Robust visual tracking using structural region hierarchy and graph matching

Authors:
Yi-Zhe Song;Chuan Li;Liang Wang;Peter Hall;Peiyi Shen
Affiliations:
School of Electronic Engineering and Computer Science, Queen Mary, University of London, London E1 4NS, UK and Department of Computer Science, University of Bath, Bath BA2 7AY, UK;Department of Computer Science, University of Bath, Bath BA2 7AY, UK;National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, PR China;Department of Computer Science, University of Bath, Bath BA2 7AY, UK;XiDian University, ShaanXi 710071, PR China
Venue:
Neurocomputing
Year:
2012

Citing 17
Cited 1

Scale & Affine Invariant Interest Point Detectors

International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Real-Time Tracking Using Level Sets

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Maximally Stable Extremal Region (MSER) Tracking

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Model-Based Hand Tracking Using a Hierarchical Bayesian Filter

IEEE Transactions on Pattern Analysis and Machine Intelligence
Object tracking with dynamic feature graph

ICCCN '05 Proceedings of the 14th International Conference on Computer Communications and Networks
Feature Correspondence Via Graph Matching: Models and Global Optimization

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Robust Real-Time Visual Tracking Using Pixel-Wise Posteriors

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Object tracking using SIFT features and mean shift

Computer Vision and Image Understanding
Parametric correspondence and chamfer matching: two new techniques for image matching

IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 2
Finding semantic structures in image hierarchies using Laplacian graph energy

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Recent advances and trends in visual tracking: A review

Neurocomputing
SURF: speeded up robust features

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Fast approximated SIFT

ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Effective appearance model and similarity measure for particle filtering and visual tracking

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
A survey on visual surveillance of object motion and behaviors

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

Robust visual tracking using discriminative stable regions and K-means clustering

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Visual tracking aims to match objects of interest in consecutive video frames. This paper proposes a novel and robust algorithm to address the problem of object tracking. To this end, we investigate the fusion of state-of-the-art image segmentation hierarchies and graph matching. More specifically, (i) we represent the object to be tracked using a hierarchy of regions, each of which is described with a combined feature set of SIFT descriptors and color histograms; (ii) we formulate the tracking process as a graph matching problem, which is solved by minimizing an energy function incorporating appearance and geometry contexts; and (iii) more importantly, an effective graph updating mechanism is proposed to adapt to the object changes over time for ensuring the tracking robustness. Experiments are carried out on several challenging sequences and results show that our method performs well in terms of object tracking, even in the presence of variations of scale and illumination, moving camera, occlusion, and background clutter.