TY - GEN
T1 - SkyNet: Multi-Drone Cooperation for Real-Time Person Identification and Localization
AU - Peng, Junkun
AU - Li, Qing
AU - Tan, Yuanzheng
AU - Zhao, Dan
AU - Yuan, Zhenhui
AU - Chen, Jinhua
AU - Wang, Hanling
AU - Jiang, Yong
N1 - Funding information: This work is supported by National Natural Science Foundation of China under grant No. 61972189, the Major Key Project of PCL under grant No. PCL2021A03-1, Shenzhen Science and Technology Innovation Commission: Research
Center for Computer Network (Shenzhen) Ministry of Education, and the Shenzhen Key Lab of Software Defined Networking under grant No. ZDSYS20140509172959989
PY - 2023/5/17
Y1 - 2023/5/17
N2 - Aerial images from drones have been used to detect and track suspects in the crowd for the public safety purpose. However, using a single drone for human identification and localization faces many challenges including low accuracy and long latency, due to poor visibility, varying field of views (FoVs), and limited on-board computing resources. In this paper, we propose SkyNet, a multi-drone cooperative system for accurate and real-time human identification and localization. SkyNet computes the 3D position of a person by cross searching from multiple views. To achieve high accuracy in identification, SkyNet fuses aerial images of multiple drones according to their legibility. Moreover, by predicting the estimated finishing time of tasks, SkyNet schedules and balances workloads among edge devices and the cloud server to minimize processing latency. We implement and deploy SkyNet in real life, and evaluate the performance of identification and localization with 20 human participants. The results show that SkyNet can locate people with an average error within 0.18m on a square of 554m 2 . The identification accuracy is 91.36%. The localization and identification process is completed within 0.84s.
AB - Aerial images from drones have been used to detect and track suspects in the crowd for the public safety purpose. However, using a single drone for human identification and localization faces many challenges including low accuracy and long latency, due to poor visibility, varying field of views (FoVs), and limited on-board computing resources. In this paper, we propose SkyNet, a multi-drone cooperative system for accurate and real-time human identification and localization. SkyNet computes the 3D position of a person by cross searching from multiple views. To achieve high accuracy in identification, SkyNet fuses aerial images of multiple drones according to their legibility. Moreover, by predicting the estimated finishing time of tasks, SkyNet schedules and balances workloads among edge devices and the cloud server to minimize processing latency. We implement and deploy SkyNet in real life, and evaluate the performance of identification and localization with 20 human participants. The results show that SkyNet can locate people with an average error within 0.18m on a square of 554m 2 . The identification accuracy is 91.36%. The localization and identification process is completed within 0.84s.
KW - information fusion
KW - localization
KW - multi-drone
KW - person identification
KW - task distribution
UR - http://www.scopus.com/inward/record.url?scp=85171625049&partnerID=8YFLogxK
U2 - 10.1109/infocom53939.2023.10228978
DO - 10.1109/infocom53939.2023.10228978
M3 - Conference contribution
SN - 9798350334159
SP - 1
EP - 10
BT - IEEE INFOCOM 2023 - IEEE Conference on Computer Communications
PB - IEEE
ER -