Research Infrastructure for Real-Time Computer Vision Applications in Unmanned Aerial Systems
Research Infrastructure for Real-Time Computer Vision Applications in Unmanned Aerial Systems
复制标题
DOI:
10.1109/icite56321.2022.10101390
复制
发表时间:
2022-11
期刊:
影响因子:
--
通讯作者:
L. R. I. Dy;Kristoffer B. Borgen;Qilei Zhang;John H. Mott
中科院分区:
文献类型:
--
作者:
L. R. I. Dy;Kristoffer B. Borgen;Qilei Zhang;John H. Mott
As the use and applications of Unmanned Aerial Systems (UAS) grow, the need for rapid and efficient research and development arises. UAS aspects such as sensing, navigation, and collision avoidance need to be evaluated. To facilitate this, research infrastructure comprising a simulator and a sizeable indoor testing center has been proposed and built. The discussed infrastructure aims to boost research progress with a focus on low-power computer vision solutions for UAS applications. This research and development process optimizes available resources by eliminating suboptimal solutions early. Leveraging a motion capture system, precise and accurate metrics can be used to evaluate and compare competing solutions prior to real-world testing. Additionally, various scenarios and environments can be recreated at relatively low cost in simulation or indoors, providing researchers with rigorous testing opportunities. Competitions are currently held to pit teams from around the world to produce effective solutions for UAS tasks. Beginning with simple problems, tasks of increasing complexity will be introduced commensurate with previous successes. While it is acknowledged that simulation and indoor testing cannot completely replace real-world testing, this infrastructure setup provides an invaluable opportunity for UAS researchers.