Scalable Label-efficient Footpath Network Generation Using Remote Sensing Data and Self-supervised Learning

TL;DR

This paper presents a scalable, low-cost pipeline using self-supervised learning and remote sensing data to automatically generate and analyze footpath networks, reducing the need for manual annotation and enabling efficient urban infrastructure management.

Contribution

It introduces a novel pipeline that leverages self-supervised learning for footpath segmentation from remote sensing images, requiring less labeled data and providing accurate GIS-compatible footpath networks.

Findings

High consistency with manually collected GIS layers

Reduced annotation requirements due to self-supervised learning

Pipeline is low-cost and easily extensible

Abstract

Footpath mapping, modeling, and analysis can provide important geospatial insights to many fields of study, including transport, health, environment and urban planning. The availability of robust Geographic Information System (GIS) layers can benefit the management of infrastructure inventories, especially at local government level with urban planners responsible for the deployment and maintenance of such infrastructure. However, many cities still lack real-time information on the location, connectivity, and width of footpaths, and/or employ costly and manual survey means to gather this information. This work designs and implements an automatic pipeline for generating footpath networks based on remote sensing images using machine learning models. The annotation of segmentation tasks, especially labeling remote sensing images with specialized requirements, is very expensive, so we aim to introduce a pipeline requiring less labeled data. Considering supervised methods require large amounts of training data, we use a self-supervised method for feature representation learning to reduce annotation requirements. Then the pre-trained model is used as the encoder of the U-Net for footpath segmentation. Based on the generated masks, the footpath polygons are extracted and converted to footpath networks which can be loaded and visualized by geographic information systems conveniently. Validation results indicate considerable consistency when compared to manually collected GIS layers. The footpath network generation pipeline proposed in this work is low-cost and extensible, and it can be applied where remote sensing images are available. Github: https://github.com/WennyXY/FootpathSeg.