Angelov, Plamen and Sadeghi Tehran, Pouria and Clarke, Christopher (2017) AURORA : autonomous real-time on-board video analytics. Neural Computing and Applications, 28 (5). pp. 855-865. ISSN 0941-0643
AURORA_Final.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.
Download (11MB)
Abstract
In this paper, we describe the design and implementation of a small light weight, low-cost and power-efficient payload system for the use in unmanned aerial vehicles (UAVs). The primary application of the payload system is that of performing real-time autonomous objects detection and tracking in the videos taken from a UAV camera. The implemented objects detection and tracking algorithms utilise Recursive Density Estimation (RDE) and Evolving Local Means (ELM) clustering to perform detection and tracking moving objects. Furthermore, experiments are presented which demonstrate that the introduced system is able to detect by on-board processing any moving objects from a UAV and start tracking them in real-time while at the same time sending important data only to a control station located on the ground.