Logo des Repositoriums

Auflistung nach Schlagwort "grassland"

1 - 3 von 3
  • Konferenzbeitrag
    Comparison of UAV- and mowing machine-mounted LiDAR for grassland canopy height estimation
    (44. GIL - Jahrestagung, Biodiversität fördern durch digitale Landwirtschaft, 2024) Bracke, Justus; Storch, Marcel; Bald, Janis; Jarmer, Thomas
    Towards autonomous process monitoring, canopy height estimation in grassland based on data from a mowing machine-mounted LiDAR and a UAV-LiDAR system is compared to manually measured ground truth heights. In a field trial, a LiDAR mounted on the cabin roof of the mowing machine recorded data during the mowing process, while two recording flights before and after the mowing were conducted with a UAV-LiDAR. The data from both systems were processed similarly and parameters such as height estimation method, spatial resolution and percentile filters were systematically varied to investigate their influence on height estimation accuracy. Statistical evaluation showed that canopy height estimates based on the UAV-LiDAR (R² = 0.89, RMSE = 0.05 m) were more accurate and precise than those based on the mowing machine-mounted LiDAR (R² = 0.51, RMSE = 0.08 m). The influence of the different investigated parameters varied.
  • Konferenzbeitrag
    Different methods of yield recordings in grassland – how accurate are they in practice?
    (43. GIL-Jahrestagung, Resiliente Agri-Food-Systeme, 2023) Krug, Priska; Förschner, Adriana; Wiggenhauser, Tobias; Nußbaum, Hansjörg; Weber, Jonas
    The aim of the study is to determine the yields in grassland using various methods. Yield recording in grassland has not been common practice so far. Yields can be recorded using various methods as height measurement, for example by using a rising-plate-meter (Grasshopper), measuring the weight of sample cut or by capturing the weight of harvested biomass. A yield estimation with the Grasshopper is carried out on three plots and is validated via sample cuts. The harvest chain is recorded digitally and the harvest quantity (weight) is measured with the load cells in the loader wagon, a validation is carried out via a wagon scales. The results presents underestimated yields when using the Grasshopper. The recording of harvest weights via the loader wagon's load cells was confirmed by the wagon scales. This method can be easily used in practice, if available. However, a determination of the dry matter content remains key. The correct determination of dry matter is crucial for accurate yield recording, but this is where very great challenges lie, especially for practice. Further investigations have to be carried out.
  • Konferenzbeitrag
    Mapping invasive Lupine on grasslands using UAV images and deep learning
    (44. GIL - Jahrestagung, Biodiversität fördern durch digitale Landwirtschaft, 2024) Wijesingha, Jayan; Schulze-Brüninghoff, Damian; Wachendorf, Michael
    Semi-natural grasslands are threatened by invasive species. This study employs high-resolution images captured by an unmanned aerial vehicle (UAV) and deep learning techniques to map Lupine (Lupinus polyphyllus Lindl.) in grasslands, which is one of the most common invasive species in European grasslands. The methodology involves RGB image acquisition, structure from motion processing, canopy height modelling, and deep learning semantic segmentation model development. The resulting models were trained on RGB data, canopy surface height data, and their combination. The models demonstrate high accuracy and efficacy in identifying Lupine distribution. These models offer a valuable tool for continuously monitoring and managing invasive Lupine, with potential applications in similar environments without retraining. The method is beneficial for early-stage invasion detection, facilitating more targeted management efforts for ecologists.