Please use this identifier to cite or link to this item:
Title: Video tracking using learned hierarchical features
Authors: Wang, Gang
Chan, Kap Luk
Liu, Ting
Yang, Qingxiong
Wang, Li
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Issue Date: 2015
Source: Wang, L., Liu, T., Wang, G., Chan, K. L., & Yang, Q. (2015). Video tracking using learned hierarchical features. IEEE transactions on image processing, 24(4), 1424-1435.
Series/Report no.: IEEE transactions on image processing
Abstract: In this paper, we propose an approach to learn hierarchical features for visual object tracking. First, we offline learn features robust to diverse motion patterns from auxiliary video sequences. The hierarchical features are learned via a two-layer convolutional neural network. Embedding the temporal slowness constraint in the stacked architecture makes the learned features robust to complicated motion transformations, which is important for visual object tracking. Then, given a target video sequence, we propose a domain adaptation module to online adapt the pre-learned features according to the specific target object. The adaptation is conducted in both layers of the deep feature learning module so as to include appearance information of the specific target object. As a result, the learned hierarchical features can be robust to both complicated motion transformations and appearance changes of target objects. We integrate our feature learning algorithm into three tracking methods. Experimental results demonstrate that significant improvement can be achieved using our learned hierarchical features, especially on video sequences with complicated motion transformations.
ISSN: 1057-7149
DOI: 10.1109/TIP.2015.2403231
Rights: © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [Article DOI:].
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles

Files in This Item:
File Description SizeFormat 
Video Tracking Using Learned Hierarchical Features.pdf2.52 MBAdobe PDFThumbnail

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.