Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/116528
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: Multi-Task Structure-Aware Context Modeling for Robust Keypoint-Based Object Tracking
Author: Li, X.
Zhao, L.
Ji, W.
Wu, Y.
Wu, F.
Yang, M.
Tao, D.
Reid, I.
Citation: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019; 41(4):915-927
Publisher: IEEE
Issue Date: 2019
ISSN: 0162-8828
2160-9292
Statement of
Responsibility: 
Xi Li, Liming Zhao, Wei Ji, Yiming Wu, Fei Wu, Ming-Hsuan Yang, Dacheng Tao, Ian Reid
Abstract: In the fields of computer vision and graphics, keypoint-based object tracking is a fundamental and challenging problem, which is typically formulated in a spatio-temporal context modeling framework. However, many existing keypoint trackers are incapable of effectively modeling and balancing the following three aspects in a simultaneous manner: temporal model coherence across frames, spatial model consistency within frames, and discriminative feature construction. To address this problem, we propose a robust keypoint tracker based on spatio-temporal multi-task structured output optimization driven by discriminative metric learning. Consequently, temporal model coherence is characterized by multi-task structured keypoint model learning over several adjacent frames; spatial model consistency is modeled by solving a geometric verification based structured learning problem; discriminative feature construction is enabled by metric learning to ensure the intra-class compactness and inter-class separability. To achieve the goal of effective object tracking, we jointly optimize the above three modules in a spatio-temporal multi-task learning scheme. Furthermore, we incorporate this joint learning scheme into both single-object and multi-object tracking scenarios, resulting in robust tracking results. Experiments over several challenging datasets have justified the effectiveness of our single-object and multi-object trackers against the state-of-the-art.
Keywords: Keypoint tracking; context modeling; structure learning; multi-task learning; metric learning
Rights: © 2018 IEEE
RMID: 0030102454
DOI: 10.1109/TPAMI.2018.2818132
Appears in Collections:Australian Institute for Machine Learning publications
Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.