Tracking occluded targets in high-similarity background: an online training, non-local appearance model and periodic hybrid particle filter with projective transformation

Authors:
Yi Wang;Richard R. Schultz
Affiliations:
Department of Electrical Engineering, University of North Dakota;Department of Electrical Engineering, University of North Dakota
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 7
Cited 0

Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Incremental Singular Value Decomposition of Uncertain Data with Missing Values

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
The Template Update Problem

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
A Non-Local Algorithm for Image Denoising

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Automatic Panoramic Image Stitching using Invariant Features

International Journal of Computer Vision
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Two main challenges lie in tracking the partially occluded targets in a high-similarity background: 1) similar intensities increase the difficulty of discriminating targets from the background, and 2) occlusion (illumination and shape) decreases the relativity of targets to templates. In this paper, a novel eigenspace-based hybrid particle filter tracking method combined with online nonlocal appearance model is proposed to track the objects under highly similar environment with occlusions. By on-line training of the templates through non-local methods to generate the active appearance model, it is more likely find the maximum-likelihood distribution correctly. The projective transformation is utilized to cover all of the possible motion factors between the templates. The extended and unscented Kalman filters are switched to update the particles according to the linearity of the motion parameters. The experiment results show the effectiveness of our algorithm while dealing with occluded target in a high-similarity background.