Super-resolution land cover mapping based on deep learning and level set method
Watsana Bupphawat, Teerasit Kasetkasem, Itsuo Kumazawa, Preesan Rakwatin, Thitiporn Chanwimaluang · 2017
In this paper, we proposed an approach for super-resolution land cover mapping on remote sensing images based on the deep learning technique, namely Convolutional Neural Network (CNN) by combining with the level set method (LSM). Here, the CNN is used to find the probabilities that a subpixel belonging to a land cover class, and the LSM is employed to fine tune the boundaries among land cover classes. The QUICKBIBD satellite image data cover a part of Kasetsart University was used for evaluation. Experimental result showed that the proposed method has achieved superior accuracy than both Hopfield and Pixel-Swapping methods.