zyinshi / Optical Flow
Implementation of Lucas-Kanade optical flow algorithm.
Stars: ✭ 35
Programming Languages
matlab
3953 projects
Implementation of Optical Flow Algorithm
The implementation has 4 parts:
-
Naive dense optical flow.(
opticalFlow.m
) Windowsize and threshold for smallest eigen value are free parameter -
Corner-based sparse optical flow
- Corner detection is based on Gaussian deviation (
CornerDetect.m
,gaussian.m
,d_gaussian.m
)
- Iterative Coarse to Fine Optical Flow (details can be found in
report.pdf
)
- Multi-resolution pyramid (
pyramidFlow.m
) - apply Lucas-Kanada optical flow iteratively to estimate potential motion velocity on each level (
iterOpticalflow.m
)
- Experiments
- Motion based Background Subtraction (
bg.m
) Remove the dynamic portions of an image from a static background - Motion based Image Segmentation
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].