Highly consistent sequential segmentation

Authors:
Michael Donoser;Martin Urschler;Hayko Riemenschneider;Horst Bischof
Affiliations:
Institute for Computer Graphics and Vision, Graz University of Technology, Austria;Ludwig Boltzmann Institute for Clinical Forensic Imaging, Graz, Austria and Institute for Computer Graphics and Vision, Graz University of Technology, Austria;Institute for Computer Graphics and Vision, Graz University of Technology, Austria;Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Venue:
SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
Year:
2011

Citing 10
Cited 0

Mean Shift: A Robust Approach Toward Feature Space Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Motion Segmentation and Tracking Using Normalized Cuts

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Efficient Graph-Based Image Segmentation

International Journal of Computer Vision
Using the Inner-Distance for Classification of Articulated Shapes

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
A Spectral Technique for Correspondence Problems Using Pairwise Constraints

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Fast Global Minimization of the Active Contour/Snake Model

Journal of Mathematical Imaging and Vision
Video object annotation, navigation, and composition

Proceedings of the 21st annual ACM symposium on User interface software and technology
What went where

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Efficient partial shape matching of outer contours

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper deals with segmentation of image sequences in an unsupervised manner with the goal of getting highly consistent segmentation results from frame-to-frame. We first introduce a segmentation method that uses results of the previous frame as initialization and significantly improves consistency in comparison to a single frame based approach. We also find correspondences between the segmented regions from one frame to the next to further increase consistency. This matching step is based on a modified version of an efficient partial shape matching method which allows identification of similar parts of regions despite topology changes like merges and splits. We use the identified matched parts to define a partial matching cost which is then used as input to pairwise graph matching. Experiments demonstrate that we can achieve highly consistent segmentations for diverse image sequences, even allowing to track manually initialized moving and static objects.