Evaluation of several feature detectors/extractors on underwater images towards vslam

Franco Hidalgo, Thomas Bräunl

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

Modern visual SLAM (vSLAM) algorithms take advantage of computer vision developments in image processing and in interest point detectors to create maps and trajectories from camera images. Different feature detectors and extractors have been evaluated for this purpose in air and ground environments, but not extensively for underwater scenarios. In this paper (I) we characterize underwater images where light and suspended particles alter considerably the images captured, (II) evaluate the performance of common interest points detectors and descriptors in a variety of underwater scenes and conditions towards vSLAM in terms of the number of features matched in subsequent video frames, the precision of the descriptors and the processing time. This research justifies the usage of feature detectors in vSLAM for underwater scenarios and present its challenges and limitations.

Original languageEnglish
Article number4343
Pages (from-to)1-16
Number of pages16
JournalSensors
Volume20
Issue number15
DOIs
StatePublished - 1 Aug 2020

Keywords

  • AKAZE
  • BRISK
  • Descriptor
  • Detector
  • Monocular underwater
  • ORB
  • SIFT
  • SURF
  • Underwater robots
  • Underwater video
  • VSLAM

Fingerprint

Dive into the research topics of 'Evaluation of several feature detectors/extractors on underwater images towards vslam'. Together they form a unique fingerprint.

Cite this