Rünger, CarolinNeubauer, GritZamboni, PedroVan der Maaten-Theunissen, MariekeEltner, Anette2025-12-182025-12-182025-12-18https://opara.zih.tu-dresden.de/handle/123456789/1914https://doi.org/10.25532/OPARA-1051This dataset provides a collection of processed airborne LiDAR data and associated annotations of historical charcoal kiln sites in the Erzgebirgskreis district of Saxony, Germany for object detection. The starting point is raw LiDAR data, from which a digital terrain model (DTM) was first derived. Based on this, various DTM derivatives were calculated, which are used as three-channel input data (hillshade, slope and sky-view factor) for a convolutional neural network. The dataset includes training, validation and test data, including annotations, as well as trained model weights and configuration files for inference. In addition, model predictions for test areas in the Ore Mountains (Saxony) and for the Kermeter mountain range in the Rureifel (North Rhine-Westphalia) are included. To ensure reproducibility, suitable Conda environments for training and inference with MMDetection v2.28.2 are also provided.Attribution-NonCommercial-ShareAlike 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-sa/4.0/3::34::315::315-022::23::207::207-06