Road Network Fusion for Incremental Map Updates

TL;DR

This paper introduces extit{MapFuse}, a system that combines human-annotated maps with automatically inferred maps to enable rapid and accurate map updates, including road creation and closure detection.

Contribution

The paper presents extit{MapFuse}, a novel fusion system that improves map accuracy and update speed by integrating human-annotated and automatic maps, especially for road closures.

Findings

extit{MapFuse} effectively detects road closures.

Fusion reduces mapping errors caused by automatic inference.

System enables faster map updates with minimal manual effort.

Abstract

In the recent years a number of novel, automatic map-inference techniques have been proposed, which derive road-network from a cohort of GPS traces collected by a fleet of vehicles. In spite of considerable attention, these maps are imperfect in many ways: they create an abundance of spurious connections, have poor coverage, and are visually confusing. Hence, commercial and crowd-sourced mapping services heavily use human annotation to minimize the mapping errors. Consequently, their response to changes in the road network is inevitably slow. In this paper we describe \mapfuse, a system which fuses a human-annotated map (e.g., OpenStreetMap) with any automatically inferred map, thus effectively enabling quick map updates. In addition to new road creation, we study in depth road closure, which have not been examined in the past. By leveraging solid, human-annotated maps with minor corrections, we derive maps which minimize the trajectory matching errors due to both road network change and imperfect map inference of fully-automatic approaches.