In this study, we address the problem of online RGB-D tracking which confronted with various challenges caused by deformation, occlusion, background clutter, and abrupt motion. Various trackers have different strengths and weaknesses, and thus a single tracker can merely perform well in specific scenarios. We propose a 3D tracker-level fusion algorithm (TLF3D) which enhances the strengths of different trackers and suppresses their weaknesses to achieve robust tracking performance in various scenarios. The fusion result is generated from outputs of base trackers by optimizing an energy function considering both the 3D cube attraction and 3D trajectory smoothness. In addition, three complementary base RGB-D trackers with intrinsically different tracking components are proposed for the fusion algorithm. We perform extensive experiments on a large-scale RGB-D benchmark dataset. The evaluation results demonstrate the effectiveness of the proposed fusion algorithm and the superior performance of the proposed TLF3D tracker against state-of-the-art RGB-D trackers.
Ning AN
Chinese Academy of Sciences,University of Chinese Academy of Sciences
Xiao-Guang ZHAO
Chinese Academy of Sciences,University of Chinese Academy of Sciences
Zeng-Guang HOU
Chinese Academy of Sciences,University of Chinese Academy of Sciences
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.
Copy
Ning AN, Xiao-Guang ZHAO, Zeng-Guang HOU, "3D Tracker-Level Fusion for Robust RGB-D Tracking" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 8, pp. 1870-1881, August 2017, doi: 10.1587/transinf.2016EDP7498.
Abstract: In this study, we address the problem of online RGB-D tracking which confronted with various challenges caused by deformation, occlusion, background clutter, and abrupt motion. Various trackers have different strengths and weaknesses, and thus a single tracker can merely perform well in specific scenarios. We propose a 3D tracker-level fusion algorithm (TLF3D) which enhances the strengths of different trackers and suppresses their weaknesses to achieve robust tracking performance in various scenarios. The fusion result is generated from outputs of base trackers by optimizing an energy function considering both the 3D cube attraction and 3D trajectory smoothness. In addition, three complementary base RGB-D trackers with intrinsically different tracking components are proposed for the fusion algorithm. We perform extensive experiments on a large-scale RGB-D benchmark dataset. The evaluation results demonstrate the effectiveness of the proposed fusion algorithm and the superior performance of the proposed TLF3D tracker against state-of-the-art RGB-D trackers.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7498/_p
Copy
@ARTICLE{e100-d_8_1870,
author={Ning AN, Xiao-Guang ZHAO, Zeng-Guang HOU, },
journal={IEICE TRANSACTIONS on Information},
title={3D Tracker-Level Fusion for Robust RGB-D Tracking},
year={2017},
volume={E100-D},
number={8},
pages={1870-1881},
abstract={In this study, we address the problem of online RGB-D tracking which confronted with various challenges caused by deformation, occlusion, background clutter, and abrupt motion. Various trackers have different strengths and weaknesses, and thus a single tracker can merely perform well in specific scenarios. We propose a 3D tracker-level fusion algorithm (TLF3D) which enhances the strengths of different trackers and suppresses their weaknesses to achieve robust tracking performance in various scenarios. The fusion result is generated from outputs of base trackers by optimizing an energy function considering both the 3D cube attraction and 3D trajectory smoothness. In addition, three complementary base RGB-D trackers with intrinsically different tracking components are proposed for the fusion algorithm. We perform extensive experiments on a large-scale RGB-D benchmark dataset. The evaluation results demonstrate the effectiveness of the proposed fusion algorithm and the superior performance of the proposed TLF3D tracker against state-of-the-art RGB-D trackers.},
keywords={},
doi={10.1587/transinf.2016EDP7498},
ISSN={1745-1361},
month={August},}
Copy
TY - JOUR
TI - 3D Tracker-Level Fusion for Robust RGB-D Tracking
T2 - IEICE TRANSACTIONS on Information
SP - 1870
EP - 1881
AU - Ning AN
AU - Xiao-Guang ZHAO
AU - Zeng-Guang HOU
PY - 2017
DO - 10.1587/transinf.2016EDP7498
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2017
AB - In this study, we address the problem of online RGB-D tracking which confronted with various challenges caused by deformation, occlusion, background clutter, and abrupt motion. Various trackers have different strengths and weaknesses, and thus a single tracker can merely perform well in specific scenarios. We propose a 3D tracker-level fusion algorithm (TLF3D) which enhances the strengths of different trackers and suppresses their weaknesses to achieve robust tracking performance in various scenarios. The fusion result is generated from outputs of base trackers by optimizing an energy function considering both the 3D cube attraction and 3D trajectory smoothness. In addition, three complementary base RGB-D trackers with intrinsically different tracking components are proposed for the fusion algorithm. We perform extensive experiments on a large-scale RGB-D benchmark dataset. The evaluation results demonstrate the effectiveness of the proposed fusion algorithm and the superior performance of the proposed TLF3D tracker against state-of-the-art RGB-D trackers.
ER -