Beyond Road Extraction: A Dataset for Map Update using Aerial Images

TL;DR

This paper introduces MUNO21, a new dataset for automatic map updating using aerial images, highlighting the need for improved methods to accurately update existing maps rather than creating new ones from scratch.

Contribution

The paper presents a novel dataset for map update tasks and emphasizes the shift from road extraction to map updating, addressing practical challenges in maintaining accurate maps.

Findings

Existing road extraction methods need significant improvement for map update tasks.

The MUNO21 dataset reveals new research challenges in map updating.

Current methods are insufficient for fully automated map updates.

Abstract

The increasing availability of satellite and aerial imagery has sparked substantial interest in automatically updating street maps by processing aerial images. Until now, the community has largely focused on road extraction, where road networks are inferred from scratch from an aerial image. However, given that relatively high-quality maps exist in most parts of the world, in practice, inference approaches must be applied to update existing maps rather than infer new ones. With recent road extraction methods showing high accuracy, we argue that it is time to transition to the more practical map update task, where an existing map is updated by adding, removing, and shifting roads, without introducing errors in parts of the existing map that remain up-to-date. In this paper, we develop a new dataset called MUNO21 for the map update task, and show that it poses several new and interesting research challenges. We evaluate several state-of-the-art road extraction methods on MUNO21, and find that substantial further improvements in accuracy will be needed to realize automatic map update.