Topological Map Extraction from Overhead Images

TL;DR

PolyMapper is a novel end-to-end model that directly extracts topological maps, including building footprints and road networks, from overhead images, bypassing pixel-wise segmentation and closely matching existing map structures.

Contribution

The paper introduces PolyMapper, a new approach that predicts vector-based topological maps directly from aerial images, including a novel sequentialization method for graph representation.

Findings

Achieves high accuracy in extracting building footprints and road networks.

Performs well on large-scale datasets, closely matching existing map services.

Outperforms state-of-the-art methods in topological map extraction.

Abstract

We propose a new approach, named PolyMapper, to circumvent the conventional pixel-wise segmentation of (aerial) images and predict objects in a vector representation directly. PolyMapper directly extracts the topological map of a city from overhead images as collections of building footprints and road networks. In order to unify the shape representation for different types of objects, we also propose a novel sequentialization method that reformulates a graph structure as closed polygons. Experiments are conducted on both existing and self-collected large-scale datasets of several cities. Our empirical results demonstrate that our end-to-end learnable model is capable of drawing polygons of building footprints and road networks that very closely approximate the structure of existing online map services, in a fully automated manner. Quantitative and qualitative comparison to the state-of-the-art also shows that our approach achieves good levels of performance. To the best of our knowledge, the automatic extraction of large-scale topological maps is a novel contribution in the remote sensing community that we believe will help develop models with more informed geometrical constraints.