Using Satellite Imagery for Good: Detecting Communities in Desert and Mapping Vaccination Activities
This work addresses mapping and public health monitoring in remote desert areas, but it is incremental as it applies existing deep learning methods to a new domain.
The paper tackles the problem of detecting built structures in low-resolution satellite imagery using a Fully Convolutional Network, achieving efficient detection and correlating these communities with vaccination activities to provide useful statistics.
Deep convolutional neural networks (CNNs) have outperformed existing object recognition and detection algorithms. On the other hand satellite imagery captures scenes that are diverse. This paper describes a deep learning approach that analyzes a geo referenced satellite image and efficiently detects built structures in it. A Fully Convolution Network (FCN) is trained on low resolution Google earth satellite imagery in order to achieve end result. The detected built communities are then correlated with the vaccination activity that has furnished some useful statistics.