Improved Multi-sampling Kernelized Correlation Filter Target Tracking Algorithm
Ying Hou, Yemei He
Available Online April 2019.
- https://doi.org/10.2991/icmeit-19.2019.107How to use a DOI?
- Target tracking; Kernelized Correlation Filter (KCF); PSNR; Multi-Sampling.
- In order to solve the tracking failure of kernelized correlation filter (KCF) tracking algorithm in the case of target fast motion and motion blur, proposing a multi-sampling tracking algorithm based on KCF. Firstly, a PSNR-based judgment mechanism is introduced to determine whether the current frame target is tracking errors. If the tracking error occurs, the search range is extended to a muti-sampling search area. Finally re-detect the target of the current frame. The improved algorithm of this paper is compared with several classical correlation filter target tracking algorithms in the OTB video dataset. The experimental results show that the precision of this algorithm is 0.732 and the success rate is 0.575, ranking first, which is 5.3% and 4.3% higher than the KCF algorithm. Especially when the target has fast motion and motion blur, it has stronger tracking accuracy.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Ying Hou AU - Yemei He PY - 2019/04 DA - 2019/04 TI - Improved Multi-sampling Kernelized Correlation Filter Target Tracking Algorithm PB - Atlantis Press SP - 671 EP - 674 SN - 2352-538X UR - https://doi.org/10.2991/icmeit-19.2019.107 DO - https://doi.org/10.2991/icmeit-19.2019.107 ID - Hou2019/04 ER -