The EAVISE Solar Panel Dataset consists a solar panel training set, containing 2500 solar panel annotations and a larger image 16000x16000 aerial image with solar panels blacked out, containing the 150000 negatives random samples collected for model training. We also provide a test image of a single 2x2km urban area (Sint-Truiden, Belgium) with a resolution of 25cm/pixel combined with solar panel installation annotations. The image has an original resolution of 8000x8000 pixels but was upscaled using bicubic interpolation to a resolution of 16000x16000 pixels to provide enough pixel information per individual solar panel (19x14 pixels).
Both training and test data is made publicly available, to encourage further research in this area.
The data was originally supplied by AGIV, as part of the publicly available medium-scale aerial footage of Flanders.
Positive training dataset can be downloaded by clicking the following link. [right click - save as]
The large negative training image, with blacked solar panels - regions to ignore -, can be downloaded by clicking the following link. [right click - save as]
Annotations for the positive training set can be found by clicking the following link.
If you plan to use this dataset, we require you to cite the following publication:
2016; Detection of solar panel installations in RGB aerial imaging: a comparative study.; Puttemans S, Van Ranst W, Goedemé T; Proceedings of GEOBIA2016; published; Enschede, The Netherlands; 14-16 September 2016.