Solar Roof Panel Extraction from UAV Photogrammetric Point Cloud

Abstract

Many buildings are using solar panels as an additional source of electricity. As solar energy is renewable energy and the maintenance cost of solar panels is cheap. This research uses a statistical approach of analyzing point clouds generated from UAV-based photogrammetric processing. An algorithm has been developed to extract solar panels on the building rooftops. The data acquisition is done using an Unmanned Aerial Vehicle (UAV) platform mounted with an optical sensor. The RGB images acquired are further used to generate a photogrammetric point cloud dataset. Geomatics engineering building of Indian Institute of Technology Roorkee, India is considered as the study area, on which solar panels were already installed on its roof. Normal vectors are computed for each points in the building point cloud dataset. The normal vector has its components in the x-axis, y-axis, and z-axis correspondingly. Based on the contribution of the z-component of normal vectors, the points are classified into roof, facade, and solar panel points respectively. The results obtained are evaluated by comparing classified points with respect to manually classified solar panel points. This comparision suggests that the developed algorithm is effective in extracting the solar roof panels efficiently. This research can be used to calculate the effective area of solar panels.