| Work Detail |
Spanish scientists have developed thermal image mapping on dense, high-resolution point clouds that represent the state and geometry of photovoltaic modules and the automatic identification of individual solar panels in 3D space. The proposed methodology provides “exceptionally high” precision. Scientists from the University of Jaén (Spain) have developed a novel method to monitor photovoltaic plants based on remote sensing data. Their method uses an unmanned aerial vehicle (UAV) equipped with a double RGB and thermal camera that flies over a photovoltaic plant. With these two cameras, different algorithms create 3D models. “The key contribution of this study is twofold,” the academics say. “First, the mapping of thermal images onto dense, high-resolution point clouds that represent the state and geometry of solar photovoltaic modules, and second, the automatic identification of individual solar panels in 3D space and their thermal characterization along along its oriented surface. The group used a DJI Matrice 210 UAV equipped with a Zenmuse XT2 camera, which combines a FLIR Tau 2 thermal sensor with a 4K RGB camera. After flying the device over urban and rural plants for half an hour, the images were processed in the Pix4D software. Computer vision algorithms were used to detect individual solar panels. The software first detects chipped edges, then employs morphological operations, then performs edge extraction, and finishes with edge filtering. It uses the data collected from the thermal camera to extract the temperatures of each identified panel. “The final stage consists of estimating the average temperature of each solar panel,” explains the team. “At this point, we have a set of 3D points for each panel. Therefore, the next step comes down to consulting your thermal data and calculating the average temperature. In this way, a representative temperature of the entire panel is calculated.” After testing the detection method and comparing it with real results on the ground, the scientists found that its accuracy was “exceptionally high”, 99.12% in the urban landscape and 99.31% in the rural landscape. Furthermore, 0.88% and 0.69% false negatives were observed, respectively. Regarding the precision indices for extracting the temperature of the photovoltaic panels, they found a minimum observed value of 0.0010 degrees and a maximum of 0.2607 degrees. “This indicates a great agreement between the manually and automatically extracted temperature,” they added. The novel method was presented in “ Automated detection and tracking of photovoltaic modules from 3D remote sensing data ,” published in Applied Energy . “This methodology has significant potential to improve the management, monitoring and evaluation of the performance of photovoltaic solar panel installations, contributing to the advancement of renewable energy technologies,” the researchers concluded. |
