肖通;李德平;万义良;金瑞;王柱;高伟;费玉雯;
XIAO Tong;LI De-ping;WAN Yi-liang;JIN Rui;WANG Zhu;GAO Wei;FEI Yu-wen;School of Geograhic Sciences,Hunan Normal University/Hunan Key Laboratory of Geospatial Big Data Mining and Application;School of Architecture,Hunan University;Hunan Architectural Design Institute Limited Company;

• 1:湖南师范大学地理科学学院/地理空间大数据挖掘与应用湖南省重点实验室
• 2:湖南大学建筑学院
• 3:湖南省建筑设计院集团有限公司

摘要(Abstract)：

城市化进程加快导致街道安全性问题突出,已有研究利用城市视觉要素刻画街道安全感空间分布,忽略了街道真实安全性与安全感间的差异。该文利用街景影像和手机信令数据,结合K-means聚类算法与笛卡尔积运算模型减少"安全感知差异",以长沙市主城区为研究案例,得到白天、夜晚及总体城市街道安全性分布:1)长沙市主城区安全感指数随圈层数增加呈波动递减趋势,主要原因是建筑视觉要素占比下降较快以及天空视觉要素占比逐步上升;2)长沙市主城区呈双圈层结构,白天高安全性、夜晚低安全性以及总体安全性最低的区域主要分布在主城区中心,具有明显的聚集现象。该研究通过对城市街道安全性和低安全性街道的分析提出街道优化建议,为城市规划提供参考。
The accelerated urbanization process leads to more prominent street safety problems, and it is important to explore the spatial distribution of urban street safety for sustainable urban development.Previous studies have used urban visual elements to portray the spatial distribution of street safety, but ignored the difference between the real safety and the sense of street safety.In this paper, street view images and mobile signaling data are used to reduce the "perceptual difference" by combining K-means and Cartesian product models.Finally, we obtain the safety distribution of urban streets in the main urban area of Changsha. It is found as follows.1) In the main urban area of Changsha, the overall trend of safety perception index in the circle distribution is decreasing, and the main reason for the decreasing trend is that the proportion of visual elements in buildings is decreasing too fast and the proportion of visual elements in the sky is gradually increasing. 2) The urban safety perception in the main urban area of Changsha presents a double circle structure, and the areas with high safety during daytime, low safety at night and the lowest overall safety are mainly distributed in the main center of the main urban area of Changsha, with an obvious aggregation phenomenon. Some suggestions are put forward for street optimization through the analysis of urban street safety, which provide important references for urban planning.

关键词(KeyWords)： 街道安全性;街景;手机信令数据;语义分割;安全感
street safety;street view;mobile signaling data;semantic segmentation;safety perception

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41701465);; 教育部人文社会科学青年基金项目(20YJC790055、21YJCZH151);; 湖南省自然科学基金青年基金项目(2020JJ5051);; 长沙市杰出创新青年培养计划项目(kq2009017)

作者(Authors): 肖通;李德平;万义良;金瑞;王柱;高伟;费玉雯;
XIAO Tong;LI De-ping;WAN Yi-liang;JIN Rui;WANG Zhu;GAO Wei;FEI Yu-wen;School of Geograhic Sciences,Hunan Normal University/Hunan Key Laboratory of Geospatial Big Data Mining and Application;School of Architecture,Hunan University;Hunan Architectural Design Institute Limited Company;

