Updating the inverse of a matrix
SIAM Review
Computing occluding and transparent motions
International Journal of Computer Vision
Performance of optical flow techniques
International Journal of Computer Vision
Region-based tracking using affine motion models in long image sequences
CVGIP: Image Understanding
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields
Computer Vision and Image Understanding
EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
International Journal of Computer Vision
Efficient Region Tracking With Parametric Models of Geometry and Illumination
IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking a person with pre-recorded image database and a pan, tilt, and zoom camera
Machine Vision and Applications
Robot Vision
Numerical Recipes in C: The Art of Scientific Computing
Numerical Recipes in C: The Art of Scientific Computing
Contour Tracking by Stochastic Propagation of Conditional Density
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Empirical Bayesian EM-based Motion Segmentation
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
A New Bayesian Relaxation Framework for the Estimation and Segmentation of Multiple Motions
SSIAI '00 Proceedings of the 4th IEEE Southwest Symposium on Image Analysis and Interpretation
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Multi-View Subspace Constraints on Homographies
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Camera Motion Estimation from Non-Stationary Scenes Using EM-Based Motion Segmentation
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Variational Space-Time Motion Segmentation
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Layered Motion Segmentation and Depth Ordering by Tracking Edges
IEEE Transactions on Pattern Analysis and Machine Intelligence
Cluster Analysis
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
A Rao-Blackwellized particle filter for EigenTracking
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Learning appearance and transparency manifolds of occluded objects in layers
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Motion segmentation by multistage affine classification
IEEE Transactions on Image Processing
Multiple motion segmentation with level sets
IEEE Transactions on Image Processing
Representing moving images with layers
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
We present a novel and efficient motion segmentation and tracking algorithm that follows the shift and align paradigm. We introduce two statistical tests to evaluate the similarity of aligned image pixels or patches and we use them to determine the spatial extend of each segment. The one statistical test is fast and accurate when the noise is moderate and the other employs a sophisticated noise model involving the Mahalanobis distance to handle correlated noise. Direct computation of the Mahalanobis distance is prohibitively expensive so we apply the Sherman-Morrison-Woodbury identity and amortization to reduce the cost by several orders of magnitude. We tested both versions of the algorithm on a variety of image sequences (indoor and outdoor, real and synthetic, constant and varying lighting, stationary and moving camera, one of them with known ground truth) with very good results.