Learning-based risk assessment and motion estimation by vision for unmanned aerial vehicle landing in an unvisited area

Hsiu Wen Cheng, Tsung Lin Chen, Chung Hao Tien*

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

We proposed a vision-based methodology as an aid for an unmanned aerial vehicle (UAV) landing on a previously unsurveyed area. When the UAV was commanded to perform a landing mission in an unknown airfield, the learning procedure was activated to extract the surface features for learning the obstacle appearance. After the learning process, while hovering the UAV above the potential landing spot, the vision system would be able to predict the roughness value for confidence in a safe landing. Finally, using hybrid optical flow technology for motion estimation, we successfully carried out the UAV landing without a predefined target. Our work combines a well-equipped flight control system with the proposed vision system to yield more practical versatility for UAV applications.

Original languageEnglish
Article number063011
JournalJournal of Electronic Imaging
Volume28
Issue number6
DOIs
StatePublished - Nov 2019

Keywords

  • optical flow
  • self-supervised learning
  • unmanned aerial vehicle
  • vision-based landing

Fingerprint Dive into the research topics of 'Learning-based risk assessment and motion estimation by vision for unmanned aerial vehicle landing in an unvisited area'. Together they form a unique fingerprint.

  • Cite this