参考文献(References)：

• [1] 吴鹏森.改革开放以来的中国城市化与犯罪变化——基于一种比较的视角[J].江苏行政学院学报，2012(6):51-58.
• [2] 周丽.基于安全性分析的城市生活性街道景观研究[D].南京：南京工业大学，2016.
• [3] 陈月.城市道路景观的安全性设计研究[D].南昌：江西农业大学，2015.
• [4] 李薇.犯罪预防视角下的哈尔滨住宅小区安全性研究[D].哈尔滨：东北林业大学，2011.
• [5] 刘霞.生活性街道物质环境要素对街道安全性的影响研究—以武汉市为例[D].武汉：华中科技大学，2020.
• [6] 张延吉，秦波，朱春武.北京城市建成环境对犯罪行为和居住安全感的影响[J].地理学报，2019,74(2):238-252.
• [7] 刘成.住区物质环境的犯罪预防与安全[D].武汉：华中科技大学，2004.
• [8] 张丽英，裴韬，陈宜金，等.基于街景图像的城市环境评价研究综述[J].地球信息科学学报，2019,21(1):45-58.
• [9] WILSON J Q,KELLING G L.Broken windows[J].Atlantic Monthly,1982,249(3):29-38.
• [10] REA M,BULLOUGH J,BRONS J.Spectral considerations for outdoor lighting:Designing for perceived scene brightness[J].Lighting Research & Technology,2015,47(8):909-919.
• [11] 陈筝，刘悦来，刘颂.美国景观视觉资源规划设计方法评析及新技术改进潜力分析[J].风景园林，2015(5):111-117.
• [12] YE Y,RICHARDS D,LU Y,et al.Measuring daily accessed street greenery:A human-scale approach for informing better urban planning practices[J].Landscape and Urban Planning,2019,191:103434.DOI:10.1016/j.landurbplan.2018.08.028.
• [13] 张书亮，闾国年，李秀梅.网络地理信息系统[M].北京：科学出版社，2005.
• [14] ZHANG G,ZHU A X.The representativeness and spatial bias of volunteered geographic information:A review[J].Annals of GIS,2018,24(3):151-162.
• [15] 徐磊青，江文津，陈筝.公共空间安全感研究：以上海城市街景感知为例[J].风景园林，2018,25(7):23-29.
• [16] NAIK N,PHILIPOOM J,RASKAR R,et al.Streetscore-predicting the perceived safety of one million streetscapes[A].2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops[C].2014.793-799.
• [17] ZHANG F,ZHOU B L,LIU L,et al.Measuring human perceptions of a large-scale urban region using machine learning[J].Landscape and Urban Planning,2018,180:148-160.
• [18] ZHANG F,FAN Z Y,KANG Y H,et al."Perception bias":Deciphering a mismatch between urban crime and perception of safety[J].Landscape and Urban Planning,2021,207:104003.DOI:10.1016/j.landurbplan.2020.104003.
• [19] COZENS P M.Urban planning and environmental criminology:Towards a new perspective for safer cities[J].Planning Practice and Research,2011,26(4):481-508.
• [20] KINNEY J B,BRANTINGHAM P L,WUSCHKE K,et al.Crime attractors,generators and detractors:Land use and urban crime opportunities[J].Built Environment,2008,34(1):62-74.
• [21] BRANTINGHAM P,BRANTINGHAM P.Criminality of place:Crime generators and crime attractors[J].European Journal on Criminal Policy and Research,1995,3(3):5-26.
• [22] LI H,HERFORT B,HUANG W,et al.Exploration of openstreetmap missing built-up areas using twitter hierarchical clustering and deep learning in mozambique[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,166:41-51.
• [23] 陈子豪，张毅，刘瑜，等.基于社交媒体感知城市旅游活动类型——以苏州市为例[J].地理与地理信息科学，2020,36(2):54-61.
• [24] 张雪霞，吴升，赵志远，等.基于手机信令数据的城市小活动空间人群空间分布特征[J].地球信息科学学报，2021,23(8):1433-1445.
• [25] 姚海芳，冯天楠，刘劲松.基于手机信令数据的机场航空旅客分类识别研究——以石家庄正定国际机场为例[J].地理与地理信息科学，2020,36(3):56-62.
• [26] 长沙市规划勘测设计研究院.长沙市城市总体规划(2003-2020)(2014修改)[EB/OL].http://www.csgky.net/product/30.html,2022-01-07.
• [27] ZHAO H S,SHI J P,QI X J,et al.Pyramid scene parsing network[A].2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[C].2017.6230-6239.
• [28] SHELHAMER E,LONG J,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
• [29] CORDTS M,OMRAN M,RAMOS S,et al.The cityscapes dataset for semantic urban scene understanding[A].2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[C].2016.3213-3223.
• [30] MMSEGMENTATION.OpenMMLab semantic segmentation toolbox and benchmark[Z/OL] https://github.com/open-mmlab/mmsegmentation,2020-12-31.
• [31] 黄杏元，马劲松，汤勤.地理信息系统概论[M].北京：高等教育出版社，2001.
• [32] 陈健，曾钰洁，黄军林.以人民为中心的“15分钟生活圈”行动规划实践及启示——基于长沙的观察[J].中外建筑，2020(11):124-127.
• [33] 王德，傅英姿.手机信令数据助力上海市社区生活圈规划[J].上海城市规划，2019(6):23-29.
• [34] WAGSTAFF K,CARDIE C,ROGERS S,et al.Constrained K-means clustering with background knowledge[A].Proceedings of 18th International Conference on Machine Learning[C].2001.577-584.
• [35] 张帆，刘瑜.街景影像——基于人工智能的方法与应用[J].遥感学报，2021,25(5):1043-1054.