Exploiting convolutional representations for multiscale human settlement detection: Preliminary results

Dalton Lunga; Dilip Patlolla; Hsiuhan Lexie Yang; Jeanette Weaver; Budhendra Bhadhuri

doi:10.1109/IGARSS.2017.8127822

Exploiting convolutional representations for multiscale human settlement detection: Preliminary results

Dalton Lunga, Dilip Patlolla, Hsiuhan Lexie Yang, Jeanette Weaver, Budhendra Bhadhuri

GeoAI

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

2 Scopus citations

Abstract

We test this premise and explore representation spaces from a single deep convolutional network and their visualization to argue for a novel unified feature extraction framework. The objective is to utilize and re-purpose trained feature extractors without the need for network retraining on three remote sensing tasks i.e. superpixel mapping, pixel-level segmentation and semantic based image visualization. By leveraging the same convolutional feature extractors and viewing them as visual information extractors that encode different settlement representation spaces, we demonstrate a preliminary inductive transfer learning potential on multiscale experiments that incorporate edge-level details up to semantic-level information.

Original language	English
Title of host publication	2017 IEEE International Geoscience and Remote Sensing Symposium
Subtitle of host publication	International Cooperation for Global Awareness, IGARSS 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3779-3782
Number of pages	4
ISBN (Electronic)	9781509049516
DOIs	https://doi.org/10.1109/IGARSS.2017.8127822
State	Published - Dec 1 2017
Event	37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017 - Fort Worth, United States Duration: Jul 23 2017 → Jul 28 2017

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2017-July

Conference

Conference	37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017
Country/Territory	United States
City	Fort Worth
Period	07/23/17 → 07/28/17

Funding

This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes.

Keywords

Convolutional neural networks
Inductive transfer learning
Representation learning
Segmentation
Settlement mapping

Access to Document

10.1109/IGARSS.2017.8127822

Cite this

Lunga, D., Patlolla, D., Yang, H. L., Weaver, J., & Bhadhuri, B. (2017). Exploiting convolutional representations for multiscale human settlement detection: Preliminary results. In 2017 IEEE International Geoscience and Remote Sensing Symposium: International Cooperation for Global Awareness, IGARSS 2017 - Proceedings (pp. 3779-3782). Article 8127822 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2017-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2017.8127822

Lunga, Dalton ; Patlolla, Dilip ; Yang, Hsiuhan Lexie et al. / Exploiting convolutional representations for multiscale human settlement detection : Preliminary results. 2017 IEEE International Geoscience and Remote Sensing Symposium: International Cooperation for Global Awareness, IGARSS 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 3779-3782 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{ee1c8dcb34474d94b46cd622c682d8bc,

title = "Exploiting convolutional representations for multiscale human settlement detection: Preliminary results",

abstract = "We test this premise and explore representation spaces from a single deep convolutional network and their visualization to argue for a novel unified feature extraction framework. The objective is to utilize and re-purpose trained feature extractors without the need for network retraining on three remote sensing tasks i.e. superpixel mapping, pixel-level segmentation and semantic based image visualization. By leveraging the same convolutional feature extractors and viewing them as visual information extractors that encode different settlement representation spaces, we demonstrate a preliminary inductive transfer learning potential on multiscale experiments that incorporate edge-level details up to semantic-level information.",

keywords = "Convolutional neural networks, Inductive transfer learning, Representation learning, Segmentation, Settlement mapping",

author = "Dalton Lunga and Dilip Patlolla and Yang, \{Hsiuhan Lexie\} and Jeanette Weaver and Budhendra Bhadhuri",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017 ; Conference date: 23-07-2017 Through 28-07-2017",

year = "2017",

month = dec,

day = "1",

doi = "10.1109/IGARSS.2017.8127822",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

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

pages = "3779--3782",

booktitle = "2017 IEEE International Geoscience and Remote Sensing Symposium",

}

Lunga, D, Patlolla, D, Yang, HL, Weaver, J & Bhadhuri, B 2017, Exploiting convolutional representations for multiscale human settlement detection: Preliminary results. in 2017 IEEE International Geoscience and Remote Sensing Symposium: International Cooperation for Global Awareness, IGARSS 2017 - Proceedings., 8127822, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2017-July, Institute of Electrical and Electronics Engineers Inc., pp. 3779-3782, 37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017, Fort Worth, United States, 07/23/17. https://doi.org/10.1109/IGARSS.2017.8127822

Exploiting convolutional representations for multiscale human settlement detection: Preliminary results. / Lunga, Dalton; Patlolla, Dilip; Yang, Hsiuhan Lexie et al.
2017 IEEE International Geoscience and Remote Sensing Symposium: International Cooperation for Global Awareness, IGARSS 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 3779-3782 8127822 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2017-July).

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

TY - GEN

T1 - Exploiting convolutional representations for multiscale human settlement detection

T2 - 37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017

AU - Lunga, Dalton

AU - Patlolla, Dilip

AU - Yang, Hsiuhan Lexie

AU - Weaver, Jeanette

AU - Bhadhuri, Budhendra

PY - 2017/12/1

Y1 - 2017/12/1

N2 - We test this premise and explore representation spaces from a single deep convolutional network and their visualization to argue for a novel unified feature extraction framework. The objective is to utilize and re-purpose trained feature extractors without the need for network retraining on three remote sensing tasks i.e. superpixel mapping, pixel-level segmentation and semantic based image visualization. By leveraging the same convolutional feature extractors and viewing them as visual information extractors that encode different settlement representation spaces, we demonstrate a preliminary inductive transfer learning potential on multiscale experiments that incorporate edge-level details up to semantic-level information.

AB - We test this premise and explore representation spaces from a single deep convolutional network and their visualization to argue for a novel unified feature extraction framework. The objective is to utilize and re-purpose trained feature extractors without the need for network retraining on three remote sensing tasks i.e. superpixel mapping, pixel-level segmentation and semantic based image visualization. By leveraging the same convolutional feature extractors and viewing them as visual information extractors that encode different settlement representation spaces, we demonstrate a preliminary inductive transfer learning potential on multiscale experiments that incorporate edge-level details up to semantic-level information.

KW - Convolutional neural networks

KW - Inductive transfer learning

KW - Representation learning

KW - Segmentation

KW - Settlement mapping

UR - https://www.scopus.com/pages/publications/85041845124

U2 - 10.1109/IGARSS.2017.8127822

DO - 10.1109/IGARSS.2017.8127822

M3 - Conference contribution

AN - SCOPUS:85041845124

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 3779

EP - 3782

BT - 2017 IEEE International Geoscience and Remote Sensing Symposium

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 23 July 2017 through 28 July 2017

ER -

Lunga D, Patlolla D, Yang HL, Weaver J, Bhadhuri B. Exploiting convolutional representations for multiscale human settlement detection: Preliminary results. In 2017 IEEE International Geoscience and Remote Sensing Symposium: International Cooperation for Global Awareness, IGARSS 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 3779-3782. 8127822. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2017.8127822

Exploiting convolutional representations for multiscale human settlement detection: Preliminary results

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this