Stereo vision for the stabilization of a quadrotor

Stereo vision is a broad field that is part of computer vision. Autonomous mobile robots make use of stereo vision to detect obstacles and measure their relative distance to them for path planning. Technically, it consists of the processing of two images simultaneously adquired by two cameras, from a given scene. Stereo vision is a field with multiple applications and many resources had been invested for research in this subject. In this paper, we present a stereo vision based controller design and its implementation on a mini helicopter with 4 rotors known as quadrotor. The dynamic model is obtained using the well known Euler-Lagrange approach. Experiment results show good performance of the proposed controller using "real-time" optical flow and image processing from two cameras.