基于街景变化的城市更新模式与感知演变的关联分析——以上海市中央活动区为例

Street View-Based Analysis of the Relationship Between Urban Renewal Patterns and Perception Evolution: Evidence from Shanghai’s Central Activity Zone

摘要

【目的】人本尺度的空间感知逐渐成为评价城市更新绩效的重要维度，但既有研究缺乏对“城市更新-感知变化”之间动态关联的分析。【方法】以上海市中央活动区为案例，基于时序街景图像，运用图神经网络模型结合K-means聚类方法识别5种典型城市景观，通过深度学习模型评估6个维度的视觉感知质量，运用方差分析、卡方检验与净感知变化指数评估不同更新模式的感知效应差异。【结果】上海市中央活动区内视觉感知呈现显著的空间集聚与分异特征；不同景观类型的视觉感知存在显著差异，绿化覆盖的景观道的综合感知最优；“拆建类”更新与美观感和愉悦感的动态变化具有显著关联，“留改类”更新在优质存量空间具有更高的感知边际效益。【结论】不同更新模式对市民感知的影响具有维度差异性。结合案例分析提出的实施差异化更新策略，能为城市精细化更新从存量提质向感知增效转型提供精确的循证决策支撑。

Abstract

[Objective] As global urban renewal advances toward high-quality development, human-scale perceptual landscapes have become central to urban regeneration. However, existing research inadequately addresses how different renewal pathways influence citizens’ perceptual experiences of urban environments. Meanwhile, accompanying the paradigm shift from “demolish-construct-preserve” to a balanced “preserve-renovate-demolish” approach, two typical renewal modes have gradually emerged: First, “demolition-reconstruction renewal,” which achieves spatial transformation through functional replacement and element restructuring, often resulting in structural changes to urban physical environments. Second, “preservation-renovation renewal,” which advances transformation through micro-updates such as building facade improvements and pedestrian environment optimization without altering existing landscape structures. Based on this context, our research objectives include: 1) Mapping the spatial distribution and temporal evolution of multi-dimensional visual perception in urban core functional areas, identifying which urban landscape types are consistently associated with higher or lower perceptual quality. 2) Examining whether differential associations exist between different renewal pathways and perceptual changes. [Methods] This study focuses on Shanghai’s central activity zone. As one of the most structurally complex and rapidly evolving urban renewal areas in China, this zone provides an ideal context for examining diverse renewal pathways. The research constructs a comprehensive analytical framework combining temporal street view imagery analysis with machine learning techniques. Street view data were collected using systematic sampling at 50-meter intervals, capturing images from four cardinal directions at each observation point, with a temporal span from 2017 to 2022. The methodology integrates three core analytical components: First, urban landscape perception assessment utilizes the internationally recognized Place Pulse 2.0 dataset and ResNet50 network architecture to evaluate six perceptual dimensions: safety, vitality, affluence, beauty, interest, and pleasantness. Python-based ZENSVI packages enable automated perception prediction through pre-trained deep learning models. Second, urban physical landscape clustering employs semantic segmentation using GluonCV with DeepLab v3+ models trained on the ADE20K dataset. Based on semantic segmentation results, we constructed 11 core landscape characteristic indicators, including sky openness, green view ratio, traffic orientation index, building aspect ratio, and others. A K-means clustering approach based on the GraphSAGE (Graph Sample and Aggregate) graph neural network identifies five typical urban landscape types, incorporating spatial constraints through multi-scale distance thresholds and exponential distance decay weights. The GraphSAGE generates spatially-aware feature vectors by sampling and aggregating features from node neighborhoods, combining node attributes with neighborhood information. Third, the renewal mode impact analysis employs a two-step analytical framework: ANOVA tests examine perceptual score differences across different landscape clusters, establishing baseline relationships; chi-square tests examine the associations between renewal modes and perceptual change directions, while the net perceptual change index (NPCI) quantifies the net perceptual gain or loss of each renewal pathway. [Results] The spatial distribution analysis reveals that visual perception quality in Shanghai’s