Large-scale solar panel mapping from aerial images using deep convolutional networks

Jiangye Yuan; Hsiu Han Lexie Yang; Olufemi A. Omitaomu; Budhendra L. Bhaduri

doi:10.1109/BigData.2016.7840915

Large-scale solar panel mapping from aerial images using deep convolutional networks

Jiangye Yuan, Hsiu Han Lexie Yang, Olufemi A. Omitaomu, Budhendra L. Bhaduri

Oak Ridge National Laboratory

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

71 Scopus citations

Abstract

Up-to-date maps of installed solar photovoltaic panels are a critical input for policy and financial assessment of solar distributed generation. However, such maps for large areas are not available. With high coverage and low cost, aerial images enable large-scale mapping, but it is highly difficult to automatically identify solar panels from images, which are small objects with varying appearances dispersed in complex scenes. We introduce a new approach based on deep convolutional networks, which effectively learns to delineate solar panels in aerial scenes. The approach is applied to mapping solar panels in imagery covering 200 square kilometers in two cities, using only 12 square kilometers of training data that are manually labeled. Results are generated efficiently with an accuracy comparable to manual mapping, demonstrating the effectiveness and scalability of our approach.

Original language	English
Title of host publication	Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016
Editors	Ronay Ak, George Karypis, Yinglong Xia, Xiaohua Tony Hu, Philip S. Yu, James Joshi, Lyle Ungar, Ling Liu, Aki-Hiro Sato, Toyotaro Suzumura, Sudarsan Rachuri, Rama Govindaraju, Weijia Xu
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2703-2708
Number of pages	6
ISBN (Electronic)	9781467390040
DOIs	https://doi.org/10.1109/BigData.2016.7840915
State	Published - 2016
Event	4th IEEE International Conference on Big Data, Big Data 2016 - Washington, United States Duration: Dec 5 2016 → Dec 8 2016

Publication series

Name	Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016

Conference

Conference	4th IEEE International Conference on Big Data, Big Data 2016
Country/Territory	United States
City	Washington
Period	12/5/16 → 12/8/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Solar PV panel
convolutional network
mapping

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/BigData.2016.7840915

Cite this

Yuan, J., Yang, H. H. L., Omitaomu, O. A., & Bhaduri, B. L. (2016). Large-scale solar panel mapping from aerial images using deep convolutional networks. In R. Ak, G. Karypis, Y. Xia, X. T. Hu, P. S. Yu, J. Joshi, L. Ungar, L. Liu, A.-H. Sato, T. Suzumura, S. Rachuri, R. Govindaraju, & W. Xu (Eds.), Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016 (pp. 2703-2708). Article 7840915 (Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigData.2016.7840915

Yuan, Jiangye ; Yang, Hsiu Han Lexie ; Omitaomu, Olufemi A. et al. / Large-scale solar panel mapping from aerial images using deep convolutional networks. Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016. editor / Ronay Ak ; George Karypis ; Yinglong Xia ; Xiaohua Tony Hu ; Philip S. Yu ; James Joshi ; Lyle Ungar ; Ling Liu ; Aki-Hiro Sato ; Toyotaro Suzumura ; Sudarsan Rachuri ; Rama Govindaraju ; Weijia Xu. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 2703-2708 (Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016).

@inproceedings{56771fa56b77461facd7385736d8c266,

title = "Large-scale solar panel mapping from aerial images using deep convolutional networks",

abstract = "Up-to-date maps of installed solar photovoltaic panels are a critical input for policy and financial assessment of solar distributed generation. However, such maps for large areas are not available. With high coverage and low cost, aerial images enable large-scale mapping, but it is highly difficult to automatically identify solar panels from images, which are small objects with varying appearances dispersed in complex scenes. We introduce a new approach based on deep convolutional networks, which effectively learns to delineate solar panels in aerial scenes. The approach is applied to mapping solar panels in imagery covering 200 square kilometers in two cities, using only 12 square kilometers of training data that are manually labeled. Results are generated efficiently with an accuracy comparable to manual mapping, demonstrating the effectiveness and scalability of our approach.",

keywords = "Solar PV panel, convolutional network, mapping",

author = "Jiangye Yuan and Yang, {Hsiu Han Lexie} and Omitaomu, {Olufemi A.} and Bhaduri, {Budhendra L.}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 4th IEEE International Conference on Big Data, Big Data 2016 ; Conference date: 05-12-2016 Through 08-12-2016",

year = "2016",

doi = "10.1109/BigData.2016.7840915",

language = "English",

series = "Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016",

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

pages = "2703--2708",

editor = "Ronay Ak and George Karypis and Yinglong Xia and Hu, {Xiaohua Tony} and Yu, {Philip S.} and James Joshi and Lyle Ungar and Ling Liu and Aki-Hiro Sato and Toyotaro Suzumura and Sudarsan Rachuri and Rama Govindaraju and Weijia Xu",

