Semi-Nonnegative matrix factorization for motion segmentation with missing data

Authors:
Quanyi Mo;Bruce A. Draper
Affiliations:
Colorado State University;Colorado State University
Venue:
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Year:
2012

Citing 6
Cited 0

Non-negative Matrix Factorization with Sparseness Constraints

The Journal of Machine Learning Research
Multibody Grouping by Inference of Multiple Subspaces from High-Dimensional Data Using Oriented-Frames

IEEE Transactions on Pattern Analysis and Machine Intelligence
Convex and Semi-Nonnegative Matrix Factorizations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Dense point trajectories by GPU-accelerated large displacement optical flow

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
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

Motion segmentation is an old problem that is receiving renewed interest because of its role in video analysis. In this paper, we present a Semi-Nonnegative Matrix Factorization (SNMF)method that models dense point tracks in terms of their optical flow, and decomposes sets of point tracks into semantically meaningful motion components. We show that this formulation of SNMF with missing values outperforms the state-of-the-art algorithm of Brox and Malik in terms of accuracy on 10-frame video segments from the Berkeley test set, while being over 100 times faster. We then show how SNMF can be applied to longer videos using sliding windows. The result is competitive in terms of accuracy with Brox and Malik's algorithm, while still being two orders of magnitude faster.