基于复杂网络的城市肌理自动识别方法研究* ——以上海中环内地区为例
Research on Automatic Recognition Method of Urban Texture Based on Complex Network: A Case Study within Shanghai Middle Ring Road
冯韵洁
同济大学建筑与城市规划学院 硕士研究生
徐怡怡
同济大学建筑与城市规划学院 硕士研究生
徐子寒
同济大学建筑与城市规划学院 硕士研究生
刘乐峰
同济大学建筑与城市规划学院 硕士研究生
沈 尧（通信作者）
同济大学建筑与城市规划学院 同济大学中英联合城市科学实验室 副教授，博士生导师，eshenyao@tongji.edu.cn
摘要: 城市肌理在城市规划和设计中至关重要，然而既有研究多聚焦于形态类型学，缺乏对综合形态指标、多尺度结构及其 社会经济内涵的系统考量。基于复杂网络视角，提出一种多维度、数据驱动的城市肌理自动识别方法：以建筑邻近关系 构建空间加权网络，结合多分辨率社区发现算法识别多尺度肌理片区结构，测度关键尺度下的片区肌理特征，并通过 递归聚类形成城市肌理族谱。以上海中环地区为例，实证结果显示该方法能有效揭示城市肌理的多尺度结构，精细化 测度片区特征，提炼出2大类8种肌理类型，并揭示其对房价的显著影响。不仅改进了城市肌理自动识别的技术路径，也 为深入理解城市肌理的自组织规律提供思路，以期为城市更新和历史文脉保护提供科学工具。
Abstract: Urban texture is vital in urban planning and design, yet previous studies have mainly focused on morphological typologies, with limited attention to integrated indicators, multi-scale structures, and socioeconomic implications. This study proposes a multidimensional, data-driven approach to automatic urban texture recognition from a complex network perspective. A weighted building adjacency network, incorporating spatial proximity and morphological divergence, has been constructed, and multi-resolution community detection has been applied to identify texture patch structures across scales. Key texture characteristics have been measured at critical scales, followed by recursive clustering to generate a genealogical map of urban texture. Using Shanghai's Middle Ring area as a case study, the results demonstrate that this method effectively reveals multiscale hierarchical structures, enables refined measurement of texture characteristics, identifies two major categories and eight basic texture types, and uncovers significant socioeconomic implications, particularly the impacts of urban texture on housing prices. This research advances technical methods for automated texture identification, deepens understanding of its selforganizing principles, and provides practical tools for urban renewal and historical context preservation.
关键词：城市肌理；复杂网络；多尺度；自动识别；建筑足迹
Keyword: urban texture; complex network; multi-scale; automatic recognition; building footprints
中图分类号：TU984
文献标识码: A
LYNCH K. Good city form[M]. Cambridge, Massachusetts: MIT Press, 1984.
童明. 城市肌理如何激发城市活力[J]. 城市规划
学刊，2014（3）：85-96.
TONG Ming. How urban fabric can help sustain
the vitality of cities[J]. Urban Planning Forum,
2014(3): 85-96.
贾新锋，黄晶. 基于局部规则概念的城市肌理再
研究[J]. 华中建筑，2011，29（12）：137-139.
JIA Xinfeng, HUANG Jing. New research of urban
texture based on local rule[J]. Huazhong Architecture, 2011, 29(12): 137-139.
江泓，张四维. 生产、复制与特色消亡——“空
间生产”视角下的城市特色危机[J]. 城市规划
学刊，2009（4）：40-45.
JIANG Hong, ZHANG Siwei. Production, duplication, and characteristics extinction: an analysis on
the crisis of city's characteristic with the theory of
"production of space"[J]. Urban Planning Forum,
2009(4): 40-45.
杨保军，朱子瑜，蒋朝晖，等. 城市特色空间刍议
[J]. 城市规划，2013，37（3）：11-16.
YANG Baojun, ZHU Ziyu, JIANG Chaohui, et al.
Reflections on featured urban space[J]. City Planning
Review, 2013, 37(3): 11-16.
邓浩，宋峰，蔡海英. 城市肌理与可步行性——
城市步行空间基本特征的形态学解读[J]. 建筑
学报，2013（6）：8-13.
DENG Hao, SONG Feng, CAI Haiying. Urban
tissue and walkability morphological analysis on
the essential characteristics of urban walkable
space[J]. Architectural Journal, 2013(6): 8-13.
CANIGGIA G, MAFFEI G L. Architectural composition and building typology: interpreting basic
building[M]. Firenze: Alinea Editrice, 2001.
刘铨，丁沃沃. 城市肌理形态研究中的图示化方
法及其意义[J]. 建筑师，2012（1）：5-12.
LIU Quan, DING Wowo. Diagrammatic methods
and the significance in the study of urban fabric[J].
The Architect, 2012(1): 5-12.