central activity zone exhibits significant spatial clustering and differentiation characteristics. High-quality perception areas concentrate in urban core zones including the Hengshan-Fuxing Historic and Cultural Area, Nanjing West Road, People’s Square, and Xintiandi, which serve as mature commercial, cultural, and social centers with refined built environments, rich commercial vitality, and profound historical heritage. Conversely, low-quality perception areas vary by dimension, with “beauty” and “pleasantness” cold spots mainly concentrated in the Old City, North Sichuan Road, and Shanghai Railway Station vicinity, while “interest,” “vitality,” “safety,” and “affluence” cold spots appear significantly in Xuhui Riverside, Qiantan, and Houtan areas. The 2017–2022 perception change analysis demonstrates that urban renewal processes generate complex spatial characteristics, with perception improvement and deterioration areas displaying relatively discrete rather than concentrated distribution patterns, reflecting the point-based, micro-renewal dominant renewal mode. Overall, areas with perception improvements outnumber deteriorated areas, with pleasantness and interest showing particularly notable enhancement. ANOVA and Tukey’s HSD tests reveal statistically significant differences across all six perceptual dimensions among different landscape cluster types. Cluster 2 (green landscaped roads) and cluster 3 (mixed-function community streets) achieve the highest multi-dimensional perception evaluations, while cluster 1 (traffic-oriented arterials) and cluster 4 (open undeveloped spaces) receive the lowest perception scores across all dimensions. Effect sizes indicate that landscape types most significantly influence vitality and beauty perceptions, while their impact on affluence perception remains limited. Dynamic analysis through chi-square testing reveals that among six perceptual dimensions, only beauty and pleasantness changes show statistically significant associations with urban landscape renewal pathways (p<0.001). Net perceptual change index analysis demonstrates that preservation-renovation renewal in high-quality landscape features can achieve perception improvements potentially exceeding demolition-reconstruction renewal benefits. Notably, when other landscape types are updated to “green landscaped roads” and “mixed-function community streets,” they generally generate more positive perceptual changes. [Conclusion] Based on temporal street view analysis from 2017 to 2022, this study demonstrates that the perceptual effects of urban renewal are not solely determined by the intensity of physical intervention. Static perceptual advantages of certain landscape types do not necessarily translate into proportional perceptual gains during renewal processes, revealing clear asymmetries across perceptual dimensions. In dense urban core contexts dominated by incremental renewal, preservation-renovation can generate perceptual benefits comparable to or greater than demolition-reconstruction in high-quality existing environments, while the latter remains more effective for improving low-quality spaces. By linking renewal pathways to dynamic perceptual change, this study provides an evidence-based framework to support differentiated, human-centered urban renewal strategies.

关键词

数字景观 / 存量更新 / 视觉感知 / 时序街景图像 / 图神经网络 / 中央活动区

Key words

digital landscape / stock-based renewal / visual perception / time-series street view imagery / graph neural network / central activity zone

参考文献

[1] 郑时龄 . 关于上海城市更新的思考[J]. 建筑实践，2019（7）： 8-11.

[2] Zheng S L . Reflections on Urban Renewal of Shanghai[J]. Architectural Practice，2019（7）： 8-11.

[3] 宋伟轩， 陈浩， 崔璨， 等 . 建立可持续城市更新模式的理论、方法与路径思考[J]. 自然资源学报，2025， 40（1）： 20-38.

[4] Song W X， Chen H， Cui C， et al. Theoretical, Methodological, and Implementation Considerations for Establishing a Sustainable Urban Renewal Model[J]. Journal of Natural Resources，2025， 40（1）： 20-38.

[5] Bennett M M， Smith L C . Advances in Using Multitemporal Night-Time Lights Satellite Imagery to Detect, Estimate, and Monitor Socioeconomic Dynamics[J]. Remote Sensing of Environment， 2017， 192： 176-197.

