打印

作者

来源

LANDSCAPE AND URBAN PLANNING,Vol.181,P.169-178

语言

英文

关键字

Perceptions; Discrete choice models; Machine learning; Public spaces; LATENT-VARIABLES; CHOICE MODELS; LANDSCAPE; NEIGHBORHOODS; BEHAVIOR; THRESHOLDS; AESTHETICS; INDICATORS; PREFERENCE; IMPACT

作者单位

[Rossetti, Tomas; Lobel, Hans; Rocco, Victor; Hurtubia, Ricardo] Pontificia Univ Catolica Chile, Dept Transport Engn & Logist, Santiago, Chile. [Rossetti, Tomas; Rocco, Victor; Hurtubia, Ricardo] Ctr Sustainable Urban Dev CEDEUS, Santiago, Chile. [Lobel, Hans] Pontificia Univ Catolica Chile, Dept Comp Sci, Santiago, Chile. [Hurtubia, Ricardo] Pontificia Univ Catolica Chile, Sch Architecture, Santiago, Chile. [Rossetti, Tomas] Vicuna Mackenna 4860, Santiago, Chile. Rossetti, T (reprint author), Pontificia Univ Catolica Chile, Dept Transport Engn & Logist, Santiago, Chile.; Rossetti, T (reprint author), Ctr Sustainable Urban Dev CEDEUS, Santiago, Chile.; Rossetti, T (reprint author), Vicuna Mackenna 4860, Santiago, Chile. E-Mail: terosset@uc.cl

标签

智慧城市,城市空间 |

摘要

People's perceptions of the built environment influence the way they use and navigate it. Understanding these perceptions may be useful to inform the design, management and planning process of public spaces. Recently, several studies have used data collected at a massive scale and machine learning methods to quantify these perceptions, showing promising results in terms of predictive performance. Nevertheless, most of these models can be of little help in understanding users' perceptions due to the difficulty associated with identifying the importance of each attribute of landscapes. In this work, we propose a novel approach to quantify perceptions of landscapes through discrete choice models, using semantic segmentations of images of public spaces, generated through machine learning algorithms, as explanatory variables. The proposed models are estimated using the Place Pulse dataset, with over 1.2 million perceptual indicators, and are able to provide useful insights into how users perceive the built environment as a function of its features. The models obtained are used to infer perceptual variables in the city of Santiago, Chile, and show they have a significant correlation with socioeconomic indicators.