Building Floor Number Estimation from Crowdsourced Street-Level Images: Munich Dataset and Baseline Method

TL;DR

This paper introduces a deep learning approach to estimate building floor numbers from crowdsourced street images, supported by a new Munich dataset, achieving high accuracy and enabling enhanced 3D city modeling.

Contribution

It presents a novel end-to-end deep learning framework and releases a large, annotated dataset for building floor estimation from street-level imagery.

Findings

Achieves 81.2% exact accuracy in floor classification.

Predicts within +/-1 floor for 97.9% of buildings.

Provides a scalable method for enriching 3D city models.

Abstract

Accurate information on the number of building floors, or above-ground storeys, is essential for household estimation, utility provision, risk assessment, evacuation planning, and energy modeling. Yet large-scale floor-count data are rarely available in cadastral and 3D city databases. This study proposes an end-to-end deep learning framework that infers floor numbers directly from unrestricted, crowdsourced street-level imagery, avoiding hand-crafted features and generalizing across diverse facade styles. To enable benchmarking, we release the Munich Building Floor Dataset, a public set of over 6800 geo-tagged images collected from Mapillary and targeted field photography, each paired with a verified storey label. On this dataset, the proposed classification-regression network attains 81.2% exact accuracy and predicts 97.9% of buildings within +/-1 floor. The method and dataset together offer a scalable route to enrich 3D city models with vertical information and lay a foundation for future work in urban informatics, remote sensing, and geographic information science. Source code and data will be released under an open license at https://github.com/ya0-sun/Munich-SVI-Floor-Benchmark.