An anchor patch based optimization framework for reducing optical flow drift in long image sequences

Authors:
Wenbin Li;Darren Cosker;Matthew Brown
Affiliations:
Department of Computer Science, University of Bath, Bath, UK;Department of Computer Science, University of Bath, Bath, UK;Department of Computer Science, University of Bath, Bath, UK
Venue:
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Year:
2012

Citing 13
Cited 0

The robust estimation of multiple motions: parametric and piecewise-smooth flow fields

Computer Vision and Image Understanding
Trainable videorealistic speech animation

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
The Integration of Optical Flow and Deformable Models with Applications to Human Face Shape and Motion Estimation

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Universal capture - image-based facial animation for "The Matrix Reloaded"

SIGGRAPH '05 ACM SIGGRAPH 2005 Courses
Capturing and animating occluded cloth

ACM SIGGRAPH 2007 papers
An Improved Algorithm for TV-L1 Optical Flow

Statistical and Geometrical Approaches to Visual Motion Analysis
High resolution passive facial performance capture

ACM SIGGRAPH 2010 papers
Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Database and Evaluation Methodology for Optical Flow

International Journal of Computer Vision
High-quality passive facial performance capture using anchor frames

ACM SIGGRAPH 2011 papers
Robust trajectory-space TV-L1 optical flow for non-rigid sequences

EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
Feature-Based Deformable Surface Detection with Self-Occlusion Reasoning

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

Tracking through long image sequences is a fundamental research issue in computer vision. This task relies on estimating correspondences between image pairs over time where error accumulation in tracking can result in drift. In this paper, we propose an optimization framework that utilises a novel Anchor Patch algorithm which significantly reduces overall tracking errors given long sequences containing highly deformable objects. The framework may be applied to any tracking algorithm that calculates dense correspondences between images, e.g. optical flow. We demonstrate the success of our approach by showing significant tracking error reduction using 6 existing optical flow algorithms applied to a range of benchmark ground truth sequences. We also provide quantitative analysis of our approach given synthetic occlusions and image noise.