Machine vision
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Object Level Grouping for Video Shots
International Journal of Computer Vision
Particle Video: Long-Range Motion Estimation Using Point Trajectories
International Journal of Computer Vision
Robust Multiple Structures Estimation with J-Linkage
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Clustering Point Trajectories with Various Life-Spans
CVMP '09 Proceedings of the 2009 Conference for Visual Media Production
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
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
Multiple Plane Detection in Image Pairs Using J-Linkage
ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
A global optimization approach to robust multi-model fitting
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
A closed form solution to robust subspace estimation and clustering
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Track to the future: Spatio-temporal video segmentation with long-range motion cues
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
| Hi-index | 0.00 |
We present an approach for motion segmentation using independently detected keypoints instead of commonly used tracklets or trajectories. This allows us to establish correspondences over non- consecutive frames, thus we are able to handle multiple object occlusions consistently. On a frame-to-frame level, we extend the classical split-and-merge algorithm for fast and precise motion segmentation. Globally, we cluster multiple of these segmentations of different time scales with an accurate estimation of the number of motions. On the standard benchmarks, our approach performs best in comparison to all algorithms which are able to handle unconstrained missing data. We further show that it works on benchmark data with more than 98% of the input data missing. Finally, the performance is evaluated on a mobile-phone-recorded sequence with multiple objects occluded at the same time.