Feature Adaptive Correlation Tracking

Yulong XU; Yang LI; Jiabao WANG; Zhuang MIAO; Hang LI; Yafei ZHANG

doi:10.1587/transinf.2016EDL8164

Feature Adaptive Correlation Tracking

Yulong XU, Yang LI, Jiabao WANG, Zhuang MIAO, Hang LI, Yafei ZHANG

Full Text Views

0

Cite this

Summary :

Feature extractor plays an important role in visual tracking, but most state-of-the-art methods employ the same feature representation in all scenes. Taking into account the diverseness, a tracker should choose different features according to the videos. In this work, we propose a novel feature adaptive correlation tracker, which decomposes the tracking task into translation and scale estimation. According to the luminance of the target, our approach automatically selects either hierarchical convolutional features or histogram of oriented gradient features in translation for varied scenarios. Furthermore, we employ a discriminative correlation filter to handle scale variations. Extensive experiments are performed on a large-scale benchmark challenging dataset. And the results show that the proposed algorithm outperforms state-of-the-art trackers in accuracy and robustness.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.3 pp.594-597

Publication Date: 2017/03/01

Publicized: 2016/11/28

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDL8164

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Authors

Yulong XU
  PLA University of Science and Technology (PLAUST)
Yang LI
  PLA University of Science and Technology (PLAUST)
Jiabao WANG
  PLA University of Science and Technology (PLAUST)
Zhuang MIAO
  PLA University of Science and Technology (PLAUST)
Hang LI
  PLA University of Science and Technology (PLAUST)
Yafei ZHANG
  PLA University of Science and Technology (PLAUST)

Keyword

visual tracking, correlation filter, feature selection, convolutional neural networks, scale estimation

Cite this

Copy

Yulong XU, Yang LI, Jiabao WANG, Zhuang MIAO, Hang LI, Yafei ZHANG, "Feature Adaptive Correlation Tracking" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 3, pp. 594-597, March 2017, doi: 10.1587/transinf.2016EDL8164.
Abstract: Feature extractor plays an important role in visual tracking, but most state-of-the-art methods employ the same feature representation in all scenes. Taking into account the diverseness, a tracker should choose different features according to the videos. In this work, we propose a novel feature adaptive correlation tracker, which decomposes the tracking task into translation and scale estimation. According to the luminance of the target, our approach automatically selects either hierarchical convolutional features or histogram of oriented gradient features in translation for varied scenarios. Furthermore, we employ a discriminative correlation filter to handle scale variations. Extensive experiments are performed on a large-scale benchmark challenging dataset. And the results show that the proposed algorithm outperforms state-of-the-art trackers in accuracy and robustness.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8164/_p

Copy

@ARTICLE{e100-d_3_594,
author={Yulong XU, Yang LI, Jiabao WANG, Zhuang MIAO, Hang LI, Yafei ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Feature Adaptive Correlation Tracking},
year={2017},
volume={E100-D},
number={3},
pages={594-597},
abstract={Feature extractor plays an important role in visual tracking, but most state-of-the-art methods employ the same feature representation in all scenes. Taking into account the diverseness, a tracker should choose different features according to the videos. In this work, we propose a novel feature adaptive correlation tracker, which decomposes the tracking task into translation and scale estimation. According to the luminance of the target, our approach automatically selects either hierarchical convolutional features or histogram of oriented gradient features in translation for varied scenarios. Furthermore, we employ a discriminative correlation filter to handle scale variations. Extensive experiments are performed on a large-scale benchmark challenging dataset. And the results show that the proposed algorithm outperforms state-of-the-art trackers in accuracy and robustness.},
keywords={},
doi={10.1587/transinf.2016EDL8164},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Feature Adaptive Correlation Tracking
T2 - IEICE TRANSACTIONS on Information
SP - 594
EP - 597
AU - Yulong XU
AU - Yang LI
AU - Jiabao WANG
AU - Zhuang MIAO
AU - Hang LI
AU - Yafei ZHANG
PY - 2017
DO - 10.1587/transinf.2016EDL8164
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2017
AB - Feature extractor plays an important role in visual tracking, but most state-of-the-art methods employ the same feature representation in all scenes. Taking into account the diverseness, a tracker should choose different features according to the videos. In this work, we propose a novel feature adaptive correlation tracker, which decomposes the tracking task into translation and scale estimation. According to the luminance of the target, our approach automatically selects either hierarchical convolutional features or histogram of oriented gradient features in translation for varied scenarios. Furthermore, we employ a discriminative correlation filter to handle scale variations. Extensive experiments are performed on a large-scale benchmark challenging dataset. And the results show that the proposed algorithm outperforms state-of-the-art trackers in accuracy and robustness.
ER -