Automatic detection and mapping of solar photovoltaic arrays with deep convolutional neural networks in high resolution satellite images

Kaiji He, Long Zhang

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

424 Downloads (Pure)

Abstract

The locations and capacities of household rooftop
solar photovoltaic (PV) arrays are important for power grid
planning. However, it is hard to collect such information manually
as a significant number of PV arrays are distributed dispersedly
in residential areas. With the development of deep learning
model on image recognition, it brings an opportunity to build
an intelligent detector that is able to automatically identify and
delineate PV arrays in satellite images. Convolutional neural
networks (CNN) are ideally suited for this task as CNN has
capability of capturing spatial information of digital images by
convolution operation. In this work, we trained a deep CNN
with manually annotated satellite images taken from a region of
Manchester (UK), and validated our detector with another set
of satellite images taken from the same city. Our results indicate
that the detector is capable to identify PV arrays with a high
accuracy and delineate them in pixel-wise with high precision,
showing the feasibility of our approach.
Original languageEnglish
Title of host publication2020 IEEE 4th Conference on Energy Internet and Energy System Integration: Connecting the Grids Towards a Low-Carbon High-Efficiency Energy System, EI2 2020
Pages3068-3073
Number of pages6
ISBN (Electronic)9781728196060
DOIs
Publication statusPublished - 15 Feb 2021

Publication series

Name2020 IEEE 4th Conference on Energy Internet and Energy System Integration: Connecting the Grids Towards a Low-Carbon High-Efficiency Energy System, EI2 2020

Keywords

  • Deep convolutional neural networks
  • Mask R-CNN
  • Photovoltaic arrays
  • Satellite images

Fingerprint

Dive into the research topics of 'Automatic detection and mapping of solar photovoltaic arrays with deep convolutional neural networks in high resolution satellite images'. Together they form a unique fingerprint.

Cite this