Vision-based detection and pose estimation for formation of micro aerial vehicles

This paper proposes an innovative method to detect micro aerial vehicles (MAVs) and estimate their relative pose in formation using a monocular on-board camera. Haar classifier is trained for autonomously detecting MAV in open scenes, like grasslands or obstruct-free playgrounds. In order to increase the robustness of the detection, a Kaiman filter has been employed to conduct image tracking. Contours of detected MAV have been extracted for shape matching. Point sets quantized from contours match with the given point sets using Hungarian algorithm and relaxation labeling based on shape contexts. Two techniques, affine and thin plate spline (TPS) transformation, are explored, while TPS is better in dealing with distorted shapes. In experiments, we develop and implement an innovative 2D shape-based pose estimation method by using only one monocular camera which results in fast and accurate performances.