Comparison of Visual Simultaneous Localization and Mapping Methods for Fixed-Wing Aircraft Using SlamBench2

Abstract

Visual Simultaneous Localization and Mapping (VSLAM) algorithms have evolved rapidly in the last few years, however there has been little research evaluating current algorithms effectiveness and limitations when applied to tracking the position of a fixed-wing aerial vehicle. This research looks to evaluate current monocular VSLAM algorithms performance on aerial vehicle datasets using the SLAMBench2 bench marking suite. It does so by using simulated datasets generated in the AftrBurner Engine to test the quality of each algorithms tracking solution, as well as finding any dependence on camera Field of View (FOV), aircraft altitude, bank angle, and bank rate.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 19, 2020
Accession Number
AD1102935

Entities

People

  • Patrick R. Latcham

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Autonomy

DTIC Thesaurus Topics

  • Air Force
  • Aircrafts
  • Algorithms
  • Department Of Defense
  • Electrical Engineering
  • Fixed Wing Aircraft
  • Flight Paths
  • Global Positioning Systems
  • Governments
  • Inertial Measurement Units
  • Kalman Filters
  • Maps
  • Micro Air Vehicles
  • Navigation
  • Simultaneous Localization And Mapping
  • United States Government
  • Unmanned Aerial Vehicles

Readers

  • Aerospace Engineering
  • Computer Vision.