[6] Zhou D J， Xu S， Sun C Z， et al. Dynamic and Drivers of Spatial Change in Rapid Urban Renewal Within Beijing Inner City[J]. Habitat International， 2021， 111： 102349.

[7] Kim J H， Ki D， Osutei N， et al. Beyond Visual Inspection：Capturing Neighborhood Dynamics with Historical Google Street View and Deep Learning-Based Semantic Segmentation[J]. Journal of Geographical Systems， 2024， 26（4）： 541-564.

[8] Tang J X， Long Y . Measuring Visual Quality of Street Space and Its Temporal Variation：Methodology and Its Application in the Hutong Area in Beijing[J]. Landscape and Urban Planning， 2019， 191： 103436.

[9] 邵钰涵， 殷雨婷， 薛贞颖 . 基于街景大数据的北京、上海街景舒适度评价及比较[J]. 风景园林，2021， 28（1）： 53-59.

[10] Shao Y H， Yin Y T， Xue Z Y . Evaluation and Comparison of Streetscape Comfort in Beijing and Shanghai Based on a Big Data Approach with Street Images[J]. Landscape Architecture，2021， 28（1）： 53-59.

[11] 胡一可， 张天霖， 王磊， 等 . 景观服务视角下城市街区感知测度及空间分布特征[J]. 风景园林，2022， 29（10）： 45-52.

[12] Hu Y K， Zhang T L， Wang L， et al. Measurement and Spatial Distribution of Perception in Urban Blocks from the Perspective of Landscape Service[J]. Landscape Architecture，2022， 29（10）： 45-52.

[13] 黄路， 冲拓弥 . 利用众包视觉感知方法促进公众视角融入城市设计决策[J]. 风景园林，2025， 32（5）： 22-28.

[14] Huang L， Oki T . Promoting the Integration of Public Perspective into Urban Design Decision-Making Based on Crowdsourced Visual Perception Method[J]. Landscape Architecture，2025， 32（5）： 22-28.

[15] 陈崇贤， 刘欣宜， 邱添， 等 . 夜跑友好视角下城市街道环境视觉感知评价[J]. 风景园林，2024， 31（4）： 36-43.

[16] Chen C X， Liu X Y， Qiu T， et al. Evaluation on Visual Perception of Urban Street Environment from the Perspective of Being Friendly to Nighttime Running[J]. Landscape Architecture，2024， 31（4）： 36-43.

[17] Wang Z Y， Ito K， Biljecki F . Assessing the Equity and Evolution of Urban Visual Perceptual Quality with Time Series Street View Imagery[J]. Cities， 2024， 145： 104704.

[18] Liu Y J， Wang Z Y， Ren S Y， et al. Physical Urban Change and Its Socio-environmental Impact：Insights from Street View Imagery[J]. Computers, Environment and Urban Systems， 2025， 119： 102284.

[19] Liang X C，Zhao T H，Biljecki F. Revealing Spatio-temporal Evolution of Urban Visual Environments with Street View Imagery[J]. Landscape and Urban Planning，2023，237：104802.

[20] 白钊成， 齐君， 唐雪琼 . 基于图像识别的街道环境绿量与运动偏好路径的关系[J]. 西南大学学报（自然科学版），2022， 44（8）： 185-194.

[21] Bai Z C， Qi J， Tang X Q . Study on the Relationship Between Street Environmental Green Volume and Preference of Exercise Route Based on Image Recognition[J]. Journal of Southwest University（Natural Science），2022， 44（8）： 185-194.

[22] Rossetti T， Lobel H， Rocco V， et al. Explaining Subjective Perceptions of Public Spaces as a Function of the Built Environment：A Massive Data Approach[J]. Landscape and Urban Planning， 2019， 181： 169-178.

[23] Ito K， Zhu Y H， Abdelrahman M， et al. ZenSVI：An Open-Source Software for the Integrated Acquisition, Processing and Analysis of Street View Imagery Towards Scalable Urban Science[J]. Computers, Environment and Urban Systems， 2025， 119： 102283.

