Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICARCV50220.2020.9305485
Title: Near-Parallel Binocular-Like Camera Pair for Multi-Drone Detection and 3D Localization
Authors: Yi, J
Srigrarom, S 
Issue Date: 13-Dec-2020
Publisher: IEEE
Citation: Yi, J, Srigrarom, S (2020-12-13). Near-Parallel Binocular-Like Camera Pair for Multi-Drone Detection and 3D Localization. 2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV) : 204-210. ScholarBank@NUS Repository. https://doi.org/10.1109/ICARCV50220.2020.9305485
Abstract: The paper presents the concept of using a pair of cameras that are setup near and almost parallel to each other to do detection and 3D localization of multiple drone at far distance away. These setup of the two cameras resemble the binocular cameras, as such the 3D positions of the detected drones can be estimated by epipolar-like geometry. For the special case of detecting the multiple drones at a distance, quick depth distance approximation based on similar triangles is also proposed. Sample field tests of detecting and tracking multiple drones at near and far distances in open areas are presented. The depth distances obtained are comparable to the actual GPS readings from the detected drones.
Source Title: 2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV)
URI: https://scholarbank.nus.edu.sg/handle/10635/217738
ISBN: 9781728177090
DOI: 10.1109/ICARCV50220.2020.9305485
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
ARCV20_Near_parallel_multi_camera_multi_drone_3D_localization.pdfPublished version1.67 MBAdobe PDF

CLOSED

None

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.