Motion Based Image Segmentation with Unsupervised Bayesian Learning
WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Ego-Motion Estimation and 3D Model Refinement in Scenes with Varying Illumination
WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Dynamic Texture Recognition by Spatio-Temporal Multiresolution Histograms
WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Over-Parameterized Variational Optical Flow
International Journal of Computer Vision
A hardware-friendly adaptive tensor based optical flow algorithm
ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part II
Revisiting the brightness constraint: probabilistic formulation and algorithms
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
A study of the yosemite sequence used as a test sequence for estimation of optical flow
SCIA'05 Proceedings of the 14th Scandinavian conference on Image Analysis
A multi-resolution approach for massively-parallel hardware-friendly optical flow estimation
Journal of Visual Communication and Image Representation
Hi-index | 0.01 |
An accurate optical flow estimation algorithm is proposed in this paper. By combining the three-dimensional (3D) structure tensor with a parametric flow model, the optical flow estimation problem is converted to a generalized eigenvalue problem. The optical flow can be accurately estimated from the generalized eigenvectors. The confidence measure derived from the generalized eigenvalues is used to adaptively adjust the coherent motion region to further improve the accuracy. Experiments using both synthetic sequences with ground truth and real sequences illustrate our method. Comparisons with classical and recently published methods are also given to demonstrate the accuracy of our algorithm.