[24] Cohen J . Statistical Power Analysis for the Behavioral Sciences[M]. 2nd ed. New York：Routledge， 1988.

[25] Bai Z C， Huang S Y， Wang L， et al. Refined Understanding of Street Vitality：Comparing the Spatial Effects of Pedestrian Vitality and Cycling Vitality and the Spatial Heterogeneity of Factors[J]. International Journal of Digital Earth， 2025， 18（1）： 2501769.

[26] Chen L， Lu Y， Ye Y， et al. Examining the Association Between the Built Environment and Pedestrian Volume Using Street View Images[J]. Cities， 2022， 127： 103734.

[27] 刘江， 华怡冰， 郭华贵 . 基于多源数据的城市慢行系统声景品质评价与预测[J]. 中国园林，2025， 41（6）： 56-63.

[28] Liu J， Hua Y B， Guo H G . Evaluation and Prediction of Soundscape Quality in Urban Pedestrian Street System Based on Multi-source Data[J]. Chinese Landscape Architecture，2025， 41（6）： 56-63.

[29] Biljecki F， Ito K . Street View Imagery in Urban Analytics and GIS：A Review[J]. Landscape and Urban Planning， 2021， 215： 104217.

[30] Liu Z Y， Ma X Y， Hu L H， et al. Information in Streetscapes：Research on Visual Perception Information Quantity of Street Space Based on Information Entropy and Machine Learning[J]. ISPRS International Journal of Geo-Information， 2022， 11（12）： 628.

[31] Zhai Y J， Gong R Y， Huo J Z， et al. Building Façade Color Distribution, Color Harmony and Diversity in Relation to Street Functions：Using Street View Images and Deep Learning[J]. ISPRS International Journal of Geo-Information， 2023， 12（6）： 224.

[32] Cheshmehzangi A， Chen W X， Mangi E， et al. Practical Challenges of Urban Regeneration in China[J]. Frontiers in Sustainable Cities， 2023， 5： 913500.

[33] Gehl J. Life Between Buildings：Using Public Space[M]. Princeton： Princeton University Press， 2012.

[34] 段一行 . 创新驱动城市自主更新的新模式[J]. 城市规划，2022， 46（2）： 100-107.

[35] Duan Y X . New Mode of Urban Self-regeneration in Innovation-Driven Cities[J]. City Planning Review，2022， 46（2）： 100-107.

[36] 曹越皓， 杨培峰， 李敏敏， 等 . 基于视觉融合模型的城市景观精细化感知方法研究：以重庆市主城区为例[J]. 中国园林，2025， 41（3）： 76-83.

[37] Cao Y H， Yang P F， Li M M， et al. Research on Fine-Grained Perception Method of Urban Landscape Based on Visual Fusion Model：A Case Study of Chongqing’s Main Urban Area[J]. Chinese Landscape Architecture，2025， 41（3）： 76-83.

[38] Ahmad Nia H， Atun R A， Rahbarianyazd R . Perception Based Method for Measuring the Aesthetic Quality of the Urban Environment[J]. Open House International， 2017， 42（2）： 11-19.

[39] 金方廷 . 网红街区的缙绅化：媒介时代城市景观的形塑与生产[J]. 中国图书评论，2024（ 8）： 8-20.

[40] Jin F T . The Gentry of Online Celebrity Block：The Shaping and Production of Urban Landscape in the Media Age[J]. China Book Review，2024（ 8）： 8-20.

[41] Rui J， Cai C F . Plausible or Misleading? Evaluating the Adaption of the Place Pulse 2.0 Dataset for Predicting Subjective Perception in Chinese Urban Landscapes[J]. Habitat International， 2025， 157： 103333.

基金资助

国家自然科学基金“基于生态系统服务权衡与协同的市级生态空间多目标优化研究”(52178050)