Shape and motion from image streams under orthography: a factorization method
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
Motion Segmentation and Tracking Using Normalized Cuts
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Two-View Multibody Structure-and-Motion with Outliers through Model Selection
IEEE Transactions on Pattern Analysis and Machine Intelligence
A tutorial on spectral clustering
Statistics and Computing
IEEE Transactions on Pattern Analysis and Machine Intelligence
Motion segmentation with missing data using power factorization and GPCA
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Perspective n-view multibody structure-and-motion through model selection
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Recovering articulated non-rigid shapes, motions and kinematic chains from video
AMDO'06 Proceedings of the 4th international conference on Articulated Motion and Deformable Objects
Motion segmentation by model-based clustering of incomplete trajectories
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part II
A novel framework for motion segmentation and tracking by clustering incomplete trajectories
Computer Vision and Image Understanding
Hi-index | 0.00 |
In this paper we present a motion segmentation algorithm for image sequences based on the Hadamard (or Schur) product of shape interaction matrices computed over a range of dimensions of the ambient space and using a spectral clustering algorithm. Most motion segmentation algorithms proposed to date are based on the use of a shape interaction matrix, obtained via factorization, since it encodes the essential information to segment independently moving rigid objects. However, so far, most studies have been limited to using a single shape interaction matrix to cluster the motions of different objects. In this paper, we propose to combine the shape interaction matrices computed for different subspace dimensions using the Hadamard product. The benefit of this approach is that the affinity of trajectories belonging to the same object is stressed while the affinity between trajectories belonging to different objects is diminished. Once the final shape interaction matrix is computed, we use a spectral clustering algorithm to segment the different motions. Experiments on the Hopkins155 data set for both independent and articulated motions show that our new algorithmprovides a lower miss-classification error rate, outperforming other state of the art algorithms.