Versailles-FP dataset: Wall Detection in Ancient

TL;DR

This paper introduces the Versailles-FP dataset with groundtruth wall masks for 17th-18th century palace floor plans, and proposes a U-Net based method for accurate wall detection, validated on modern datasets.

Contribution

The paper presents a new historical dataset for wall detection in ancient floor plans and a U-Net based approach that outperforms previous methods.

Findings

State-of-the-art wall detection accuracy achieved

Automatic wall mask generation validated on modern datasets

U-Net framework surpasses fully connected network approaches

Abstract

Access to historical monuments' floor plans over a time period is necessary to understand the architectural evolution and history. Such knowledge bases also helps to rebuild the history by establishing connection between different event, person and facts which are once part of the buildings. Since the two-dimensional plans do not capture the entire space, 3D modeling sheds new light on the reading of these unique archives and thus opens up great perspectives for understanding the ancient states of the monument. Since the first step in the building's or monument's 3D model is the wall detection in the floor plan, we introduce in this paper the new and unique Versailles FP dataset of wall groundtruthed images of the Versailles Palace dated between 17th and 18th century. The dataset's wall masks are generated using an automatic approach based on multi directional steerable filters. The generated wall masks are then validated and corrected manually. We validate our approach of wall mask generation in state-of-the-art modern datasets. Finally we propose a U net based convolutional framework for wall detection. Our method achieves state of the art result surpassing fully connected network based approach.