Safe Avoidance Region Detection for Unmanned Aerial Vehicle Using Cues from Expansion of Feature Points

Abstract

Develop an obstacle detection system for Unmanned Aerial Vehicle (UAV) especially for small UAV is challenging. A robust system should be able to not only detect obstacles but the free region for the avoidance path as well. Besides, the configuration of the obstacles in the operating environment should never be disregard. In this paper, expansion cues from the detected feature points with the help of convex hull will be used to categorize the regions in the image frame. A micro LIDAR sensor is used as the initial detector of obstacle and queue for image capturing by the camera. Next, ORB algorithm is applied to find the obstacle regions and free space regions. This is done through the principal of object size changes and distance relationship in an image perspective. The proposed system was evaluated through series of experiments in a real environment which consist of different configuration of obstacles. The experiments show the proposed system was able to find the safe avoidance region regardless of the configuration of the obstacles in the operating environment. Keywords: Expansion cue; ORB; Feature points; Safe avoidance region