Motion segmentation by velocity clustering with estimation of subspace dimension

Authors:
Liangjing Ding;Adrian Barbu;Anke Meyer-Baese
Affiliations:
Department of Scientific Computing, Florida State University;Department of Statistics, Florida State University;Department of Scientific Computing, Florida State University
Venue:
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume 2
Year:
2012

Citing 12
Cited 0

Shape and motion from image streams under orthography: a factorization method

International Journal of Computer Vision
Multibody Grouping from Motion Images

International Journal of Computer Vision
A Multibody Factorization Method for Independently Moving Objects

International Journal of Computer Vision
Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
A multi-body factorization method for motion analysis

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
A Factorization-Based Approach to Articulated Motion Recovery

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Generalized Principal Component Analysis (GPCA)

IEEE Transactions on Pattern Analysis and Machine Intelligence
Spectral Curvature Clustering (SCC)

International Journal of Computer Vision
Motion Segmentation in the Presence of Outlying, Incomplete, or Corrupted Trajectories

IEEE Transactions on Pattern Analysis and Machine Intelligence
Object segmentation by long term analysis of point trajectories

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
A general framework for motion segmentation: independent, articulated, rigid, non-rigid, degenerate and non-degenerate

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

The performance of clustering based motion segmentation methods depends on the dimension of the subspace where the point trajectories are projected. This paper presents a strategy for estimating the best subspace dimension using a novel clustering error measure. For each obtained segmentation, the proposed measure estimates the average least square error between the point trajectories and synthetic trajectories generated based on the motion models from the segmentation. The second contribution of this paper is the use of the velocity vector instead of the traditional trajectory vector for segmentation. The evaluation on the Hopkins 155 video benchmark database shows that the proposed method is competitive with current state-of-the-art methods both in terms of overall performance and computational speed.