This project involved the development of a memory-efficient but powerful video stabilisation algorithm designed to work on teleoperated systems. The method works by extracting features from each subsequent frame of the live feed and detecting their movement using the pyramidal implementation of the Lucas Kanade method. The correction phase involves using a Kalman Filter to predict the position of features for the current frame based on the previous one and morphing it, resulting in a smoother live feed.
-
Notifications
You must be signed in to change notification settings - Fork 0
This project served as my dissertation for the completion of my undergraduate degree at VIT, Vellore. I developed a memory-efficient but effective video stabilisation method designed to work with teleoperated UAVs.
Kshitij022/Video-Stabilisation-for-Teleoperated-Systems
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
This project served as my dissertation for the completion of my undergraduate degree at VIT, Vellore. I developed a memory-efficient but effective video stabilisation method designed to work with teleoperated UAVs.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published