Browsing by Author "Eltner, Anette"

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • ItemOpen Access
    Dataset for object detection of charcoal kiln sites
    (Technische Universität Dresden, 2025-12-18) Rünger, Carolin; Neubauer, Grit; Zamboni, Pedro; Van der Maaten-Theunissen, Marieke; Eltner, Anette
    This 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.
  • ItemOpen Access
    RillGrowEvaluationTime-LapseSfM
    (Technische Universität Dresden, 2024-08-29) Eltner, Anette
    This project contains data for the evaluation and calibration of model outputs of several thousand runs of the soil erosion model RillGrow. For more information about the data see the read.me.
  • ItemOpen Access
    Structure from motion cross-scale dataset on agricultural areas in eastern Germany over a period of 3.5 years – plot scale, single slope scale, and catchment scale
    (Technische Universität Dresden, 2026-02-05) Epple, Lea; Eltner, Anette; Grothum, Oliver; Bienert, Anne
    This study presents a unpresented approach to enhance soil erosion modelling through the utilisation of nested high-resolution spatio-temporal data obtained through structure from motion (SfM) photogrammetry. This technique permits comprehensive observation of soil surface elevation changes during precipitation events, encompassing data acquisition at diverse scales, from plot to slope to micro-catchment. The study presents a unique dataset that integrates high-resolution time-lapse photogrammetry, field measurements, and UAV (uncrewed aerial vehicle) photogrammetric data, collected over nearly four years. This dataset is intended to enhance the understanding of soil erosion processes and serve as a valuable resource for model evaluation and calibration. The authors encourage the broader scientific community to utilise and expand this dataset, which is expected to contribute to the development of more accurate soil erosion models, thereby improving predictions and management strategies.