 |
Technical Program
Paper Detail
| Paper: | MP-P8.12 |
| Session: | Motion Detection and Estimation |
| Time: | Monday, October 9, 14:20 - 17:00 |
| Presentation: |
Poster
|
| Title: |
LUCAS-KANADE WITHOUT ITERATIVE WARPING |
| Authors: |
Alex Rav-Acha; The Hebrew University of Jerusalem | | | | | Shmuel Peleg; The Hebrew University of Jerusalem | | |
| Abstract: |
Many methods for motion computation and object tracking are based on the Lucas-Kanade (LK) framework. We present a method which substantially speeds up the LK approach while preserving its accuracy. This acceleration is obtained by avoiding the iterative image warping, inherent to the LK framework. A three-fold speedup is observed on standard image alignment tasks. Our second contribution focuses on adopting a multi-frame approach in order to increase alignment accuracy and robustness. By utilizing the acceleration procedure, the complexity of this multi-frame alignment becomes comparable to that of the two-frame approach. |
|
