Aerial vehicle localization using generic landmarks

Mark P. Deangelo, Joseph Francis Horn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This research presents a new method to localize an aircraft without GPS using fixed, generic landmarks observed from an optical sensor. Computer vision object detectors are trained to detect abundant generic landmarks referred as buildings, fields, trees, and road intersections from aerial perspectives. Various landmark attributes and spatial relationships to other landmarks are used to help associate observed landmarks with reference landmarks, which are processed offline before a flight. During a flight, the aircraft navigates with attitude, heading, airspeed, and altitude measurements and obtains measurement corrections by processing aerial photos with similar generic landmark detection techniques. Landmark coordinates extracted from the aircraft’s camera images and inertial measurements are combined into an unscented Kalman filter to obtain an estimate of the aircraft’s position and wind velocities. The objective is to achieve practical navigation performance using available autopilot hardware and a downward pointing camera. The method is demonstrated with an airplane simulation and high resolution orthoimagery. The simulations indicate feasible localization results for outdoor visual flight conditions. Finally, real world flight test results demonstrate localization accuracy within two feet for a quad-rotor flying in an indoor lab at an altitude of ten feet.

Original languageEnglish (US)
Title of host publicationAIAA Guidance, Navigation, and Control Conference, 2017
PublisherAmerican Institute of Aeronautics and Astronautics Inc, AIAA
ISBN (Print)9781624104503
StatePublished - Jan 1 2017
EventAIAA Guidance, Navigation, and Control Conference, 2017 - Grapevine, United States
Duration: Jan 9 2017Jan 13 2017

Publication series

NameAIAA Guidance, Navigation, and Control Conference, 2017

Other

OtherAIAA Guidance, Navigation, and Control Conference, 2017
CountryUnited States
CityGrapevine
Period1/9/171/13/17

Fingerprint

Aircraft
Antennas
Cameras
Optical sensors
Kalman filters
Computer vision
Global positioning system
Navigation
Rotors
Detectors
Hardware
Processing

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Deangelo, M. P., & Horn, J. F. (2017). Aerial vehicle localization using generic landmarks. In AIAA Guidance, Navigation, and Control Conference, 2017 (AIAA Guidance, Navigation, and Control Conference, 2017). American Institute of Aeronautics and Astronautics Inc, AIAA.
Deangelo, Mark P. ; Horn, Joseph Francis. / Aerial vehicle localization using generic landmarks. AIAA Guidance, Navigation, and Control Conference, 2017. American Institute of Aeronautics and Astronautics Inc, AIAA, 2017. (AIAA Guidance, Navigation, and Control Conference, 2017).
@inproceedings{3418ae23d82645bf872b396929fc2775,
title = "Aerial vehicle localization using generic landmarks",
abstract = "This research presents a new method to localize an aircraft without GPS using fixed, generic landmarks observed from an optical sensor. Computer vision object detectors are trained to detect abundant generic landmarks referred as buildings, fields, trees, and road intersections from aerial perspectives. Various landmark attributes and spatial relationships to other landmarks are used to help associate observed landmarks with reference landmarks, which are processed offline before a flight. During a flight, the aircraft navigates with attitude, heading, airspeed, and altitude measurements and obtains measurement corrections by processing aerial photos with similar generic landmark detection techniques. Landmark coordinates extracted from the aircraft’s camera images and inertial measurements are combined into an unscented Kalman filter to obtain an estimate of the aircraft’s position and wind velocities. The objective is to achieve practical navigation performance using available autopilot hardware and a downward pointing camera. The method is demonstrated with an airplane simulation and high resolution orthoimagery. The simulations indicate feasible localization results for outdoor visual flight conditions. Finally, real world flight test results demonstrate localization accuracy within two feet for a quad-rotor flying in an indoor lab at an altitude of ten feet.",
author = "Deangelo, {Mark P.} and Horn, {Joseph Francis}",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
isbn = "9781624104503",
series = "AIAA Guidance, Navigation, and Control Conference, 2017",
publisher = "American Institute of Aeronautics and Astronautics Inc, AIAA",
booktitle = "AIAA Guidance, Navigation, and Control Conference, 2017",

