Optical Flow Estimation: An Error Analysis of Gradient-Based Methods with Local Optimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
On the estimation of optical flow: relations between different approaches and some new results
Artificial Intelligence
Investigations of multigrid algorithms for the estimation of optical flow fieldsin image sequences
Computer Vision, Graphics, and Image Processing
Computation of component image velocity from local phase information
International Journal of Computer Vision
Distributed representation and analysis of visual motion
Distributed representation and analysis of visual motion
Performance of optical flow techniques
International Journal of Computer Vision
Optical flow estimation: advances and comparisons
ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Multiple constraints for optical flow
ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Robust computation of optical flow in a multi-scale differential framework
International Journal of Computer Vision
Multimodal Elastic Matching of Brain Images
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Point Matching under Large Image Deformations and Illumination Changes
IEEE Transactions on Pattern Analysis and Machine Intelligence
A low level real-time vision system using specific computing architectures
ISCGAV'06 Proceedings of the 6th WSEAS International Conference on Signal Processing, Computational Geometry & Artificial Vision
Superpipelined high-performance optical-flow computation architecture
Computer Vision and Image Understanding
Optimization strategies for high-performance computing of optical-flow in general-purpose processors
IEEE Transactions on Circuits and Systems for Video Technology
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
A color neuromorphic approach for motion estimation
WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
A multi-resolution approach for massively-parallel hardware-friendly optical flow estimation
Journal of Visual Communication and Image Representation
Pipelined architecture for real-time cost-optimized extraction of visual primitives based on FPGAs
Digital Signal Processing
Parallel architecture for hierarchical optical flow estimation based on FPGA
IEEE Transactions on Very Large Scale Integration (VLSI) Systems
| Hi-index | 0.00 |
Optical flow estimation by means of first derivatives can producesurprisingly accurate and dense optical flow fields. In particular,recent empirical evidence suggests that the method that is based onlocal optimization of first-order constancy constraints is among themost accurate and reliable methods available. Nevertheless, asystematic investigation of the effects of the various parameters forthis algorithm is still lacking. This paper reports such aninvestigation. Performance is assessed in terms of flow-fieldaccuracy, density, and resolution. The investigation yields newinformation regarding pre-filter, differentiator, least-squaresneighborhood, and reliability test selection. Several changes topreviously-employed parameter settings result in significant overallperformance improvements, while they simultaneously reduce thecomputational cost of the estimator.