Tree species annotations for deep learning

<p>The dataset contains &gt;10,000 labeled tree species and the model weights&nbsp;for tree species detection. Format: Image tiles (.twf) with a 256 &times; 256 pixel size stride in the PASCAL VOC format. The labels are saved as a .xml.&nbsp;The RGB orthophotos are open source and can be accessed at: https://www.swisstopo.admin.ch/de/geodata/images/ortho/swissimage10.html.</p> <p>The methodology used to create the data is presented in Beloiu et al. 2023,&nbsp;Individual tree-crown detection and species identification in heterogeneous forests using aerial RGB imagery and deep learning, Remote sensing.</p> <p>Table 1. Tree species and the number of labels available for them.</p> <table align="center"> <tbody> <tr> <td> <p><strong>Scientific name</strong></p> </td> <td> <p><strong>Common name</strong></p> </td> <td> <p><strong>Class</strong></p> </td> <td> <p><strong>Total</strong></p> </td> </tr> <tr> <td> <p><em>Picea abies</em></p> </td> <td> <p>Norway spruce</p> </td> <td> <p>10</p> </td> <td> <p><strong>3459</strong></p> </td> </tr> <tr> <td> <p><em>Abies alba</em></p> </td> <td> <p>Silver fir</p> </td> <td> <p>11</p> </td> <td> <p><strong>2375</strong></p> </td> </tr> <tr> <td> <p><em>Pinus sylvestris</em></p> </td> <td> <p>Scots pine</p> </td> <td> <p>15</p> </td> <td> <p><strong>599</strong></p> </td> </tr> <tr> <td> <p><em>Fagus sylvatica</em></p> </td> <td> <p>European beech</p> </td> <td> <p>50</p> </td> <td> <p><strong>4181</strong></p> </td> </tr> <tr> <td> <p><strong><em>Total</em></strong></p> </td> <td> <p>&nbsp;</p> </td> <td> <p>&nbsp;</p> </td> <td> <p><strong><em>10614</em></strong></p> </td> </tr> </tbody> </table>