Using Satellite Imagery for Good: Detecting Communities in Desert and Mapping Vaccination Activities

TL;DR

This paper presents a deep learning method using Fully Convolutional Networks to analyze satellite imagery for detecting communities and mapping vaccination activities, providing useful statistics for public health efforts.

Contribution

It introduces a novel application of FCNs to satellite imagery for community detection and vaccination activity mapping, enhancing public health monitoring.

Findings

Effective detection of built communities from satellite images.

Correlation between detected communities and vaccination activities.

Provides useful statistical insights for public health planning.

Abstract

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.