}

Deangelo, MP & Horn, JF 2017, Aerial vehicle localization using generic landmarks. in AIAA Guidance, Navigation, and Control Conference, 2017. AIAA Guidance, Navigation, and Control Conference, 2017, American Institute of Aeronautics and Astronautics Inc, AIAA, AIAA Guidance, Navigation, and Control Conference, 2017, Grapevine, United States, 1/9/17.

Aerial vehicle localization using generic landmarks. / Deangelo, Mark P.; Horn, Joseph Francis.

AIAA Guidance, Navigation, and Control Conference, 2017. American Institute of Aeronautics and Astronautics Inc, AIAA, 2017. (AIAA Guidance, Navigation, and Control Conference, 2017).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Aerial vehicle localization using generic landmarks

AU - Deangelo, Mark P.

AU - Horn, Joseph Francis

PY - 2017/1/1

Y1 - 2017/1/1

N2 - This research presents a new method to localize an aircraft without GPS using fixed, generic landmarks observed from an optical sensor. Computer vision object detectors are trained to detect abundant generic landmarks referred as buildings, fields, trees, and road intersections from aerial perspectives. Various landmark attributes and spatial relationships to other landmarks are used to help associate observed landmarks with reference landmarks, which are processed offline before a flight. During a flight, the aircraft navigates with attitude, heading, airspeed, and altitude measurements and obtains measurement corrections by processing aerial photos with similar generic landmark detection techniques. Landmark coordinates extracted from the aircraft’s camera images and inertial measurements are combined into an unscented Kalman filter to obtain an estimate of the aircraft’s position and wind velocities. The objective is to achieve practical navigation performance using available autopilot hardware and a downward pointing camera. The method is demonstrated with an airplane simulation and high resolution orthoimagery. The simulations indicate feasible localization results for outdoor visual flight conditions. Finally, real world flight test results demonstrate localization accuracy within two feet for a quad-rotor flying in an indoor lab at an altitude of ten feet.

AB - This research presents a new method to localize an aircraft without GPS using fixed, generic landmarks observed from an optical sensor. Computer vision object detectors are trained to detect abundant generic landmarks referred as buildings, fields, trees, and road intersections from aerial perspectives. Various landmark attributes and spatial relationships to other landmarks are used to help associate observed landmarks with reference landmarks, which are processed offline before a flight. During a flight, the aircraft navigates with attitude, heading, airspeed, and altitude measurements and obtains measurement corrections by processing aerial photos with similar generic landmark detection techniques. Landmark coordinates extracted from the aircraft’s camera images and inertial measurements are combined into an unscented Kalman filter to obtain an estimate of the aircraft’s position and wind velocities. The objective is to achieve practical navigation performance using available autopilot hardware and a downward pointing camera. The method is demonstrated with an airplane simulation and high resolution orthoimagery. The simulations indicate feasible localization results for outdoor visual flight conditions. Finally, real world flight test results demonstrate localization accuracy within two feet for a quad-rotor flying in an indoor lab at an altitude of ten feet.

UR - http://www.scopus.com/inward/record.url?scp=85017557656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017557656&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781624104503

T3 - AIAA Guidance, Navigation, and Control Conference, 2017

BT - AIAA Guidance, Navigation, and Control Conference, 2017

PB - American Institute of Aeronautics and Astronautics Inc, AIAA

ER -

Deangelo MP, Horn JF. Aerial vehicle localization using generic landmarks. In AIAA Guidance, Navigation, and Control Conference, 2017. American Institute of Aeronautics and Astronautics Inc, AIAA. 2017. (AIAA Guidance, Navigation, and Control Conference, 2017).