Modelling spatial correlation and image statistics for improved tracking of human gestures

Authors:
Rik Bellens;Sidharta Gautama;Johan D'Haeyer
Affiliations:
Department of Telecommunications and Information Processing, University of Ghent, Gent, Belgium;Department of Telecommunications and Information Processing, University of Ghent, Gent, Belgium;Department of Telecommunications and Information Processing, University of Ghent, Gent, Belgium
Venue:
IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part I
Year:
2005

Citing 5
Cited 0

CONDENSATION—Conditional Density Propagation forVisual Tracking

International Journal of Computer Vision
The visual analysis of human movement: a survey

Computer Vision and Image Understanding
A survey of computer vision-based human motion capture

Computer Vision and Image Understanding - Modeling people toward vision-based underatanding of a person's shape, appearance, and movement
Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Learning the Statistics of People in Images and Video

International Journal of Computer Vision - Special Issue on Computational Vision at Brown University

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we examine sensor specific distributions of local image operators (edge and line detectors), which describe the appearance of people in video sequences. The distributions are used to describe a probabilistic articulated motion model to track the gestures of a person in terms of arms and body movement, which is solved using a particle filter. We focus on modeling the statistics of one sensor and examine the influence of image noise and scale, and the spatial accuracy that is obtainable. Additionally spatial correlation between pixels is modeled in the appearance model. We show that by neglecting the correlation high detection probabilities are quickly overestimated, which can often lead to false positives. Using the weighted geometric mean of pixel information leads to much improved results.