Figure 2 - uploaded by Teja Kattenborn
Content may be subject to copyright.
Source publication
Accurate information on the spatial distribution of plant species and communities is in high demand for various fields of application, such as nature conservation, forestry, and agriculture. A series of studies has shown that Convolutional Neural Networks (CNNs) accurately predict plant species and communities in high-resolution remote sensing data...
Contexts in source publication
Context 1
... considered for each case study, i.e. open surface water for the case study F. japonica and barren soil for the case study P. afra. For both cases, 4,184 and 910 photographs, respectively, were downloaded from the web using the Google Search API and different queries (e.g., river, river bed, open water and soil, barren, ground, dry respectively). Fig. 2 shows an example of downloaded images for the three classes for both case ...
Context 2
... plant photographs have very heterogeneous acquisition settings and their perspective often greatly differs from the typical bird-view perspective of remote sensing data (Fig. 2). To test if the accuracy of the species identification can be increased by pre-selecting photographs with a similar perspective to the remote sensing data, we filtered training photographs based on their acquisition angle and distance from the target plants (Fig. 3). As the iNaturalist photographs do not readily inform acquisition ...
Context 3
... both cases, 4,184 and 910 photographs, respectively, were downloaded from the web using the Google Search API and different queries (e.g., river, river bed, open water and soil, barren, ground, dry respectively). Figure 2 shows an example of downloaded images for the three classes for both case studies. ...
Context 4
... plant photographs have very heterogeneous acquisition settings and their perspective often greatly differs from the typical bird-view perspective of remote sensing data ( Fig. 2). To test if the accuracy of the species identification can be increased by pre-selecting photographs with a similar perspective to the remote sensing data, we filtered training photographs based on their acquisition angle and distance from the target plants (Fig. 3). As the iNaturalist photographs do not readily inform acquisition ...
Context 5
... was tested with two case studies where the target species have quite different morphological characteristics compared to the surrounding species. For instance, P. afra has quite roundish leaves combined with a mostly star-shaped branching structure, while F. japonica differs from the surrounding vegetation through its large heart-shaped leaves ( Fig. 1, 2). However, the success of such an approach not only depends on contrasting morphological properties between the target and the surrounding species but also if such properties are visible in both the citizen science photographs and the orthoimagery. Therefore, we tested the approach with UAV imagery with a ground sampling distance in ...
