Monitoring road infrastructures from satellite images in Greater Maputo

TL;DR

This paper presents an automatic, object-oriented satellite image analysis pipeline to classify road pavement types, aiding infrastructure monitoring in developing countries.

Contribution

It introduces a novel, accurate, and cost-effective methodology for classifying road surfaces using satellite imagery, applicable to various cities.

Findings

The approach accurately distinguishes paved from unpaved roads.

The methodology is inexpensive and easy to replicate.

It demonstrates effectiveness in the context of Greater Maputo.

Abstract

The information about pavement surface type is rarely available in road network databases of developing countries although it represents a cornerstone of the design of efficient mobility systems. This research develops an automatic classification pipeline for road pavement which makes use of satellite images to recognize road segments as paved or unpaved. The proposed methodology is based on an object-oriented approach, so that each road is classified by looking at the distribution of its pixels in the RGB space. The proposed approach is proven to be accurate, inexpensive, and readily replicable in other cities.