Using convolutional neural networks to identify objects from very high-resolution remote sensing imagery

In Journal of Applied Remote Sensing
Volume (Issue): 12 (2)
Peer-reviewed Article

A new method for classifying land cover features in high resolution satellite imagery was developed. The method involves (1) performing image segmentation to delineate homogeneous ground objects in the image, and (2) using a convolutional neural network classifier to extract the land cover of the segments (i.e. whether they represent buildings, cropland, forest, etc.).

Author:
Tengyu
Fu
Lei
Ma
Manchun
Li
Date: