This article concentrates on open-source implementation on flying object detection in cluttered scenes. It is of\nsignificance for ground stereo-aided autonomous landing of unmanned aerial vehicles. The ground stereo vision\nguidance system is presented with details on system architecture and workflow. The Chanââ?¬â??Vese detection algorithm\nis further considered and implemented in the robot operating systems (ROS) environment. A data-driven interactive\nscheme is developed to collect datasets for parameter tuning and performance evaluating. The flying vehicle outdoor\nexperiments capture the stereo sequential images dataset and record the simultaneous data from pan-and-tilt unit,\nonboard sensors and differential GPS. Experimental results by using the collected dataset validate the effectiveness of\nthe published ROS-based detection algorithm.
Loading....