Flying object detection system using an omnidirectional camera. (December 2020)

• Record Type: Journal Article
• Authors: Hirabayashi, Manato; Kurosawa, Kenji; Yokota, Ryo; Imoto, Daisuke; Hawai, Yoshinori; Akiba, Norimitsu; Tsuchiya, Ken'ichi; Kakuda, Hidetoshi; Tanabe, Kosuke; Honma, Masakatsu
• Is Part Of: Forensic science international. Volume 35(2020)
• Publication Date: 2020-12
• Subjects: Surveillance system -- Small object detection -- Spherical camera -- Drone detection -- Security support
• DOI: 10.1016/j.fsidi.2020.301027
• Languages: English
• ISSNs: 2666-2817

Abstract

Abstract: While the effective utilization of drones is expected to grow in a wide range of fields, there are concerns over new threats related to the exploitation of drones that have not been considered thus far. From the perspective of surveillance, the remarkable ability of drones to fly in any arbitrary direction imposes the need for wider range sensing than ever. Cameras are commonly used as surveillance devices; however, traditional cameras capture a limited field of view and, although the output can have a spatially dense resolution, there are significant blind spots. Omnidirectional cameras are emerging as devices that can capture almost all directions simultaneously with one device. In this paper, we present a drone detection system that uses an omnidirectional camera. We use system modularization to improve the detection accuracy for small objects through a combination of image dividing and state-of-the-art object detection algorithms. Three-dimensional direction of detected objects is visualized by our system using the well-calibrated intrinsic/extrinsic parameters of the omnidirectional camera. Our system was evaluated using a dataset for actual flying drones recorded using an omnidirectional camera. Our quantitative evaluation indicates that our system achieved an at-best average precision and average recall of over 0.8 for small objects represented as 10–20 pixel squares in the original image. Highlights: Proposed surveillance support system using an omnidirectional camera. Focusing on drone detection as a countermeasure against future threats from the air. Achieved an at-best detection precision and recall of over 0.8 for small drones.