Direct Recovery of Motion and Shape in the General Case by Fixation
IEEE Transactions on Pattern Analysis and Machine Intelligence
The role of fixation in visual motion analysis
International Journal of Computer Vision
Performance of optical flow techniques
International Journal of Computer Vision
Fast electronic digital image stabilization for off-road navigation
Real-Time Imaging
Performance characterization of image stabilization algorithms
Real-Time Imaging
Recovery of Ego-Motion Using Region Alignment
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fixation simplifies 3D motion estimation
Computer Vision and Image Understanding
On the consistency of instantaneous rigid motion estimation
International Journal of Computer Vision
Understanding the Behavior of SFM Algorithms: A Geometric Approach
International Journal of Computer Vision
A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shooting a smooth video with a shaky camera
Machine Vision and Applications
An FFT-based technique for translation, rotation, and scale-invariant image registration
IEEE Transactions on Image Processing
A phase-based approach to the estimation of the optical flow field using spatial filtering
IEEE Transactions on Neural Networks
Editorial: ECOVISION: Challenges in Early-Cognitive Vision
International Journal of Computer Vision
A recursive fuzzy systemfor efficient digital image stabilization
Advances in Fuzzy Systems - Regular issue
Hi-index | 0.00 |
A novel method is introduced for the stabilization of short image sequences. Stabilization is achieved by means of fixation of the central image region using a variable window size block matching method. When applied to a sliding temporal window, the stabilization improves the performance of standard optic flow techniques. Due to the unique choice of fixation as the main stabilization mechanism, the proposed method not only increases the flow field density but renders certain global structural properties of the flow fields more predictable as well. This in turn is advantageous for egomotion computation.