Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers

Authors:
Qian Yu;Thang Ba Dinh;Gérard Medioni
Affiliations:
University of Southern California, Los Angeles, USA CA 90089-0273;University of Southern California, Los Angeles, USA CA 90089-0273;University of Southern California, Los Angeles, USA CA 90089-0273
Venue:
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Year:
2008

Citing 0
Cited 19

Vehicle tracking based on co-learning particle filter

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Adaptive appearance model and condensation algorithm for robust face tracking

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special issue on recent advances in biometrics
Robust and fast collaborative tracking with two stage sparse optimization

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
On-line multi-view forests for tracking

Proceedings of the 32nd DAGM conference on Pattern recognition
Robust visual tracking using randomized forest and online appearance model

ACIIDS'11 Proceedings of the Third international conference on Intelligent information and database systems - Volume Part II
Multiple target tracking using cognitive data association of spatiotemporal prediction and visual similarity

Pattern Recognition
Semi-supervised vehicle recognition: an approximate region constrained approach

RSKT'12 Proceedings of the 7th international conference on Rough Sets and Knowledge Technology
Dual-force metric learning for robust distracter-resistant tracker

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Online spatio-temporal structural context learning for visual tracking

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Fast and adaptive deep fusion learning for detecting visual objects

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
FaceHugger: the ALIEN tracker applied to faces

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Robust Visual Tracking via Structured Multi-Task Sparse Learning

International Journal of Computer Vision
Robust visual tracking with discriminative sparse learning

Pattern Recognition
A survey of appearance models in visual object tracking

ACM Transactions on Intelligent Systems and Technology (TIST) - Survey papers, special sections on the semantic adaptive social web, intelligent systems for health informatics, regular papers
Shifted subspaces tracking on sparse outlier for motion segmentation

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Discriminative subspace learning with sparse representation view-based model for robust visual tracking

Pattern Recognition
Visual tracking via weakly supervised learning from multiple imperfect oracles

Pattern Recognition
Structured partial least squares for simultaneous object tracking and segmentation

Neurocomputing
Robust object tracking using enhanced random ferns

The Visual Computer: International Journal of Computer Graphics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Visual tracking is a challenging problem, as an object may change its appearance due to viewpoint variations, illumination changes, and occlusion. Also, an object may leave the field of view and then reappear. In order to track and reacquire an unknown object with limited labeling data, we propose to learn these changes online and build a model that describes all seen appearance while tracking. To address this semi-supervised learning problem, we propose a co-training based approach to continuously label incoming data and online update a hybrid discriminative generative model. The generative model uses a number of low dimension linear subspaces to describe the appearance of the object. In order to reacquire an object, the generative model encodes all the appearance variations that have been seen. A discriminative classifier is implemented as an online support vector machine, which is trained to focus on recent appearance variations. The online co-training of this hybrid approach accounts for appearance changes and allows reacquisition of an object after total occlusion. We demonstrate that under challenging situations, this method has strong reacquisition ability and robustness to distracters in background.