Tree Species Identification Using 3D Spectral Data and 3D Convolutional Neural Network
- Resource Type
- Conference
- Authors
- Polonen, Ilkka; Annala, Leevi; Rahkonen, Samuli; Nevalainen, Olli; Honkavaara, Eija; Tuominen, Sakari; Viljanen, Niko; Hakala, Teemu
- Source
- 2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2018 9th Workshop on. :1-5 Sep, 2018
- Subject
- Geoscience
Signal Processing and Analysis
Vegetation
Three-dimensional displays
Training
Hyperspectral imaging
Convolutional neural networks
Forestry
Tree species
spectral imaging
3D
convolutional neural network
UAV
- Language
- ISSN
- 2158-6276
In this study we apply 3D convolutional neural network (CNN) for tree species identification. Study includes the three most common Finnish tree species. Study uses a relatively large high-resolution spectral data set, which contains also a digital surface model for the trees. Data has been gathered using an unmanned aerial vehicle, a framing hyperspectral imager and a regular RGB camera. Achieved classification results are promising by with overall accuracy of 96.2 % for the classification of the validation data set.