Online Deformable Object Tracking Based on Structure-Aware Hyper-Graph

Recent advances in online visual tracking focus on designing part-based model to handle the deformation and occlusion challenges. However, previous methods usually consider only the pairwise structural dependences of target parts in two consecutive frames rather than the higher order constraints in...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2016-08, Vol.25 (8), p.3572-3584
Main Authors: Du, Dawei, Qi, Honggang, Li, Wenbo, Wen, Longyin, Huang, Qingming, Lyu, Siwei
Format: Article
Language:English
Subjects:
deformable object tracking
Deformation
dense subgraph searching
Formability
Frames
Image segmentation
Mathematical models
Methods
Object tracking
Occlusion
Online
Online tracking
part-based model
Robustness
Searching
structure-aware hyper-graph
Support vector machines
Target tracking
Tracking
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent advances in online visual tracking focus on designing part-based model to handle the deformation and occlusion challenges. However, previous methods usually consider only the pairwise structural dependences of target parts in two consecutive frames rather than the higher order constraints in multiple frames, making them less effective in handling large deformation and occlusion challenges. This paper describes a new and efficient method for online deformable object tracking. Different from most existing methods, this paper exploits higher order structural dependences of different parts of the tracking target in multiple consecutive frames. We construct a structure-aware hyper-graph to capture such higher order dependences, and solve the tracking problem by searching dense subgraphs on it. Furthermore, we also describe a new evaluating data set for online deformable object tracking (the Deform-SOT data set), which includes 50 challenging sequences with full annotations that represent realistic tracking challenges, such as large deformations and severe occlusions. The experimental result of the proposed method shows considerable improvement in performance over the state-of-the-art tracking methods.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2016.2570556