Spatio-temporal extraction of articulated models in a graph pyramid

Authors:
Nicole M. Artner;Adrian Ion;Walter G. Kropatsch
Affiliations:
PRIP, Vienna University of Technology, Austria;PRIP, Vienna University of Technology, Austria and Institute of Science and Technology Austria, IST Austria;PRIP, Vienna University of Technology, Austria
Venue:
GbRPR'11 Proceedings of the 8th international conference on Graph-based representations in pattern recognition
Year:
2011

Citing 14
Cited 0

Relative sensitivity of a family of closet-point graphs in computer vision applications

Pattern Recognition
Region-based parametric motion segmentation using color information

Graphical Models and Image Processing
The visual analysis of human movement: a survey

Computer Vision and Image Understanding
Human motion analysis: a review

Computer Vision and Image Understanding
Vision pyramids that do not grow too high

Pattern Recognition Letters - Special issue: In memoriam Azriel Rosenfeld
A survey of advances in vision-based human motion capture and analysis

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Incremental discovery of object parts in video sequences

Computer Vision and Image Understanding
A Factorization-Based Approach for Articulated Nonrigid Shape, Motion and Kinematic Chain Recovery From Video

IEEE Transactions on Pattern Analysis and Machine Intelligence
Rigid Part Decomposition in a Graph Pyramid

CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Learning Articulated Structure and Motion

International Journal of Computer Vision
On-Line Random Naive Bayes for Tracking

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Multibody Motion Segmentation Using the Geometry of 6 Points in 2D Images

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Multi-scale 2D tracking of articulated objects using hierarchical spring systems

Pattern Recognition
Segmenting highly articulated video objects with weak-prior random forests

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a method to create a model of an articulated object using the planar motion in an initialization video. The model consists of rigid parts connected by points of articulation. The rigid parts are described by the positions of salient feature-points tracked throughout the video. Following a filtering step that identifies points that belong to different objects, rigid parts are found by a grouping process in a graph pyramid. Valid articulation points are selected by verifying multiple hypotheses for each pair of parts.