Adaptive Scale Correlation Tracking based on SVM

DOI

10.2991/fmsmt-17.2017.147How to use a DOI?

Keywords

Object tracking; SVM; Multi-scale; Correlation filter

Abstract

Although the correlation filter-based trackers achieve the competitive results both on accuracy and robustness, there is still a need to improve the overall tracking capability. Focusing on the issue that the correlation filter-based trackers algorithm has poor performance in handling scale-variant target and Occlusion, this paper presents a multi-scale correlation filter algorithm combined with SVM detector to solve the above problems. Firstly, by introducing the scale factor into the kernel matrix to improve the performance of correlation filter processing scale transform. Then we trained an online SVM detector to retrieve the target when the target is occluded, and adaptively adjust the learning rate of the model. By comparing with the other six outstanding tracking algorithm, experimental results show that the proposed approach could estimate the object state accurately and handle the object occlusion problem effectively.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Kang Yuan
AU  - Da-peng Wei
PY  - 2017/04
DA  - 2017/04
TI  - Adaptive Scale Correlation Tracking based on SVM
BT  - Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)
PB  - Atlantis Press
SP  - 756
EP  - 761
SN  - 2352-5401
UR  - https://doi.org/10.2991/fmsmt-17.2017.147
DO  - 10.2991/fmsmt-17.2017.147
ID  - Yuan2017/04
ER  -