Browsing by Author "Eltner, Anette"

Now showing 1 - 6 of 6

Open 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.
Open Access
Dataset: Image-based water stage measurement with deep learning
(Technische Universität Dresden, 2020-04-06) Eltner, Anette
This dataset contains the results of the application of deep learning to classify water areas in images captured with a low-cost Raspberry Pi camera. Furthermore, the photogrammetrically measured 3D point cloud of the shore and the extracted water stage information is included as well as the comparison between camera gauge measurement and an independent reference gauge measurement.
Open Access
Flow velocity and discharge measurement in rivers using terrestrial and UAV imagery
(Technische Universität Dresden, 2019-06-11) Eltner, Anette
An automatic workflow is introduced, including an image-based tracking tool, to measure surface flow velocities in rivers. The method is based on PTV and comprises an automatic definition of the search area for particles to track. Tracking is performed in the original images. Only the final tracks are geo-referenced, intersecting the image observations with water surface in object space. Detected particles and corresponding feature tracks are filtered considering particle and flow characteristics to mitigate the impact of sun glare and outliers. The method can be applied to different perspectives, including terrestrial and aerial (i.e. UAV) imagery. To account for camera movements images can be co-registered in an automatic approach. In addition to velocity estimates, discharge is calculated using the surface velocities and wetted cross-section derived from surface models computed with SfM and multi-media photogrammetry. The workflow is tested at two river reaches (paved and natural) in Germany. Reference data is provided by ADCP measurements. At the paved river reach highest deviations of flow velocity and discharge reach 5% and 4%, respectively. At the natural river deviations are larger (26% and 20%, respectively) due to the irregular cross-section shapes hindering accurate contrasting of ADCP- and image-based results. The provided tool enables the measurement of surface flow velocities independently of the perspective from which images are acquired. With the contact-less measurement spatially distributed velocity fields can be estimated and river discharge in previously ungauged and unmeasured regions can be calculated.
Open 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.
Open Access
StageDetect - An image-based tool for automatic water stage detection - image dataset
(Technische Universität Dresden, 2018-10-02) Eltner, Anette
The dataset includes image sets and data to reference the image measurements. The image sets and datasets are used for figure 3 in the in the WRR manuscript 'Automatic image-based water stage measurement for long-term observations in ungauged catchments'. The image sets comprises the master image of the image sequences captured in frequent interval with Raspberry Pi cameras at the river Wesenitz and Wernersbach in Saxony, Germany. If entire image sequences (instead of single masters) are requested (they are not provided here due to large data size), please contact Anette.Eltner@tu-dresden.de
Open 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.