Landmark-aided localization for air vehicles using learned object detectors

Mark P. DeAngelo, Joseph Francis Horn

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

1 Citation (Scopus)

Abstract

This research presents a real time method to localize an aircraft without GPS using fixed landmarks observed from an optical sensor. The objective is to achieve practical navigation performance using available autopilot hardware and a downward pointing camera. Computer vision cascade object detectors are trained to detect selected landmarks prior to a flight. The method also explores aircraft localization using roads between landmark updates. During a flight, the aircraft navigates with inertial measurements and obtains measurement updates when landmarks are detected. Inertial measurements and information extracted from the aircraft’s camera images are combined into an unscented Kalman filter to obtain an estimate of the aircraft’s position and wind velocities.

Original languageEnglish (US)
Title of host publicationAIAA Guidance, Navigation, and Control Conference
PublisherAmerican Institute of Aeronautics and Astronautics Inc, AIAA
ISBN (Print)9781624103896
StatePublished - Jan 1 2016
EventAIAA Guidance, Navigation, and Control Conference, 2016 - San Diego, United States
Duration: Jan 4 2016Jan 8 2016

Publication series

Name2016 AIAA Guidance, Navigation, and Control Conference

Other

OtherAIAA Guidance, Navigation, and Control Conference, 2016
CountryUnited States
CitySan Diego
Period1/4/161/8/16

Fingerprint

Aircraft
Detectors
Air
Cameras
Optical sensors
Kalman filters
Computer vision
Global positioning system
Navigation
Hardware

All Science Journal Classification (ASJC) codes

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

Cite this

DeAngelo, M. P., & Horn, J. F. (2016). Landmark-aided localization for air vehicles using learned object detectors. In AIAA Guidance, Navigation, and Control Conference (2016 AIAA Guidance, Navigation, and Control Conference). American Institute of Aeronautics and Astronautics Inc, AIAA.
DeAngelo, Mark P. ; Horn, Joseph Francis. / Landmark-aided localization for air vehicles using learned object detectors. AIAA Guidance, Navigation, and Control Conference. American Institute of Aeronautics and Astronautics Inc, AIAA, 2016. (2016 AIAA Guidance, Navigation, and Control Conference).
@inproceedings{037672ced5e340eabd7fb09297785205,
title = "Landmark-aided localization for air vehicles using learned object detectors",
abstract = "This research presents a real time method to localize an aircraft without GPS using fixed landmarks observed from an optical sensor. The objective is to achieve practical navigation performance using available autopilot hardware and a downward pointing camera. Computer vision cascade object detectors are trained to detect selected landmarks prior to a flight. The method also explores aircraft localization using roads between landmark updates. During a flight, the aircraft navigates with inertial measurements and obtains measurement updates when landmarks are detected. Inertial measurements and information extracted from the aircraft’s camera images are combined into an unscented Kalman filter to obtain an estimate of the aircraft’s position and wind velocities.",
author = "DeAngelo, {Mark P.} and Horn, {Joseph Francis}",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
isbn = "9781624103896",
series = "2016 AIAA Guidance, Navigation, and Control Conference",
publisher = "American Institute of Aeronautics and Astronautics Inc, AIAA",
booktitle = "AIAA Guidance, Navigation, and Control Conference",

}

DeAngelo, MP & Horn, JF 2016, Landmark-aided localization for air vehicles using learned object detectors. in AIAA Guidance, Navigation, and Control Conference. 2016 AIAA Guidance, Navigation, and Control Conference, American Institute of Aeronautics and Astronautics Inc, AIAA, AIAA Guidance, Navigation, and Control Conference, 2016, San Diego, United States, 1/4/16.

Landmark-aided localization for air vehicles using learned object detectors. / DeAngelo, Mark P.; Horn, Joseph Francis.

AIAA Guidance, Navigation, and Control Conference. American Institute of Aeronautics and Astronautics Inc, AIAA, 2016. (2016 AIAA Guidance, Navigation, and Control Conference).

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

TY - GEN

T1 - Landmark-aided localization for air vehicles using learned object detectors

AU - DeAngelo, Mark P.

AU - Horn, Joseph Francis

PY - 2016/1/1

Y1 - 2016/1/1

N2 - This research presents a real time method to localize an aircraft without GPS using fixed landmarks observed from an optical sensor. The objective is to achieve practical navigation performance using available autopilot hardware and a downward pointing camera. Computer vision cascade object detectors are trained to detect selected landmarks prior to a flight. The method also explores aircraft localization using roads between landmark updates. During a flight, the aircraft navigates with inertial measurements and obtains measurement updates when landmarks are detected. Inertial measurements and information extracted from the aircraft’s camera images are combined into an unscented Kalman filter to obtain an estimate of the aircraft’s position and wind velocities.

AB - This research presents a real time method to localize an aircraft without GPS using fixed landmarks observed from an optical sensor. The objective is to achieve practical navigation performance using available autopilot hardware and a downward pointing camera. Computer vision cascade object detectors are trained to detect selected landmarks prior to a flight. The method also explores aircraft localization using roads between landmark updates. During a flight, the aircraft navigates with inertial measurements and obtains measurement updates when landmarks are detected. Inertial measurements and information extracted from the aircraft’s camera images are combined into an unscented Kalman filter to obtain an estimate of the aircraft’s position and wind velocities.

UR - http://www.scopus.com/inward/record.url?scp=84958063792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958063792&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84958063792

SN - 9781624103896

T3 - 2016 AIAA Guidance, Navigation, and Control Conference

BT - AIAA Guidance, Navigation, and Control Conference

PB - American Institute of Aeronautics and Astronautics Inc, AIAA

ER -

DeAngelo MP, Horn JF. Landmark-aided localization for air vehicles using learned object detectors. In AIAA Guidance, Navigation, and Control Conference. American Institute of Aeronautics and Astronautics Inc, AIAA. 2016. (2016 AIAA Guidance, Navigation, and Control Conference).