A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Quantifying legibility of indoor spaces using Deep Convolutional Neural Networks: Case studies in train stations
https://orcid.org/0000-0001-9339-8393
https://orcid.org/0000-0002-1703-9863
https://orcid.org/0000-0002-3643-018X
https://orcid.org/0000-0002-9282-6357
Abstract Legibility is the extent to which 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 scalable 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 modelling of legibility for any indoor space, 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% accuracy) overall, there are still discrepancies in model's recognizing confidence among different spaces, reflecting legibility differences. To prove the validity of the pipeline, we deployed a survey on Amazon Mechanical Turk, collecting 4015 samples. Meanwhile, we also conducted an identical survey, collecting 570 samples, on occupants in the station. The human samples showed a similar behavior pattern and mechanism as the DCNN models. Further, we used model results to visually explain legibility differences resulting from architectural program, building age, building style, as well as identify visual clusterings of spaces.
Highlights The paper proposes a DCNN method to measure the legibility of indoor spaces using visual data from two train stations in Paris. It explores the influence of physical attributes on spatial legibility, and compares the computer model with human perception. It quantitatively explains how architectural program, building age, style and visual clustering influence spatial legibility.
Quantifying legibility of indoor spaces using Deep Convolutional Neural Networks: Case studies in train stations
https://orcid.org/0000-0001-9339-8393
https://orcid.org/0000-0002-1703-9863
https://orcid.org/0000-0002-3643-018X
https://orcid.org/0000-0002-9282-6357
Abstract Legibility is the extent to which 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 scalable 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 modelling of legibility for any indoor space, 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% accuracy) overall, there are still discrepancies in model's recognizing confidence among different spaces, reflecting legibility differences. To prove the validity of the pipeline, we deployed a survey on Amazon Mechanical Turk, collecting 4015 samples. Meanwhile, we also conducted an identical survey, collecting 570 samples, on occupants in the station. The human samples showed a similar behavior pattern and mechanism as the DCNN models. Further, we used model results to visually explain legibility differences resulting from architectural program, building age, building style, as well as identify visual clusterings of spaces.
Highlights The paper proposes a DCNN method to measure the legibility of indoor spaces using visual data from two train stations in Paris. It explores the influence of physical attributes on spatial legibility, and compares the computer model with human perception. It quantitatively explains how architectural program, building age, style and visual clustering influence spatial legibility.
Quantifying legibility of indoor spaces using Deep Convolutional Neural Networks: Case studies in train stations
https://orcid.org/0000-0001-9339-8393
https://orcid.org/0000-0002-1703-9863
https://orcid.org/0000-0002-3643-018X
https://orcid.org/0000-0002-9282-6357
Abstract Legibility is the extent to which 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 scalable 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 modelling of legibility for any indoor space, 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% accuracy) overall, there are still discrepancies in model's recognizing confidence among different spaces, reflecting legibility differences. To prove the validity of the pipeline, we deployed a survey on Amazon Mechanical Turk, collecting 4015 samples. Meanwhile, we also conducted an identical survey, collecting 570 samples, on occupants in the station. The human samples showed a similar behavior pattern and mechanism as the DCNN models. Further, we used model results to visually explain legibility differences resulting from architectural program, building age, building style, as well as identify visual clusterings of spaces.
Highlights The paper proposes a DCNN method to measure the legibility of indoor spaces using visual data from two train stations in Paris. It explores the influence of physical attributes on spatial legibility, and compares the computer model with human perception. It quantitatively explains how architectural program, building age, style and visual clustering influence spatial legibility.
Quantifying legibility of indoor spaces using Deep Convolutional Neural Networks: Case studies in train stations
Wang, Zhoutong (author) / Liang, Qianhui (author) / Duarte, Fabio (author) / Zhang, Fan (author) / Charron, Louis (author) / Johnsen, Lenna (author) / Cai, Bill (author) / Ratti, Carlo (author)
Building and Environment ; 160
2019-04-18
Article (Journal)
Electronic Resource
English
Architektūrinių erdvių skaitomumas / ; Legibility of architectural spaces.
| BASE | 2018
Quantifying Salt and Pepper Noise Using Deep Convolutional Neural Network
| Springer Verlag | 2022