Robust data association for online applications

Authors:
Vincent Lepetit;Ali Shahrokni;Pascal Fua
Affiliations:
Computer Vzsion Laboratory, Swiss Federal Institute of Technology, EPFL, Lausanne, Switzerland;Computer Vzsion Laboratory, Swiss Federal Institute of Technology, EPFL, Lausanne, Switzerland;Computer Vzsion Laboratory, Swiss Federal Institute of Technology, EPFL, Lausanne, Switzerland
Venue:
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Year:
2003

Citing 6
Cited 3

Tracking and data association

Tracking and data association
An Efficient Implementation of Reid's Multiple Hypothesis Tracking Algorithm and Its Evaluation for the Purpose of Visual Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
CONDENSATION—Conditional Density Propagation forVisual Tracking

International Journal of Computer Vision
MLESAC: a new robust estimator with application to estimating image geometry

Computer Vision and Image Understanding - Special issue on robusst statistical techniques in image understanding
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
A Smoothing Filter for CONDENSATION

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I

Handsignals Recognition From Video Using 3D Motion Capture Data

WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Temporal motion models for monocular and multiview 3D human body tracking

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Take your eyes off the ball: Improving ball-tracking by focusing on team play

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel method for performing data association that handles complex motion models while increasing the robustness of tracking and being suitable for real-time applications. Instead of using motion model in standard recursive fashion, we robustly fit it over multiple frames simultaneously. This allows us to naturally handle arbitrarily complex motion models, to automate the initialization and to deal with occlusion and false alarms. This is effective even if the motion model is not entirely accurate and if there are frequent false-negatives and false-positives. Our algorithm is easy to implement and we show its performances on two real examples of complex motion tracking.