Localised Mixture Models in Region-Based Tracking

Authors:
Christian Schmaltz;Bodo Rosenhahn;Thomas Brox;Joachim Weickert
Affiliations:
Mathematical Image Analysis Group, Faculty of Mathematics and Computer Science, Saarland University, Saarbrücken, Germany 66041;Leibniz Universität Hannover, Hannover, Germany 30167;University of California, Berkeley, USA 94720;Mathematical Image Analysis Group, Faculty of Mathematics and Computer Science, Saarland University, Saarbrücken, Germany 66041
Venue:
Proceedings of the 31st DAGM Symposium on Pattern Recognition
Year:
2009

Citing 12
Cited 1

The visual analysis of human movement: a survey

Computer Vision and Image Understanding
Using Adaptive Tracking to Classify and Monitor Activities in a Site

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Twist Based Acquisition and Tracking of Animal and Human Kinematics

International Journal of Computer Vision
"GrabCut": interactive foreground extraction using iterated graph cuts

ACM SIGGRAPH 2004 Papers
Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation

International Journal of Computer Vision
Bilayer Segmentation of Live Video

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Three-Dimensional Shape Knowledge for Joint Image Segmentation and Pose Tracking

International Journal of Computer Vision
Vision-based human motion analysis: An overview

Computer Vision and Image Understanding
Dealing with Self-occlusion in Region Based Motion Capture by Means of Internal Regions

AMDO '08 Proceedings of the 5th international conference on Articulated Motion and Deformable Objects
Robust 3D Pose Estimation and Efficient 2D Region-Based Segmentation from a 3D Shape Prior

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Background cut

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Level Set Segmentation With Multiple Regions

IEEE Transactions on Image Processing

N-view human silhouette segmentation in cluttered, partially changing environments

Proceedings of the 32nd DAGM conference on Pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

An important problem in many computer vision tasks is the separation of an object from its background. One common strategy is to estimate appearance models of the object and background region. However, if the appearance is spatially varying, simple homogeneous models are often inaccurate. Gaussian mixture models can take multimodal distributions into account, yet they still neglect the positional information. In this paper, we propose localised mixture models (LMMs) and evaluate this idea in the scope of model-based tracking by automatically partitioning the fore- and background into several subregions. In contrast to background subtraction methods, this approach also allows for moving backgrounds. Experiments with a rigid object and the HumanEva-II benchmark show that tracking is remarkably stabilised by the new model.