Quantifying Legibility of Indoor Spaces Using Deep Convolutional Neural Networks: Case Studies in Train Stations

TL;DR

This paper presents a novel deep learning approach to quantitatively measure indoor space legibility, validated through human surveys and applied to various architectural contexts, improving understanding of spatial recognition.

Contribution

The study introduces an end-to-end DCNN-based pipeline for quantifying indoor space legibility, bridging the gap between subjective surveys and objective measurement.

Findings

DCNN achieved 98% top-1 accuracy in modeling legibility

Human survey results aligned with model predictions

Visual explanations linked legibility to architectural features

Abstract

Legibility is the extent to which a space can be easily recognized. Evaluating legibility is particularly desirable in indoor spaces, since it has a large impact on human behavior and the efficiency of space utilization. However, indoor space legibility has only been studied through survey and trivial simulations and lacks reliable quantitative measurement. We utilized a Deep Convolutional Neural Network (DCNN), which is structurally similar to a human perception system, to model legibility in indoor spaces. To implement the modeling of legibility for any indoor spaces, we designed an end-to-end processing pipeline from indoor data retrieving to model training to spatial legibility analysis. Although the model performed very well (98% top-1 accuracy) overall, there are still discrepancies in accuracy among different spaces, reflecting legibility differences. To prove the validity of the pipeline, we deployed a survey on Amazon Mechanical Turk, collecting 4,015 samples. The human samples showed a similar behavior pattern and mechanism as the DCNN models. Further, we used model results to visually explain legibility in different architectural programs, building age, building style, visual clusterings of spaces and visual explanations for building age and architectural functions.