何依，邓巍. 历史街区建筑肌理的原型与类型研
究[J]. 城市规划，2014，38（8）：57-62.
HE Yi, DENG Wei. Research on the prototype and
types of architectural texture in historic district[J].
City Planning Review, 2014, 38(8): 57-62.
房艳刚，刘继生. 基于复杂系统理论的城市肌理
组织探索[J]. 城市规划，2008（10）：32-37.
FANG Yan'gang, LIU Jisheng. Urban fabric
organization based on complex systems theory[J].
City Planning Review, 2008(10): 32-37.
BATTY M. Building a science of cities[J]. Cities,
2012(29): 9-16.
沈尧，徐怡怡，刘乐峰. 网络渗流视角下的城市
肌理识别与测度研究[J]. 城市规划学刊，2021
（5）：9.
SHEN Yao, XU Yiyi, LIU Lefeng. Urban texture
analysis from the perspective of network percolation[J]. Urban Planning Forum, 2021(5): 9.
MARZOT N. The study of urban form in Italy[J].
Urban Morphology, 2002(2): 59-73.
HILLIER B, HANSON J. The social logic of
space[M]. Cambridge: Cambridge University
Press, 1984.
陈彦光. 分形城市系统：标度•对称•空间复杂性
[M]. 北京：科学出版社，2008.
CHEN Yanguang. Fractal urban systems: scaling,
symmetry, and spatial complexity[M]. Beijing:
Science Press, 2008.
董春方. 密度与城市形态[J]. 建筑学报，2012（7）：
22-27.
DONG Chunfang. Density and urban form[J].
Architectural Journal, 2012(7): 22-27.
HAUSLEITNER B. Tracing scopes of action:
design principles to approach the complexity of the
urban block (Tesis de maestría)[R]. 2010.
BOCHER E, PETIT G, BERNARD J, et al. A
geoprocessing framework to compute urban indicators: the MApUCE tools chain[J]. Urban Climate,
2018, 24: 153-174.
RATTI C, RICHENS P. Raster analysis of urban
form[J]. Environment and Planning B: Planning
and Design, 2004, 31: 297-309.
姚佳伟，黄辰宇，刘鹏坤，等. 基于人工智能的城
市肌理识别和评价研究[J]. 住宅科技，2019，
39（11）：9-14.
YAO Jiawei, HUANG Chenyu, LIU Pengkun, et
al. Urban texture recognition and evaluation based
on artificial intelligence[J]. Housing Science,
2019, 39(11): 9-14.
HILLIER B. Space is the machine: a configurational
theory of architecture[M]. Cambridge: Cambridge
University Press, 1996.
BATTY M. Exploring isovist fields: space and
shape in architectural and urban morphology[J].
Environment and Planning B, 2001, 28(1): 123-150.
GEHL J. Life between buildings: using public
space[M]. New York: Van Nostrand Reinhold, 1987.
ZHANG X, AI T, STOTER J, et al. Building
pattern recognition in topographic data: examples
on collinear and curvilinear alignments[J]. Geoinformatica, 2013, 17(1): 1-33.
DU S, SHU M, FENG C. Representation and
discovery of building patterns: a three-level relational approach[J]. International Journal of Geographical Information Science, 2016, 30(6): 1161-
1186.
YAN X, AI T, YANG M, et al. A graph convolutional neural network for classification of building
patterns using spatial vector data[J]. ISPRS Journal
of Photogrammetry and Remote Sensing, 2019,
150: 259-273.
DENG M, TANG J, LIU Q, et al. Recognizing
building groups for generalization: a comparative
study[J]. Cartography and Geographic Information
Science, 2018, 45(3): 187-204.
BASARANER M, CETINKAYA S. Performance
of shape indices and classification schemes for
characterising perceptual shape complexity of
building footprints in GIS[J]. International Journal
of Geographical Information Science, 2017,
31(10): 1952-1977.
DU S, LUO L, CAO K, et al. Extracting building
patterns with multilevel graph partition and building
grouping[J]. ISPRS Journal of Photogrammetry &
Remote Sensing, 2016, 122(12): 81-96.
BURGHARDT D, STEINIGER S. Usage of
principal component analysis in the process of
automated generalisation[C]//Proceedings of the
22th International Cartographic Conference (ICC).
2005.
NEWMAN M E. Modularity and community structure in networks[J]. Proceedings of the National
Academy of Sciences, 2006, 103(23): 8577-8582.
LAW S, KARIMI K, PENN A, et al. Measuring the
influence of spatial configuration on the housing
market in metropolitan London[C]//Proceedings of
the Ninth International Space Syntax Symposium.
2013.
LAW S, META B P, SHEN Y, et al. Identifying
street-character-weighted local area using locally
weighted community detection methods: the case
study of London and Amsterdam[C]//Proceedings
of the 12th Space Syntax Symposium. 2019.
