Multidimensional Orientation Estimation with Applications to Texture Analysis and Optical Flow
IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance of optical flow techniques
International Journal of Computer Vision
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Bewegung als intrinsische Geometrie von Bildfolgen
Mustererkennung 1999, 21. DAGM-Symposium
The Minors of the Structure Tensor
Mustererkennung 2000, 22. DAGM-Symposium
Robust Multi-Sensor Image Alignment
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods
International Journal of Computer Vision
Full-Frame Video Stabilization
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
An adaptive confidence measure for optical flows based on linear subspace projections
Proceedings of the 29th DAGM conference on Pattern recognition
Reconstructing Optical Flow Fields by Motion Inpainting
EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Complex motion models for simple optical flow estimation
Proceedings of the 32nd DAGM conference on Pattern recognition
On performance analysis of optical flow algorithms
Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
When is a confidence measure good enough?
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
| Hi-index | 0.00 |
Dense optical flow fields are required for many applications. They can be obtained by means of various global methods which employ regularization techniques for propagating estimates to regions with insufficient information. However, incorrect flow estimates are propagated as well. We, therefore, propose surface measures for the detection of locations where the full flow can be estimated reliably, that is in the absence of occlusions, intensity changes, severe noise, transparent structures, aperture problems and homogeneous regions. In this way we obtain sparse, but reliable motion fields with lower angular errors. By subsequent application of a basic motion inpainting technique to such sparsified flow fields we obtain dense fields with smaller angular errors than obtained by the original combined local global (CLG) method and the structure tensor method in all test sequences. Experiments show that this postprocessing method makes error improvements of up to 38% feasible.