Vision-based multiple model adaptive estimation of ground targets from airborne images

Takuma Nakamura, Eric Johnson

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

Abstract

This paper describes a vision-based multiple model adaptive estimation using UAVs that enables the tracking of a mobile target that changes the system model depending on unknown factors. In our system the machine-learning-based target identification method uses Haar-like classifiers that detects the target position. The system uses multiple extended Kalman filters for each system model and estimates the states of the target through the observed positions. We estimate the probability that each system is true and use the max-probability method to determine the current model. The position controller of the UAVs uses the vision system not only to determine a desired waypoint but also to switch the control law for another model. Implementation of this system is validated through an image-in-the-loop simulation. We also explore an vision-based solution for Mission 7 of the international aerial robotics competition.

Original languageEnglish (US)
Title of host publication2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages598-607
Number of pages10
ISBN (Electronic)9781467393331
DOIs
StatePublished - Jun 30 2016
Event2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016 - Arlington, United States
Duration: Jun 7 2016Jun 10 2016

Publication series

Name2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016

Other

Other2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016
CountryUnited States
CityArlington
Period6/7/166/10/16

Fingerprint

Unmanned aerial vehicles (UAV)
Extended Kalman filters
Learning systems
Identification (control systems)
Robotics
Classifiers
Switches
Antennas
Controllers

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Control and Systems Engineering

Cite this

Nakamura, T., & Johnson, E. (2016). Vision-based multiple model adaptive estimation of ground targets from airborne images. In 2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016 (pp. 598-607). [7502626] (2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICUAS.2016.7502626
Nakamura, Takuma ; Johnson, Eric. / Vision-based multiple model adaptive estimation of ground targets from airborne images. 2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 598-607 (2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016).
@inproceedings{600a691a63604c42ae96366226496063,
title = "Vision-based multiple model adaptive estimation of ground targets from airborne images",
abstract = "This paper describes a vision-based multiple model adaptive estimation using UAVs that enables the tracking of a mobile target that changes the system model depending on unknown factors. In our system the machine-learning-based target identification method uses Haar-like classifiers that detects the target position. The system uses multiple extended Kalman filters for each system model and estimates the states of the target through the observed positions. We estimate the probability that each system is true and use the max-probability method to determine the current model. The position controller of the UAVs uses the vision system not only to determine a desired waypoint but also to switch the control law for another model. Implementation of this system is validated through an image-in-the-loop simulation. We also explore an vision-based solution for Mission 7 of the international aerial robotics competition.",
author = "Takuma Nakamura and Eric Johnson",
year = "2016",
month = "6",
day = "30",
doi = "10.1109/ICUAS.2016.7502626",
language = "English (US)",
series = "2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "598--607",
booktitle = "2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016",
address = "United States",

}

Nakamura, T & Johnson, E 2016, Vision-based multiple model adaptive estimation of ground targets from airborne images. in 2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016., 7502626, 2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016, Institute of Electrical and Electronics Engineers Inc., pp. 598-607, 2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016, Arlington, United States, 6/7/16. https://doi.org/10.1109/ICUAS.2016.7502626

Vision-based multiple model adaptive estimation of ground targets from airborne images. / Nakamura, Takuma; Johnson, Eric.

2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 598-607 7502626 (2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016).

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

TY - GEN

T1 - Vision-based multiple model adaptive estimation of ground targets from airborne images

AU - Nakamura, Takuma

AU - Johnson, Eric

PY - 2016/6/30

Y1 - 2016/6/30

N2 - This paper describes a vision-based multiple model adaptive estimation using UAVs that enables the tracking of a mobile target that changes the system model depending on unknown factors. In our system the machine-learning-based target identification method uses Haar-like classifiers that detects the target position. The system uses multiple extended Kalman filters for each system model and estimates the states of the target through the observed positions. We estimate the probability that each system is true and use the max-probability method to determine the current model. The position controller of the UAVs uses the vision system not only to determine a desired waypoint but also to switch the control law for another model. Implementation of this system is validated through an image-in-the-loop simulation. We also explore an vision-based solution for Mission 7 of the international aerial robotics competition.

AB - This paper describes a vision-based multiple model adaptive estimation using UAVs that enables the tracking of a mobile target that changes the system model depending on unknown factors. In our system the machine-learning-based target identification method uses Haar-like classifiers that detects the target position. The system uses multiple extended Kalman filters for each system model and estimates the states of the target through the observed positions. We estimate the probability that each system is true and use the max-probability method to determine the current model. The position controller of the UAVs uses the vision system not only to determine a desired waypoint but also to switch the control law for another model. Implementation of this system is validated through an image-in-the-loop simulation. We also explore an vision-based solution for Mission 7 of the international aerial robotics competition.

UR - http://www.scopus.com/inward/record.url?scp=84979766130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979766130&partnerID=8YFLogxK

U2 - 10.1109/ICUAS.2016.7502626

DO - 10.1109/ICUAS.2016.7502626

M3 - Conference contribution

AN - SCOPUS:84979766130

T3 - 2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016

SP - 598

EP - 607

BT - 2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Nakamura T, Johnson E. Vision-based multiple model adaptive estimation of ground targets from airborne images. In 2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 598-607. 7502626. (2016 International Conference on Unmanned Aircraft Systems, ICUAS 2016). https://doi.org/10.1109/ICUAS.2016.7502626