An interpretable machine learning framework for measuring urban perceptions from panoramic street view images
Summary: The proliferation of street view images (SVIs) and the constant advancements in deep learning techniques have enabled urban analysts to extract and evaluate urban perceptions from large-scale urban streetscapes. However, many existing analytical frameworks have been found to lack interpreta...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-03-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004223002092 |
| _version_ | 1797903301759467520 |
|---|---|
| author | Yunzhe Liu Meixu Chen Meihui Wang Jing Huang Fisher Thomas Kazem Rahimi Mohammad Mamouei |
| author_facet | Yunzhe Liu Meixu Chen Meihui Wang Jing Huang Fisher Thomas Kazem Rahimi Mohammad Mamouei |
| author_sort | Yunzhe Liu |
| collection | DOAJ |
| description | Summary: The proliferation of street view images (SVIs) and the constant advancements in deep learning techniques have enabled urban analysts to extract and evaluate urban perceptions from large-scale urban streetscapes. However, many existing analytical frameworks have been found to lack interpretability due to their end-to-end structure and “black-box” nature, thereby limiting their value as a planning support tool. In this context, we propose a five-step machine learning framework for extracting neighborhood-level urban perceptions from panoramic SVIs, specifically emphasizing feature and result interpretability. By utilizing the MIT Place Pulse data, the developed framework can systematically extract six dimensions of urban perceptions from the given panoramas, including perceptions of wealth, boredom, depression, beauty, safety, and liveliness. The practical utility of this framework is demonstrated through its deployment in Inner London, where it was used to visualize urban perceptions at the Output Area (OA) level and to verify against real-world crime rate. |
| first_indexed | 2024-04-10T09:30:43Z |
| format | Article |
| id | doaj.art-347e97bf870c4249bfd997c59796b865 |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-04-10T09:30:43Z |
| publishDate | 2023-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-347e97bf870c4249bfd997c59796b8652023-02-19T04:27:12ZengElsevieriScience2589-00422023-03-01263106132An interpretable machine learning framework for measuring urban perceptions from panoramic street view imagesYunzhe Liu0Meixu Chen1Meihui Wang2Jing Huang3Fisher Thomas4Kazem Rahimi5Mohammad Mamouei6Informal Cities, Oxford Martin School, University of Oxford, Oxford OX1 3BD, UK; MRC Centre for Environment and Health, School of Public Health, Imperial College London, London W2 1PG, UK; Corresponding authorGeographic Data Science Lab, Department of Geography and Planning, University of Liverpool, Liverpool L69 7ZT, UK; Corresponding authorSpaceTimeLab, Department of Civil, Environmental and Geomatic Engineering, University College London, London WC1E 6BT, UKInformal Cities, Oxford Martin School, University of Oxford, Oxford OX1 3BD, UK; Department of Occupational and Environmental Health Sciences, School of Public Health, Peking University, Beijing 100191, ChinaInformal Cities, Oxford Martin School, University of Oxford, Oxford OX1 3BD, UKInformal Cities, Oxford Martin School, University of Oxford, Oxford OX1 3BD, UKInformal Cities, Oxford Martin School, University of Oxford, Oxford OX1 3BD, UKSummary: The proliferation of street view images (SVIs) and the constant advancements in deep learning techniques have enabled urban analysts to extract and evaluate urban perceptions from large-scale urban streetscapes. However, many existing analytical frameworks have been found to lack interpretability due to their end-to-end structure and “black-box” nature, thereby limiting their value as a planning support tool. In this context, we propose a five-step machine learning framework for extracting neighborhood-level urban perceptions from panoramic SVIs, specifically emphasizing feature and result interpretability. By utilizing the MIT Place Pulse data, the developed framework can systematically extract six dimensions of urban perceptions from the given panoramas, including perceptions of wealth, boredom, depression, beauty, safety, and liveliness. The practical utility of this framework is demonstrated through its deployment in Inner London, where it was used to visualize urban perceptions at the Output Area (OA) level and to verify against real-world crime rate.http://www.sciencedirect.com/science/article/pii/S2589004223002092Environmental sciencesArtificial Intelligence |
| spellingShingle | Yunzhe Liu Meixu Chen Meihui Wang Jing Huang Fisher Thomas Kazem Rahimi Mohammad Mamouei An interpretable machine learning framework for measuring urban perceptions from panoramic street view images iScience Environmental sciences Artificial Intelligence |
| title | An interpretable machine learning framework for measuring urban perceptions from panoramic street view images |
| title_full | An interpretable machine learning framework for measuring urban perceptions from panoramic street view images |
| title_fullStr | An interpretable machine learning framework for measuring urban perceptions from panoramic street view images |
| title_full_unstemmed | An interpretable machine learning framework for measuring urban perceptions from panoramic street view images |
| title_short | An interpretable machine learning framework for measuring urban perceptions from panoramic street view images |
| title_sort | interpretable machine learning framework for measuring urban perceptions from panoramic street view images |
| topic | Environmental sciences Artificial Intelligence |
| url | http://www.sciencedirect.com/science/article/pii/S2589004223002092 |
| work_keys_str_mv | AT yunzheliu aninterpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT meixuchen aninterpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT meihuiwang aninterpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT jinghuang aninterpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT fisherthomas aninterpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT kazemrahimi aninterpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT mohammadmamouei aninterpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT yunzheliu interpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT meixuchen interpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT meihuiwang interpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT jinghuang interpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT fisherthomas interpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT kazemrahimi interpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages AT mohammadmamouei interpretablemachinelearningframeworkformeasuringurbanperceptionsfrompanoramicstreetviewimages |