An Integrated Bayesian Approach to Layer Extraction from Image Sequences
IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting and Tracking Multiple Moving Objects Using Temporal Integration
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Smoothness in Layers: Motion segmentation using nonparametric mixture estimation.
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Segmentation of Dynamic Scenes from Image Intensities
MOTION '02 Proceedings of the Workshop on Motion and Video Computing
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation
International Journal of Computer Vision
A Closed Form Solution to Direct Motion Segmentation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Segmentation of Hybrid Motions via Hybrid Quadratic Surface Analysis
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
A bottom up algebraic approach to motion segmentation
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Hi-index | 0.01 |
We propose a closed form solution for segmenting mixtures of 2-D translational and 2-D affine motion models directly from the image intensities. Our approach exploits the fact that the spatial-temporal image derivatives generated by a mixture of these motion models must satisfy a bi-homogeneous polynomial called the multibody brightness constancy constraint (MBCC). We show that the degrees of the MBCC are related to the number of motions models of each kind. Such degrees can be automatically computed using a one-dimensional search. We then demonstrate that a sub-matrix of the Hessian of the MBCC encodes information about the type of motion models. For instance, the matrix is rank-1 for 2-D translational models and rank-3 for 2-D affine models. Once the type of motion model has been identified, one can obtain the parameters of each type of motion model at every image measurement from the cross products of the derivatives of the MBCC. We then demonstrate that accounting for a 2-D translational motion model as a 2-D affine one would result in erroneous estimation of the motion models, thus motivating our aim to account for different types of motion models. We apply our method to segmenting various dynamic scenes.