Space object classification using model driven and data driven methods

Richard Linares; John L. Crassidis

Space object classification using model driven and data driven methods

Richard Linares, John L. Crassidis

Aerospace Engineering and Mechanics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

In recent years there has been an increase in the number of inactive and debris Space Objects (SOs). This work examines both data driven and model driven SO classification. The model driven approach investigated for this work is based on the Multiple Model Adaptive Estimation approach to extract SO characteristics from observations while estimating the probability the observations belonging to a given class of objects. The data driven methods are based on Principle Component Analysis and Convolutional Neural Network Classification approaches. The performance of these strategies for SO classification is demonstrated via simulated scenarios.

Original language	English (US)
Title of host publication	Spaceflight Mechanics 2016
Editors	Martin T. Ozimek, Renato Zanetti, Angela L. Bowes, Ryan P. Russell, Martin T. Ozimek
Publisher	Univelt Inc.
Pages	4213-4231
Number of pages	19
ISBN (Print)	9780877036333
State	Published - 2016
Event	26th AAS/AIAA Space Flight Mechanics Meeting, 2016 - Napa, United States Duration: Feb 14 2016 → Feb 18 2016

Publication series

Name	Advances in the Astronautical Sciences
Volume	158
ISSN (Print)	0065-3438

Other

Other	26th AAS/AIAA Space Flight Mechanics Meeting, 2016
Country/Territory	United States
City	Napa
Period	2/14/16 → 2/18/16

Find It

Find It at U of M Libraries

Cite this

Space object classification using model driven and data driven methods. / Linares, Richard; Crassidis, John L.
Spaceflight Mechanics 2016. ed. / Martin T. Ozimek; Renato Zanetti; Angela L. Bowes; Ryan P. Russell; Martin T. Ozimek. Univelt Inc., 2016. p. 4213-4231 (Advances in the Astronautical Sciences; Vol. 158).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

@inproceedings{cc908f92702a4dfe8536d5287f7d6fa5,

title = "Space object classification using model driven and data driven methods",

abstract = "In recent years there has been an increase in the number of inactive and debris Space Objects (SOs). This work examines both data driven and model driven SO classification. The model driven approach investigated for this work is based on the Multiple Model Adaptive Estimation approach to extract SO characteristics from observations while estimating the probability the observations belonging to a given class of objects. The data driven methods are based on Principle Component Analysis and Convolutional Neural Network Classification approaches. The performance of these strategies for SO classification is demonstrated via simulated scenarios.",

author = "Richard Linares and Crassidis, {John L.}",

year = "2016",

language = "English (US)",

isbn = "9780877036333",

series = "Advances in the Astronautical Sciences",

publisher = "Univelt Inc.",

pages = "4213--4231",

editor = "Ozimek, {Martin T.} and Renato Zanetti and Bowes, {Angela L.} and Russell, {Ryan P.} and Ozimek, {Martin T.}",

booktitle = "Spaceflight Mechanics 2016",

}

TY - GEN

T1 - Space object classification using model driven and data driven methods

AU - Linares, Richard

AU - Crassidis, John L.

PY - 2016

Y1 - 2016

N2 - In recent years there has been an increase in the number of inactive and debris Space Objects (SOs). This work examines both data driven and model driven SO classification. The model driven approach investigated for this work is based on the Multiple Model Adaptive Estimation approach to extract SO characteristics from observations while estimating the probability the observations belonging to a given class of objects. The data driven methods are based on Principle Component Analysis and Convolutional Neural Network Classification approaches. The performance of these strategies for SO classification is demonstrated via simulated scenarios.

AB - In recent years there has been an increase in the number of inactive and debris Space Objects (SOs). This work examines both data driven and model driven SO classification. The model driven approach investigated for this work is based on the Multiple Model Adaptive Estimation approach to extract SO characteristics from observations while estimating the probability the observations belonging to a given class of objects. The data driven methods are based on Principle Component Analysis and Convolutional Neural Network Classification approaches. The performance of these strategies for SO classification is demonstrated via simulated scenarios.

UR - http://www.scopus.com/inward/record.url?scp=85007358578&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007358578&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85007358578

SN - 9780877036333

T3 - Advances in the Astronautical Sciences

SP - 4213

EP - 4231

BT - Spaceflight Mechanics 2016

A2 - Ozimek, Martin T.

A2 - Zanetti, Renato

A2 - Bowes, Angela L.

A2 - Russell, Ryan P.

A2 - Ozimek, Martin T.

PB - Univelt Inc.

T2 - 26th AAS/AIAA Space Flight Mechanics Meeting, 2016

Y2 - 14 February 2016 through 18 February 2016

ER -

Space object classification using model driven and data driven methods

Abstract

Publication series

Other

Find It

Other files and links

Fingerprint

Cite this