<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>2026</id>
    <completedYear/>
    <publishedYear>2022</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>103</pageFirst>
    <pageLast>121</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume>90</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2022-03-30</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Classification of Tree Species and Standing Dead Trees with Lidar Point Clouds Using Two Deep Neural Networks: PointCNN and 3DmFV-Net</title>
    <abstract language="eng">Knowledge about tree species distribution is important for forest management and for modeling and protecting biodiversity in forests. Methods based on images are inherently limited to the forest canopy. Airborne lidar data provide information about the trees’ geometric structure, as well as trees beneath the upper canopy layer. In this paper, the potential of two deep learning architectures (PointCNN, 3DmFV-Net) for classification of four different tree classes is evaluated using a lidar dataset acquired at the Bavarian Forest National Park (BFNP) in a leaf-on situation with a maximum point density of about 80 pts/m2. Especially in the case of BFNP, dead wood plays a key role in forest biodiversity. Thus, the presented approaches are applied to the combined classification of living and dead trees. A total of 2721 single trees were delineated in advance using a normalized cut segmentation. The trees were manually labeled into four tree classes (coniferous, deciduous, standing dead tree with crown, and snag). Moreover, a multispectral orthophoto provided additional features, namely the Normalized Difference Vegetation Index. PointCNN with 3D points, laser intensity, and multispectral features resulted in a test accuracy of up to 87.0%. This highlights the potential of deep learning on point clouds in forestry. In contrast, 3DmFV-Net achieved a test accuracy of 73.2% for the same dataset using only the 3D coordinates of the laser points. The results show that the data fusion of lidar and multispectral data is invaluable for differentiation of the tree classes. Classification accuracy increases by up to 16.3% points when adding features generated from the multispectral orthophoto.</abstract>
    <parentTitle language="eng">PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science</parentTitle>
    <identifier type="issn">2512-2819</identifier>
    <identifier type="doi">10.1007/s41064-022-00200-4</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Maximilian Hell</author>
    <author>Melanie Brandmeier</author>
    <author>Sebastian Briechle</author>
    <author>Peter Krzystek</author>
    <collection role="institutes" number="fkv">Fakultät Kunststofftechnik und Vermessung</collection>
    <collection role="oa-colour" number="">Gefördert (Hybrid/DEAL)</collection>
    <thesisPublisher>Hochschule für Angewandte Wissenschaften Würzburg-Schweinfurt</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-fhws/files/2026/Hell_Classification_tree_species.pdf</file>
  </doc>
  <doc>
    <id>5753</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>24</pageNumber>
    <edition/>
    <issue>12</issue>
    <volume>26</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Identifying Plausible Labels from Noisy Training Data for a Land Use and Land Cover Classification Application in Amazônia Legal</title>
    <abstract language="deu">Most studies in the field of land use and land cover (LULC) classification in remote sensing rely on supervised classification, which requires a substantial amount of accurate label data. However, reliable data are often not immediately available, and are obtained through time-consuming manual labor. One potential solution to this problem is the use of already available classification maps, which may not be the true ground truth and may contain noise from multiple possible sources. This is also true for the classification maps of the MapBiomas project, which provides land use and land cover (LULC) maps on a yearly basis, classifying the Amazon basin into more than 24 classes based on the Landsat data. In this study, we utilize the Sentinel-2 data with a higher spatial resolution in conjunction with the MapBiomas maps to evaluate a proposed noise removal method and to improve classification results. We introduce a novel noise detection method that relies on identifying anchor points in feature space through clustering with self-organizing maps (SOM). The pixel label is relabeled using nearest neighbor rules, or can be removed if it is unknown. A challenge in this approach is the quantification of noise in such a real-world dataset. To overcome this problem, highly reliable validation sets were manually created for quantitative performance assessment. The results demonstrate a significant increase in overall accuracy compared to MapBiomas labels, from 79.85% to 89.65%. Additionally, we trained the L2HNet using both MapBiomas labels and the filtered labels from our approach. The overall accuracy for this model reached 93.75% with the filtered labels, compared to the baseline of 74.31%. This highlights the significance of noise detection and filtering in remote sensing, and emphasizes the need for further research in this area.</abstract>
    <parentTitle language="eng">remote sensing</parentTitle>
    <identifier type="doi">10.3390/rs16122080</identifier>
    <identifier type="urn">urn:nbn:de:bvb:863-opus-57532</identifier>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Maximilian Hell</author>
    <author>Melanie Brandmeier</author>
    <collection role="institutes" number="fkv">Fakultät Kunststofftechnik und Vermessung</collection>
    <collection role="oa-colour" number="">Gefördert (Gold)</collection>
    <file>https://opus4.kobv.de/opus4-fhws/files/5753/Hell_Identifying_Plausible_Labels.pdf</file>
  </doc>
  <doc>
    <id>4909</id>
    <completedYear/>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>142</pageFirst>
    <pageLast>149</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume>31</volume>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Transferability of Deep Learning Models &#13;
for Land Use/Land Cover Classification</title>
    <parentTitle language="deu">43. Wissenschaftlich-Technische Jahrestagung der DGPF in München. 22.-23. März 2023 in München -  Publikationen der DGPF</parentTitle>
    <identifier type="doi">10.24407/KXP:1841078182</identifier>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>Maximilian Hell</author>
    <author>Melanie Brandmeier</author>
    <author>Andreas Nüchter</author>
    <collection role="institutes" number="fkv">Fakultät Kunststofftechnik und Vermessung</collection>
  </doc>
</export-example>