booktitle = "Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016",

}

Yuan, J, Yang, HHL , Omitaomu, OA & Bhaduri, BL 2016, Large-scale solar panel mapping from aerial images using deep convolutional networks. in R Ak, G Karypis, Y Xia, XT Hu, PS Yu, J Joshi, L Ungar, L Liu, A-H Sato, T Suzumura, S Rachuri, R Govindaraju & W Xu (eds), Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016., 7840915, Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016, Institute of Electrical and Electronics Engineers Inc., pp. 2703-2708, 4th IEEE International Conference on Big Data, Big Data 2016, Washington, United States, 12/5/16. https://doi.org/10.1109/BigData.2016.7840915

Large-scale solar panel mapping from aerial images using deep convolutional networks. / Yuan, Jiangye; Yang, Hsiu Han Lexie ; Omitaomu, Olufemi A. et al.
Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016. ed. / Ronay Ak; George Karypis; Yinglong Xia; Xiaohua Tony Hu; Philip S. Yu; James Joshi; Lyle Ungar; Ling Liu; Aki-Hiro Sato; Toyotaro Suzumura; Sudarsan Rachuri; Rama Govindaraju; Weijia Xu. Institute of Electrical and Electronics Engineers Inc., 2016. p. 2703-2708 7840915 (Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016).

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

TY - GEN

T1 - Large-scale solar panel mapping from aerial images using deep convolutional networks

AU - Yuan, Jiangye

AU - Yang, Hsiu Han Lexie

AU - Omitaomu, Olufemi A.

AU - Bhaduri, Budhendra L.

PY - 2016

Y1 - 2016

N2 - Up-to-date maps of installed solar photovoltaic panels are a critical input for policy and financial assessment of solar distributed generation. However, such maps for large areas are not available. With high coverage and low cost, aerial images enable large-scale mapping, but it is highly difficult to automatically identify solar panels from images, which are small objects with varying appearances dispersed in complex scenes. We introduce a new approach based on deep convolutional networks, which effectively learns to delineate solar panels in aerial scenes. The approach is applied to mapping solar panels in imagery covering 200 square kilometers in two cities, using only 12 square kilometers of training data that are manually labeled. Results are generated efficiently with an accuracy comparable to manual mapping, demonstrating the effectiveness and scalability of our approach.

AB - Up-to-date maps of installed solar photovoltaic panels are a critical input for policy and financial assessment of solar distributed generation. However, such maps for large areas are not available. With high coverage and low cost, aerial images enable large-scale mapping, but it is highly difficult to automatically identify solar panels from images, which are small objects with varying appearances dispersed in complex scenes. We introduce a new approach based on deep convolutional networks, which effectively learns to delineate solar panels in aerial scenes. The approach is applied to mapping solar panels in imagery covering 200 square kilometers in two cities, using only 12 square kilometers of training data that are manually labeled. Results are generated efficiently with an accuracy comparable to manual mapping, demonstrating the effectiveness and scalability of our approach.

KW - Solar PV panel

KW - convolutional network

KW - mapping

UR - http://www.scopus.com/inward/record.url?scp=85015173704&partnerID=8YFLogxK

U2 - 10.1109/BigData.2016.7840915

DO - 10.1109/BigData.2016.7840915

M3 - Conference contribution

AN - SCOPUS:85015173704

T3 - Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016

SP - 2703

EP - 2708

BT - Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016

A2 - Ak, Ronay

A2 - Karypis, George

A2 - Xia, Yinglong

A2 - Hu, Xiaohua Tony

A2 - Yu, Philip S.

A2 - Joshi, James

A2 - Ungar, Lyle

A2 - Liu, Ling

A2 - Sato, Aki-Hiro

A2 - Suzumura, Toyotaro

A2 - Rachuri, Sudarsan

A2 - Govindaraju, Rama

A2 - Xu, Weijia

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE International Conference on Big Data, Big Data 2016

Y2 - 5 December 2016 through 8 December 2016

ER -

Yuan J, Yang HHL , Omitaomu OA , Bhaduri BL. Large-scale solar panel mapping from aerial images using deep convolutional networks. In Ak R, Karypis G, Xia Y, Hu XT, Yu PS, Joshi J, Ungar L, Liu L, Sato AH, Suzumura T, Rachuri S, Govindaraju R, Xu W, editors, Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 2703-2708. 7840915. (Proceedings - 2016 IEEE International Conference on Big Data, Big Data 2016). doi: 10.1109/BigData.2016.7840915

Large-scale solar panel mapping from aerial images using deep convolutional networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this