Implementation and assessment of video stabilization for structured light applications

Spring 2013

Debjani Biswas
Martial Hebert
Project description

Video stabilization techniques can be used to compensate for the movement of a camera. This is especially important for structured light application when there is background present. I will implement the algorithm described in the paper "Video Stabilization and Enhancement" (Farid and Woodword) in C++ and assess its effectiveness to compensate for movement. I will use OpenCV as the vision library. I will evaluate the quality of background subtraction under various conditions: Indoor/outdoor, different movements, smooth/textured background, presence of moving objects etc. If necessary I will modify the algorithm to improve the results.

Return to project list