Satellite recognition and pose estimation using homeomorphic manifold analysis

Haopeng Zhang; Zhiguo Jiang; Ahmed Elgammal

doi:10.1109/TAES.2014.130744

Satellite recognition and pose estimation using homeomorphic manifold analysis

Haopeng Zhang, Zhiguo Jiang, Ahmed Elgammal

SAS - Computer Science

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

We propose a novel monocular vision-based framework for both satellite recognition and pose estimation, using homeomorphic manifold analysis. We use a unified conceptual manifold to represent continuous pose variation of all satellites in the visual input space, learn nonlinear function mapping from conceptual manifold representation to visual inputs, and decompose discrete category variation in the mapping coefficient space. Experimental results on a simulated image data set show the effectiveness and robustness of our approach.

Original language	English (US)
Article number	7073533
Pages (from-to)	785-792
Number of pages	8
Journal	IEEE Transactions on Aerospace and Electronic Systems
Volume	51
Issue number	1
DOIs	https://doi.org/10.1109/TAES.2014.130744
State	Published - Jan 1 2015

All Science Journal Classification (ASJC) codes

Aerospace Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/TAES.2014.130744

Fingerprint Dive into the research topics of 'Satellite recognition and pose estimation using homeomorphic manifold analysis'. Together they form a unique fingerprint.

Cite this

@article{9a2147eb8eb64128abee02c9df09523a,

title = "Satellite recognition and pose estimation using homeomorphic manifold analysis",

abstract = "We propose a novel monocular vision-based framework for both satellite recognition and pose estimation, using homeomorphic manifold analysis. We use a unified conceptual manifold to represent continuous pose variation of all satellites in the visual input space, learn nonlinear function mapping from conceptual manifold representation to visual inputs, and decompose discrete category variation in the mapping coefficient space. Experimental results on a simulated image data set show the effectiveness and robustness of our approach.",

author = "Haopeng Zhang and Zhiguo Jiang and Ahmed Elgammal",

note = "Publisher Copyright: {\textcopyright} 1965-2011 IEEE.",

year = "2015",

month = jan,

day = "1",

doi = "10.1109/TAES.2014.130744",

language = "English (US)",

volume = "51",

pages = "785--792",

journal = "IEEE Transactions on Aerospace and Electronic Systems",

issn = "0018-9251",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - Satellite recognition and pose estimation using homeomorphic manifold analysis

AU - Zhang, Haopeng

AU - Jiang, Zhiguo

AU - Elgammal, Ahmed

PY - 2015/1/1

Y1 - 2015/1/1

N2 - We propose a novel monocular vision-based framework for both satellite recognition and pose estimation, using homeomorphic manifold analysis. We use a unified conceptual manifold to represent continuous pose variation of all satellites in the visual input space, learn nonlinear function mapping from conceptual manifold representation to visual inputs, and decompose discrete category variation in the mapping coefficient space. Experimental results on a simulated image data set show the effectiveness and robustness of our approach.

AB - We propose a novel monocular vision-based framework for both satellite recognition and pose estimation, using homeomorphic manifold analysis. We use a unified conceptual manifold to represent continuous pose variation of all satellites in the visual input space, learn nonlinear function mapping from conceptual manifold representation to visual inputs, and decompose discrete category variation in the mapping coefficient space. Experimental results on a simulated image data set show the effectiveness and robustness of our approach.

UR - http://www.scopus.com/inward/record.url?scp=84927597286&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927597286&partnerID=8YFLogxK

U2 - 10.1109/TAES.2014.130744

DO - 10.1109/TAES.2014.130744

M3 - Article

AN - SCOPUS:84927597286

VL - 51

SP - 785

EP - 792

JO - IEEE Transactions on Aerospace and Electronic Systems

JF - IEEE Transactions on Aerospace and Electronic Systems

SN - 0018-9251

IS - 1

M1 - 7073533

ER -

Satellite recognition and pose estimation using homeomorphic manifold analysis

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this