| Vegetation mapping of Sentinel-1 and 2 satellite images using Convolutional Neural Network and Random Forest with aid of Dual-Polarized and Optical vegetation indexes |
| Paper ID : 1204-SMPR |
| Authors: |
|
Nafiseh Ghasemian Sorboni1, Parham Pahlavani *2, Behnaz Bigdeli3 1School of Surveying and Geospatial Engineering, College of Eng., University of Tehran, Tehran, Iran 2University of Tehran 3School of Civil Eng., Shahrood University of Technology, Shahrood, Iran. |
| Abstract: |
| Vegetation mapping is one of the most important challenges of remote sensing society in forestry applications. The Sentinel-1 dataset has the potential of vegetation mapping but because of its limited number of polarizations, full polarized vegetation indexes are not accessible. The Sentinel-2 dataset is more suitable for vegetation mapping because a wide variety of vegetation indexes can be extracted from them. Handling this large number of vegetation indexes needs a strong feature extractor. Convolutional Neural Networks extract relevant features through their deep layers and throw out disturbances from small to large scales. Hence, they can be far useful for classifying remote sensing data when the number of input bands is considerable. After pre-processing Sentinel-1 and 2 datasets and extracting the dual polarized and optical vegetation indexes, we fed the sentinel-1 vegetation indexes alongside the VV and VH sigma Nought bands to a Random Forest classifier (RF). Also, 13 spectral features of the Sentinel-2 and the extracted indexes like Green Ratio (GR), Vegetation index based on Red Edge (VIRE) and Normalized Near Infrared (NNIR) were imported to a 1D CNN. The classification result of Sentinel-1 data showed that Dual Polarized Soil Vegetation Index (DPSVI) is a good indicator for discriminating vegetation pixels. Also, the experiment on the Sentinel-2 dataset using CNN resulted in True Positive Rate (TPR) and False Positive Rate of 0.839 and 0.034 respectively. |
| Keywords: |
| Vegetation mapping, Sentinel-1, Sentinel-2, Random Forest, Convolutional Neural Network |
| Status : Conditional Accept (Poster) |
