Motion-based mav detection in gps-denied environments

Abstract

Drones need to detect and localize each other if they are to collaborate in multi-robot teams or swarms. In this paper, a method based on dense optical flow (OF) is developed that detects dynamic objects. This is achieved by comparing the flow vectors with the direction to the Focus of Expansion (FoE) in the image plane. A simulation in AirSim is developed to validate this approach and to create a data set for motion-based dynamic object detection. This simulation includes ground-truth FoE, depth, OF and IMU data. The results show that our method performs well if the OF vector’s magnitude is large enough and its angle is sufficiently different from those of static world points. We expect that the presented method will serve as a useful baseline for deep learning methods using dense optical flow as input.