3D pose estimation of UAVs using Stereovision

Pose estimation for Unmanned Aerial Vehicles (UAV) is essential for critical maneuvers such as landing and docking. In this work we propose a simple stereovision based pose estimation algorithm using salient points detection. We propose a modular pipeline consisting of 3 major blocks: Image Segmentation (IS), Perspective Transform (PT) and Pose Determination (PD). IS block uses segmentation to detect salient points from the image which the PT block transforms from image coordinates to world coordinates. PD block uses camera parameters and object dimensions to provide Attitude and Translation matrix of the UAV. The proposed approach is highly dynamic and can adjust with change in environmental parameters.