Conference paper Open Access

Asynchronous event-based clustering and tracking for intrusion monitoring in UAS

J. P. Rodríguez-Gómez; ,A. Gómez Eguíluz; J. R. Martínez-de Dios; A. Ollero

Automatic surveillance and monitoring using Un- manned Aerial Systems (UAS) require the development of per- ception systems that robustly work under different illumination conditions. Event cameras are neuromorphic sensors that cap- ture the illumination changes in the scene with very low latency and high dynamic range. Although recent advances in event- based vision have explored the use of event cameras onboard UAS, most techniques group events in frames and, therefore, do not fully exploit the sequential and asynchronous nature of the event stream. This paper proposes a fully asynchronous scheme for intruder monitoring using UAS. It employs efficient event clustering and feature tracking modules and includes a sampling mechanism to cope with the computational cost of event-by-event processing adapting to on-board hardware computational constraints. The proposed scheme was tested on a real multirotor in challenging scenarios showing significant accuracy and robustness to lighting conditions.

This work was supported by the ARM-EXTEND (DPI2017-8979-R) project funded by the Spanish National R&D Plan.
Files (1.8 MB)
Name Size
ICRA2020___Event_based_vision.pdf
md5:d21777546412e056349f68f59760583a
1.8 MB Download
363
354
views
downloads
All versions This version
Views 36323
Downloads 35423
Data volume 907.2 MB42.1 MB
Unique views 31717
Unique downloads 30215

Share

Cite as