Vision-based target tracking with adaptive target state estimator

Ramachandra J. Sattigeri, Eric Johnson, Anthony J. Calise, Jincheol Ha

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

10 Citations (Scopus)

Abstract

This paper presents an approach to vision-based target tracking with a neural network (NN) augmented Kalman filter as the adaptive target state estimator. The vision sensor onboard the follower (tracker) aircraft is a single camera. Real-time image processing implemented in the onboard flight computer is used to derive measurements of relative bearing (azimuth and elevation angles) and the maximum angle subtended by the target aircraft on the image plane. These measurements are used to update the NN augmented Kalman filter. This filter generates estimates of the target aircraft position, velocity and acceleration in inertial 3D space that are used in the guidance and flight control law to guide the follower aircraft relative to the target aircraft. Applications of the presented approach include vision-based autonomous formation flight, pursuit and autonomous aerial refueling. The NN augmenting the Kalman filter estimates the target acceleration and hence provides for robust state estimation in the presence of unmodeled target maneuvers. Vision-in-the-loop simulation results obtained in a 6DOF real-time simulation of vision-based autonomous formation flight are presented to illustrate the efficacy of the adaptive target state estimator design.

Original languageEnglish (US)
Title of host publicationCollection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007
Pages4849-4861
Number of pages13
StatePublished - Dec 24 2007
EventAIAA Guidance, Navigation, and Control Conference 2007 - Hilton Head, SC, United States
Duration: Aug 20 2007Aug 23 2007

Publication series

NameCollection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007
Volume5

Other

OtherAIAA Guidance, Navigation, and Control Conference 2007
CountryUnited States
CityHilton Head, SC
Period8/20/078/23/07

Fingerprint

Target tracking
Aircraft
Kalman filters
Neural networks
Bearings (structural)
State estimation
Image processing
Cameras
Antennas
Sensors

All Science Journal Classification (ASJC) codes

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

Cite this

Sattigeri, R. J., Johnson, E., Calise, A. J., & Ha, J. (2007). Vision-based target tracking with adaptive target state estimator. In Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007 (pp. 4849-4861). (Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007; Vol. 5).
Sattigeri, Ramachandra J. ; Johnson, Eric ; Calise, Anthony J. ; Ha, Jincheol. / Vision-based target tracking with adaptive target state estimator. Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007. 2007. pp. 4849-4861 (Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007).
@inproceedings{23712235f3ec4d5aa34f236da290b91a,
title = "Vision-based target tracking with adaptive target state estimator",
abstract = "This paper presents an approach to vision-based target tracking with a neural network (NN) augmented Kalman filter as the adaptive target state estimator. The vision sensor onboard the follower (tracker) aircraft is a single camera. Real-time image processing implemented in the onboard flight computer is used to derive measurements of relative bearing (azimuth and elevation angles) and the maximum angle subtended by the target aircraft on the image plane. These measurements are used to update the NN augmented Kalman filter. This filter generates estimates of the target aircraft position, velocity and acceleration in inertial 3D space that are used in the guidance and flight control law to guide the follower aircraft relative to the target aircraft. Applications of the presented approach include vision-based autonomous formation flight, pursuit and autonomous aerial refueling. The NN augmenting the Kalman filter estimates the target acceleration and hence provides for robust state estimation in the presence of unmodeled target maneuvers. Vision-in-the-loop simulation results obtained in a 6DOF real-time simulation of vision-based autonomous formation flight are presented to illustrate the efficacy of the adaptive target state estimator design.",
author = "Sattigeri, {Ramachandra J.} and Eric Johnson and Calise, {Anthony J.} and Jincheol Ha",
year = "2007",
month = "12",
day = "24",
language = "English (US)",
isbn = "1563479044",
series = "Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007",
pages = "4849--4861",
booktitle = "Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007",

}

Sattigeri, RJ, Johnson, E, Calise, AJ & Ha, J 2007, Vision-based target tracking with adaptive target state estimator. in Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007. Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007, vol. 5, pp. 4849-4861, AIAA Guidance, Navigation, and Control Conference 2007, Hilton Head, SC, United States, 8/20/07.

Vision-based target tracking with adaptive target state estimator. / Sattigeri, Ramachandra J.; Johnson, Eric; Calise, Anthony J.; Ha, Jincheol.

Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007. 2007. p. 4849-4861 (Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007; Vol. 5).

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

TY - GEN

T1 - Vision-based target tracking with adaptive target state estimator

AU - Sattigeri, Ramachandra J.

AU - Johnson, Eric

AU - Calise, Anthony J.

AU - Ha, Jincheol

PY - 2007/12/24

Y1 - 2007/12/24

N2 - This paper presents an approach to vision-based target tracking with a neural network (NN) augmented Kalman filter as the adaptive target state estimator. The vision sensor onboard the follower (tracker) aircraft is a single camera. Real-time image processing implemented in the onboard flight computer is used to derive measurements of relative bearing (azimuth and elevation angles) and the maximum angle subtended by the target aircraft on the image plane. These measurements are used to update the NN augmented Kalman filter. This filter generates estimates of the target aircraft position, velocity and acceleration in inertial 3D space that are used in the guidance and flight control law to guide the follower aircraft relative to the target aircraft. Applications of the presented approach include vision-based autonomous formation flight, pursuit and autonomous aerial refueling. The NN augmenting the Kalman filter estimates the target acceleration and hence provides for robust state estimation in the presence of unmodeled target maneuvers. Vision-in-the-loop simulation results obtained in a 6DOF real-time simulation of vision-based autonomous formation flight are presented to illustrate the efficacy of the adaptive target state estimator design.

AB - This paper presents an approach to vision-based target tracking with a neural network (NN) augmented Kalman filter as the adaptive target state estimator. The vision sensor onboard the follower (tracker) aircraft is a single camera. Real-time image processing implemented in the onboard flight computer is used to derive measurements of relative bearing (azimuth and elevation angles) and the maximum angle subtended by the target aircraft on the image plane. These measurements are used to update the NN augmented Kalman filter. This filter generates estimates of the target aircraft position, velocity and acceleration in inertial 3D space that are used in the guidance and flight control law to guide the follower aircraft relative to the target aircraft. Applications of the presented approach include vision-based autonomous formation flight, pursuit and autonomous aerial refueling. The NN augmenting the Kalman filter estimates the target acceleration and hence provides for robust state estimation in the presence of unmodeled target maneuvers. Vision-in-the-loop simulation results obtained in a 6DOF real-time simulation of vision-based autonomous formation flight are presented to illustrate the efficacy of the adaptive target state estimator design.

UR - http://www.scopus.com/inward/record.url?scp=37249016883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=37249016883&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:37249016883

SN - 1563479044

SN - 9781563479045

T3 - Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007

SP - 4849

EP - 4861

BT - Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007

ER -

Sattigeri RJ, Johnson E, Calise AJ, Ha J. Vision-based target tracking with adaptive target state estimator. In Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007. 2007. p. 4849-4861. (Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2007).