Deformable object tracking with gated fusion
Publication Type
Journal Article
Publication Date
8-2019
Abstract
The tracking-by-detection framework receives growing attention through the integration with the convolutional neural networks (CNNs). Existing tracking-by-detection-based methods, however, fail to track objects with severe appearance variations. This is because the traditional convolutional operation is performed on fixed grids, and thus may not be able to find the correct response while the object is changing pose or under varying environmental conditions. In this paper, we propose a deformable convolution layer to enrich the target appearance representations in the tracking-by-detection framework. We aim to capture the target appearance variations via deformable convolution, which adaptively enhances its original features. In addition, we also propose a gated fusion scheme to control how the variations captured by the deformable convolution affect the original appearance. The enriched feature representation through deformable convolution facilitates the discrimination of the CNN classifier on the target object and background. The extensive experiments on the standard benchmarks show that the proposed tracker performs favorably against the state-of-the-art methods.
Keywords
Visual tracking, deformable convolution, gating
Discipline
Information Security
Research Areas
Information Systems and Management
Publication
IEEE Transactions on Image Processing
Volume
28
Issue
8
First Page
3766
Last Page
3777
ISSN
1057-7149
Identifier
10.1109/TIP.2019.2902784
Publisher
Institute of Electrical and Electronics Engineers
Citation
LIU, Wenxi; SONG, Yibing; CHEN, Dengsheng; HE, Shengfeng; YU, Yuanlong; YAN, Tao; HANCKE, Gerhard P.; and LAU, Rynson W.H..
Deformable object tracking with gated fusion. (2019). IEEE Transactions on Image Processing. 28, (8), 3766-3777.
Available at: https://ink.library.smu.edu.sg/sis_research/7853
Additional URL
https://doi.org/10.1109/TIP.2019.2902784