Application of a semantic segmentation convolutional neural network for accurate automatic detection and mapping of solar photovoltaic arrays in aerial imagery

TL;DR

This paper presents a convolutional neural network approach using SegNet for accurate detection and mapping of solar photovoltaic arrays in aerial imagery, improving size and shape estimation over previous methods.

Contribution

The study applies a state-of-the-art segmentation CNN, SegNet, to improve the accuracy of PV array detection and size estimation in aerial images, advancing beyond prior location-focused methods.

Findings

SegNet significantly improves size and shape estimation of PV arrays.

The method outperforms previous CNN-based PV detection algorithms.

Results demonstrate high accuracy on a large, public dataset.

Abstract

We consider the problem of automatically detecting small-scale solar photovoltaic arrays for behind-the-meter energy resource assessment in high resolution aerial imagery. Such algorithms offer a faster and more cost-effective solution to collecting information on distributed solar photovoltaic (PV) arrays, such as their location, capacity, and generated energy. The surface area of PV arrays, a characteristic which can be estimated from aerial imagery, provides an important proxy for array capacity and energy generation. In this work, we employ a state-of-the-art convolutional neural network architecture, called SegNet (Badrinarayanan et. al., 2015), to semantically segment (or map) PV arrays in aerial imagery. This builds on previous work focused on identifying the locations of PV arrays, as opposed to their specific shapes and sizes. We measure the ability of our SegNet implementation to estimate the surface area of PV arrays on a large, publicly available, dataset that has been employed in several previous studies. The results indicate that the SegNet model yields substantial performance improvements with respect to estimating shape and size as compared to a recently proposed convolutional neural network PV detection algorithm.