Accuracy assessment of crop classification in hyperspectral imagery using very deep convolutional neural networks
Accuracy assessment of crop classification in hyperspectral imagery using very deep convolutional neural networks
Mostafa Kiani Shahvandi1
1) M.Sc. graduate in geodesy and remote sensing, University of Tehran, Tehran, Iran
Publication :
2nd. International Congress on science & Engineering - paris(parisconf.com)
Abstract :
We focus on a study in which crops in the hyperspectral imagery are classified using very deep convolutional neural networks. A case study is presented for the 125-band hyperspectral imagery of Stennis Space Center. It is shown that besides other phenomena in the image, the main crop texture of the image is identified and classified. The overall accuracy and coefficient values for this method in this study are, respectively, 98.01 percent and 0.937. The comparison between the accuracy of the classification of this method with those of other conventional methods reveals that it is more accurate in crop classification in hyperspectral imagery.
Keywords :
hyperspectral imagery
classification
very deep convolutional neural networks
accuracy assessment