UAVs have their unique advantages in agility and maneuverability, and thus been deployed in search and rescue missions. Visual information is a vital cue for target detection and positioning. However, in complex environments, targets might be occluded resulting in failure of detection and positioning using visual sensors. This paper presents a target detection and positioning algorithm for UAV search and rescue missions in complex environments. The proposed algorithm combines target detection and positioning with path planning to enable fast and robust search and rescue in presence of occluded targets. YoloV4 is used for target detection and depth information from RGBD sensor is invoked to derive target position. Path planning is incorporated to achieve good observation of targets with/without occluding obstacles. The effectiveness and real-time performance of the proposed algorithm was investigated via simulation study and flight experiments using a UAV platform.
Target Detection and Positioning for UAV Search and Rescue in Complex Environments
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Kapitel : 271 ; 2765-2776
2022-03-18
12 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Deep Learning for Victims Detection from Virtual and Real Search and Rescue Environments
Springer Verlag | 2022
|Rapid positioning search and rescue device and use method thereof
Europäisches Patentamt | 2023
|Personnel search and rescue method, search and rescue boat and personnel search and rescue system
Europäisches Patentamt | 2020
|