Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Exploring the Factors Influencing Street Landscape Quality by Deep Learning Technology
Urbanization has significantly impacted the urban environment. With the city's ongoing expansion, residents' expectations for their living standards rise along with the consideration given to streetscape quality. Deep learning methods offer more precise solutions for researchers. While previous studies extensively explored street landscapes encompassing assessment, perception, and ecology, deep learning has not yet been employed. Thus, we examined street landscape determinants compared to prior work. In this study, we probed factors influencing street landscape quality, and 2) used the Delphi method to identify quality preferences. The results revealed four primary enhancement strategies. Factors were obtained via deep learning as street landscape preferences and evaluated with the Delphi method in five dimensions: architectural facade, street dimensions, street furniture, street greening, and sunlight exposure (totaling 16 factors). These findings can be used to forecast street design quality and suggest ways to enhance urban landscapes, especially on less optimal streets.
Exploring the Factors Influencing Street Landscape Quality by Deep Learning Technology
Urbanization has significantly impacted the urban environment. With the city's ongoing expansion, residents' expectations for their living standards rise along with the consideration given to streetscape quality. Deep learning methods offer more precise solutions for researchers. While previous studies extensively explored street landscapes encompassing assessment, perception, and ecology, deep learning has not yet been employed. Thus, we examined street landscape determinants compared to prior work. In this study, we probed factors influencing street landscape quality, and 2) used the Delphi method to identify quality preferences. The results revealed four primary enhancement strategies. Factors were obtained via deep learning as street landscape preferences and evaluated with the Delphi method in five dimensions: architectural facade, street dimensions, street furniture, street greening, and sunlight exposure (totaling 16 factors). These findings can be used to forecast street design quality and suggest ways to enhance urban landscapes, especially on less optimal streets.
Exploring the Factors Influencing Street Landscape Quality by Deep Learning Technology
Pan, Hao-Zhang (Autor:in) / Ou, Sheng-Jung (Autor:in)
15.12.2023
340779 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Mapping human perception of urban landscape from street-view images:A deep-learning approach
| BASE | 2022
Mapping human perception of urban landscape from street-view images: A deep-learning approach
| DOAJ | 2022
Factors influencing resident’s estimate of traffic-related phenomena in their street
| Online Contents | 2012
Factors influencing quality of concrete
| Engineering Index Backfile | 1938