Applying isomap to the learning of hyperspectral image

X. Rosalind Wang; Suresh Kumar; Tobias Kaupp; Ben Upcroft; Hugh Durrant-Whyte

Applying isomap to the learning of hyperspectral image

X. Rosalind Wang
, Suresh Kumar
, Tobias Kaupp
, Ben Upcroft
, Hugh Durrant-Whyte

University of Sydney

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

5 Citations (Scopus)

Abstract

In this paper, we present the application of a non-linear dimensionality reduction technique for the learning and probabilistic classification of hyperspectral image. Hyperspectral image spectroscopy is an emerging technique for geological investigations from airborne or orbital sensors. It gives much greater information content per pixel on the image than a normal colour image. This should greatly help with the autonomous identification of natural and manmade objects in unfamiliar terrains for robotic vehicles. However, the large information content of such data makes interpretation of hyperspectral images time-consuming and userintensive.

Original language	English
Title of host publication	Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005
Publication status	Published - 2005
Externally published	Yes
Event	2005 Australian Conference on Robotics and Automation, ACRA 2005 - Sydney, NSW, Australia Duration: 5 Dec 2005 → 7 Dec 2005

Publication series

Name	Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005

Conference

Conference	2005 Australian Conference on Robotics and Automation, ACRA 2005
Country/Territory	Australia
City	Sydney, NSW
Period	5/12/05 → 7/12/05

Cite this

@inproceedings{55c92d429ccc4856b0872480dad8bc4b,

title = "Applying isomap to the learning of hyperspectral image",

abstract = "In this paper, we present the application of a non-linear dimensionality reduction technique for the learning and probabilistic classification of hyperspectral image. Hyperspectral image spectroscopy is an emerging technique for geological investigations from airborne or orbital sensors. It gives much greater information content per pixel on the image than a normal colour image. This should greatly help with the autonomous identification of natural and manmade objects in unfamiliar terrains for robotic vehicles. However, the large information content of such data makes interpretation of hyperspectral images time-consuming and userintensive.",

author = "Wang, \{X. Rosalind\} and Suresh Kumar and Tobias Kaupp and Ben Upcroft and Hugh Durrant-Whyte",

year = "2005",

language = "English",

isbn = "0958758379",

series = "Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005",

booktitle = "Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005",

note = "2005 Australian Conference on Robotics and Automation, ACRA 2005 ; Conference date: 05-12-2005 Through 07-12-2005",

}

Wang, XR, Kumar, S, Kaupp, T, Upcroft, B & Durrant-Whyte, H 2005, Applying isomap to the learning of hyperspectral image. in Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005. Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005, 2005 Australian Conference on Robotics and Automation, ACRA 2005, Sydney, NSW, Australia, 5/12/05.

Applying isomap to the learning of hyperspectral image. / Wang, X. Rosalind; Kumar, Suresh; Kaupp, Tobias et al.
Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005. 2005. (Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005).

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Applying isomap to the learning of hyperspectral image

AU - Wang, X. Rosalind

AU - Kumar, Suresh

AU - Kaupp, Tobias

AU - Upcroft, Ben

AU - Durrant-Whyte, Hugh

PY - 2005

Y1 - 2005

N2 - In this paper, we present the application of a non-linear dimensionality reduction technique for the learning and probabilistic classification of hyperspectral image. Hyperspectral image spectroscopy is an emerging technique for geological investigations from airborne or orbital sensors. It gives much greater information content per pixel on the image than a normal colour image. This should greatly help with the autonomous identification of natural and manmade objects in unfamiliar terrains for robotic vehicles. However, the large information content of such data makes interpretation of hyperspectral images time-consuming and userintensive.

AB - In this paper, we present the application of a non-linear dimensionality reduction technique for the learning and probabilistic classification of hyperspectral image. Hyperspectral image spectroscopy is an emerging technique for geological investigations from airborne or orbital sensors. It gives much greater information content per pixel on the image than a normal colour image. This should greatly help with the autonomous identification of natural and manmade objects in unfamiliar terrains for robotic vehicles. However, the large information content of such data makes interpretation of hyperspectral images time-consuming and userintensive.

UR - https://www.scopus.com/pages/publications/84862915619

M3 - Conference Paper

AN - SCOPUS:84862915619

SN - 0958758379

SN - 9780958758376

T3 - Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005

BT - Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005

T2 - 2005 Australian Conference on Robotics and Automation, ACRA 2005

Y2 - 5 December 2005 through 7 December 2005

ER -

Applying isomap to the learning of hyperspectral image

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this