AURORA: autonomous real-time on-board video analytics

Plamen Angelov, Pouria Sadeghi Tehran, Christopher Clarke

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)

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.
Original languageEnglish
Pages (from-to)855-865
Number of pages11
JournalNeural Computing and Applications
Volume28
Issue number5
Early online date19 Apr 2016
DOIs
Publication statusPublished - 31 May 2017

Keywords

  • Autonomous objects detection
  • unmanned aerial vehicle
  • evolving clustering
  • video analytics
  • linear motion model

Cite this