feature Adaptive Fusion for Video Target
Summary :
The correlation filter-based trackers with an appearance model established by single feature have poor robustness to challenging video environment which includes factors such as occlusion, fast motion and out-of-view. In this paper, a long-term tracking algorithm based on multi-feature adaptive fusion for video target is presented. We design a robust appearance model by fusing powerful features including histogram of gradient, local binary pattern and color-naming at response map level to conquer the interference in the video. In addition, a random fern classifier is trained as re-detector to detect target when tracking failure occurs, so that long-term tracking is implemented. We evaluate our algorithm on large-scale benchmark datasets and the results show that the proposed algorithm have more accurate and more robust performance in complex video environment.
- Publication
- IEICE TRANSACTIONS on Information Vol.E101-D No.5 pp.1342-1349
- Publication Date
- 2018/05/01
- Publicized
- 2018/02/02
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2017EDP7245
- Type of Manuscript
- PAPER
- Category
- Fundamentals of Information Systems
Authors
Hainan ZHANG
China University of Mining and Technology
Yanjing SUN
China University of Mining and Technology
Song LI
China University of Mining and Technology
Wenjuan SHI
China University of Mining and Technology
Chenglong FENG
China University of Mining and Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Hainan ZHANG, Yanjing SUN, Song LI, Wenjuan SHI, Chenglong FENG, "Long-Term Tracking Based on Multi-Feature Adaptive Fusion for Video Target" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 5, pp. 1342-1349, May 2018, doi: 10.1587/transinf.2017EDP7245.
Abstract: The correlation filter-based trackers with an appearance model established by single feature have poor robustness to challenging video environment which includes factors such as occlusion, fast motion and out-of-view. In this paper, a long-term tracking algorithm based on multi-feature adaptive fusion for video target is presented. We design a robust appearance model by fusing powerful features including histogram of gradient, local binary pattern and color-naming at response map level to conquer the interference in the video. In addition, a random fern classifier is trained as re-detector to detect target when tracking failure occurs, so that long-term tracking is implemented. We evaluate our algorithm on large-scale benchmark datasets and the results show that the proposed algorithm have more accurate and more robust performance in complex video environment.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7245/_p
Copy
@ARTICLE{e101-d_5_1342,
author={Hainan ZHANG, Yanjing SUN, Song LI, Wenjuan SHI, Chenglong FENG, },
journal={IEICE TRANSACTIONS on Information},
title={Long-Term Tracking Based on Multi-Feature Adaptive Fusion for Video Target},
year={2018},
volume={E101-D},
number={5},
pages={1342-1349},
abstract={The correlation filter-based trackers with an appearance model established by single feature have poor robustness to challenging video environment which includes factors such as occlusion, fast motion and out-of-view. In this paper, a long-term tracking algorithm based on multi-feature adaptive fusion for video target is presented. We design a robust appearance model by fusing powerful features including histogram of gradient, local binary pattern and color-naming at response map level to conquer the interference in the video. In addition, a random fern classifier is trained as re-detector to detect target when tracking failure occurs, so that long-term tracking is implemented. We evaluate our algorithm on large-scale benchmark datasets and the results show that the proposed algorithm have more accurate and more robust performance in complex video environment.},
keywords={},
doi={10.1587/transinf.2017EDP7245},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Long-Term Tracking Based on Multi-Feature Adaptive Fusion for Video Target
T2 - IEICE TRANSACTIONS on Information
SP - 1342
EP - 1349
AU - Hainan ZHANG
AU - Yanjing SUN
AU - Song LI
AU - Wenjuan SHI
AU - Chenglong FENG
PY - 2018
DO - 10.1587/transinf.2017EDP7245
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2018
AB - The correlation filter-based trackers with an appearance model established by single feature have poor robustness to challenging video environment which includes factors such as occlusion, fast motion and out-of-view. In this paper, a long-term tracking algorithm based on multi-feature adaptive fusion for video target is presented. We design a robust appearance model by fusing powerful features including histogram of gradient, local binary pattern and color-naming at response map level to conquer the interference in the video. In addition, a random fern classifier is trained as re-detector to detect target when tracking failure occurs, so that long-term tracking is implemented. We evaluate our algorithm on large-scale benchmark datasets and the results show that the proposed algorithm have more accurate and more robust performance in complex video environment.
ER -
English
