Combined use of airborne laser scanning and hyperspectral imaging for forest inventories

Parkan, Matthew

doi:10.5075/epfl-thesis-9033

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, Central European forests' ecological structures are not as homogeneous as artificial plantations, making forests in Switzerland less easy to systematize through scientific models and satellite's pixel resolutions. In addition, in non-plain regions the sloped terrains constitute a challenge for active radar signals to reliably digitally inscribe multidimensional terrains (Parkan 2019). In that, the case study challenges volumetric remote sensing mobilization, both given its established forestry field and its topographical constitution.…”

Section: Introductionmentioning

confidence: 99%

Pixelating Forests: Remote Sensing Technologies in Forest Monitoring in Switzerland

Dettwiler

2022

Swiss Yearbook of Administrative Sciences

View full text Add to dashboard Cite

The paper explores the quantification and inventory of forests with remote sensing in Switzerland, by leveraging contributions of political geography related to the material and volumetric dimensions of territory. As remote sensing infrastructures are increasingly used to monitor forests and map environmental risks, they contribute to the transformation of forests into smart milieux. Focusing in particular on spatial and aerial technologies, the findings show varying infrastructural competence among cantons. The article further expounds upon the role of remote sensing in the National Forest Inventory as a vector of continuity, scalability and rationalization of forest monitoring. In conclusion, due to their rhizomatic characteristics (Deleuze & Guattari 1987), forests escape remote sensing's attempt at all-encompassing analysis. 2 Dettwiler Swiss Yearbook of Administrative Sciences

show abstract

Section: Introductionmentioning

confidence: 99%

Pixelating Forests: Remote Sensing Technologies in Forest Monitoring in Switzerland

Dettwiler

2022

Swiss Yearbook of Administrative Sciences

View full text Add to dashboard Cite

show abstract

CNN-Based Tree Species Classification Using High Resolution RGB Image Data from Automated UAV Observations

Egli

Höpke²

2020

Remote Sensing

View full text Add to dashboard Cite

Data on the distribution of tree species are often requested by forest managers, inventory agencies, foresters as well as private and municipal forest owners. However, the automated detection of tree species based on passive remote sensing data from aerial surveys is still not sufficiently developed to achieve reliable results independent of the phenological stage, time of day, season, tree vitality and prevailing atmospheric conditions. Here, we introduce a novel tree species classification approach based on high resolution RGB image data gathered during automated UAV flights that overcomes these insufficiencies. For the classification task, a computationally lightweight convolutional neural network (CNN) was designed. We show that with the chosen CNN model architecture, average classification accuracies of 92% can be reached independently of the illumination conditions and the phenological stages of four different tree species. We also show that a minimal ground sampling density of 1.6 cm/px is needed for the classification model to be able to make use of the spatial-structural information in the data. Finally, to demonstrate the applicability of the presented approach to derive spatially explicit tree species information, a gridded product is generated that yields an average classification accuracy of 88%.

show abstract

Combined use of airborne laser scanning and hyperspectral imaging for forest inventories

Cited by 2 publications

References 0 publications

Pixelating Forests: Remote Sensing Technologies in Forest Monitoring in Switzerland

Pixelating Forests: Remote Sensing Technologies in Forest Monitoring in Switzerland

CNN-Based Tree Species Classification Using High Resolution RGB Image Data from Automated UAV Observations

Contact Info

Product

Resources

About