Short Title: Int. J. Mech. Eng. Robot. Res.
Frequency: Bimonthly
Professor of School of Engineering, Design and Built Environment, Western Sydney University, Australia. His research interests cover Industry 4.0, Additive Manufacturing, Advanced Engineering Materials and Structures (Metals and Composites), Multi-scale Modelling of Materials and Structures, Metal Forming and Metal Surface Treatment.
2024-10-25
2024-09-24
Abstract—Today, in the era of the 4th industrial revolution, the Unmanned Aerial Vehicle (UAV) technology is attracting a high attention at home and abroad. As the use of unmanned aerial vehicles becomes more active, safety concerns are also increasing, and countermeasures are also being studied. In fact, the most common reason for UAV’s accidents is landing. Therefore, a safer landing method is needed. Existing methods used for safe landing include the use of separate devices for guidance or the utilization of various communication devices within the landing area. Such methods put a great burden on the drone's payload or render them ineffective when the communication becomes unstable. Therefore, in order to enhance the safety of landing, this study proposes the AI-based image recognition approach using the onboard camera. The landing platform images are recognized through the camera mounted on the UAV without adding separate equipment. The camera identifies not only the landing points, but also three-dimensional coordinates of obstacles. This allows a safer landing, while reducing the chance of accidents or fatal damages. Index Terms—landing platform tracking, obstacle avoidance, artificial intelligence, autonomous flight control, drones, UAVs Cite: Sedam Lee, Daeil Jo, and Yongjin (James) Kwon, "Camera-Based Automatic Landing of Drones Using Artificial Intelligence Image Recognition," International Journal of Mechanical Engineering and Robotics Research, Vol. 11, No. 5, pp. 357-364, May 2022. DOI: 10.18178/ijmerr.11.5.357-364 Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.