On-board Monocular Vision-based Ground Target Recognition and Localization System for a Flapping-wing Aerial Vehicle
Year: 2023
Type: conference-paper
Abstract: Flapping-wing aerial vehicle (FAV) is a novel type of aircraft that mimics the flight mode of birds and insects. Visual perception plays a crucial role in enabling FAVs to acquire ground information and achieve intelligent capabilities. However, most current FAV vision systems rely on ground processing systems for assistance, which limits their operational range due to communication constraints between the aircraft and the ground. Moreover, the use of vision systems for ground target localization on FAVs is still under-researched. In this work, we present a monocular vision-based on-board ground target recognition and localization system for a self-designed FAV, which can run in quasi-real time, and truly endows the FAV with ground autonomous visual perception capabilities. The system utilizes both the images from camera and attitude-position data of the aircraft, and resolves the issue of temporal mismatch between them. To validate feasibility and accuracy of the system, a series of real-world flight experiments are conducted, followed by a discussion of the errors observed.
Institutions: Zhejiang University, University of Manchester
Language: English
Subfield: Aerospace Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: bronze
Award: G8323016548
OpenAlex ID: W4385299233