Lost in the Woods? Place Recognition for Navigation in Difficult Forest Environments

James Garforth, Barbara Webb

Research output: Contribution to journalArticlepeer-review

Abstract

Forests present one of the most challenging environments for computer vision due to traits such as complex texture, rapidly changing lighting and high dynamicity. Loop closure by place recognition is a crucial part of successfully deploying robotic systems to map forests for the purpose of automating conservation. Modern CNN-based place recognition systems like NetVLAD have reported promising results, but the datasets used to train and test them are primarily of urban scenes. In this paper, we investigate how well NetVLAD generalises to forest environments and find that it out performs state of the art loop closure approaches. Finally, integrating NetVLAD with ORBSLAM2 and evaluating on a novel forest data set, we find that, although suitable locations for loop closure can be identified, the SLAM system is unable to resolve matched places with feature correspondences. We discuss additional considerations to be addressed in future to deal with this challenging problem.
Original languageEnglish
Article number514770
Number of pages9
JournalFrontiers in Robotics and AI
Volume7
DOIs
Publication statusPublished - 27 Nov 2020

Keywords

  • visual perception
  • place recognition
  • forests
  • scene statistics
  • navigation
  • SLAM
  • field robotics

Fingerprint

Dive into the research topics of 'Lost in the Woods? Place Recognition for Navigation in Difficult Forest Environments'. Together they form a unique fingerprint.

Cite this