Monocular Trail Detection and Tracking Aided by Visual SLAM for Small Unmanned Aerial Vehicles

André Silva, Ricardo Mendonça, Pedro Santana

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)

Abstract

This article addresses the navigation problem of small and medium-sized unmanned aerial vehicles (UAVs) built to perform missions in forest environments (e.g., search and rescue) by exploiting the presence of natural or man-made paths, typically present in this type of environments. The proposed system extends a previous monocular-based technique for trail detection and tracking so as to take into account volumetric data acquired from a Visual SLAM algorithm and, as a result, to increase its sturdiness upon challenging trails. The experimental results, obtained via a set of 12 videos recorded with a camera installed in a tele-operated, unmanned small-sized aerial vehicle, show the ability of the proposed system to overcome some of the difficulties of the original detector, attaining a success rate of 97.8%.

Original languageEnglish
Pages (from-to)531-551
Number of pages21
JournalJournal of Intelligent and Robotic Systems: Theory and Applications
Volume97
Issue number3-4
DOIs
Publication statusPublished - 1 Mar 2020

Keywords

  • Path detection
  • UAV
  • Visual SLAM

Fingerprint

Dive into the research topics of 'Monocular Trail Detection and Tracking Aided by Visual SLAM for Small Unmanned Aerial Vehicles'. Together they form a unique fingerprint.

Cite this