Enhanced Rooftop Solar Panel Detection by Efficiently Aggregating Local Features
This addresses the problem of scalable solar panel monitoring for urban planning and renewable energy assessment, though it appears incremental in methodology.
The paper tackles rooftop solar panel detection from satellite images by combining CNN-extracted local features with VLAD aggregation and traditional ML classifiers, achieving classification scores exceeding 0.9 across three cities. It also proposes a 3-phase approach for efficient model adaptation to new regions with limited labeled data.
In this paper, we present an enhanced Convolutional Neural Network (CNN)-based rooftop solar photovoltaic (PV) panel detection approach using satellite images. We propose to use pre-trained CNN-based model to extract the local convolutional features of rooftops. These local features are then combined using the Vectors of Locally Aggregated Descriptors (VLAD) technique to obtain rooftop-level global features, which are then used to train traditional Machine Learning (ML) models to identify rooftop images that do and do not contain PV panels. On the dataset used in this study, the proposed approach achieved rooftop-PV classification scores exceeding the predefined threshold of 0.9 across all three cities for each of the feature extractor networks evaluated. Moreover, we propose a 3-phase approach to enable efficient utilization of the previously trained models on a new city or region with limited labelled data. We illustrate the effectiveness of this 3-phase approach for multi-city rooftop-PV detection task.