城市尺度下的建筑色彩定量化测度——基于街景数据与机器学习的人本视角分析
|
摘要
新时期城市设计的人本化转型,催生了对于城市尺度下建筑色彩的一系列导控实践。研究针对以往建筑色彩分析难以在大尺度下高效开展的问题,结合街景数据和机器学习,提出了人本视角下的大规模、精细化分析方法。解决了以往建筑色彩分析拘泥于手工小样本采集,难以大范围运用的问题,可快速实现建筑色彩分析与主导色提取,为相关实践提供科学化建议。该分析方法运用开源易得的街景数据,实现了建筑色彩这一难以测度要素的精细化度量,在实践中具有较好的普适性和易用性。
The humanistic transformation of the urban design in the new era has given birth to a series of guiding and controlling practices for architectural color at city scale. In order to solve the problem that the previous architectural color analysis is difficult to carry out at a large scale, combining with street view data and machine learning, this article proposes a large-scale and refined analysis method from humanistic perspective. It solves the problem that the previous architectural color analysis is limited to manual small sample collection, difficult to be used in a wide range, can quickly realize architectural color analysis and dominant color extraction, and provide scientific suggestions for relevant practices. This analysis method uses open source and easy-to-obtain street view data to realize the refined measurement of architectural color, which is difficult to be measured, and has good universality and ease of use in practice.
The humanistic transformation of the urban design in the new era has given birth to a series of guiding and controlling practices for architectural color at city scale. In order to solve the problem that the previous architectural color analysis is difficult to carry out at a large scale, combining with street view data and machine learning, this article proposes a large-scale and refined analysis method from humanistic perspective. It solves the problem that the previous architectural color analysis is limited to manual small sample collection, difficult to be used in a wide range, can quickly realize architectural color analysis and dominant color extraction, and provide scientific suggestions for relevant practices. This analysis method uses open source and easy-to-obtain street view data to realize the refined measurement of architectural color, which is difficult to be measured, and has good universality and ease of use in practice.
引文
[1]卢济威.新时期城市设计的发展趋势[J].上海城市规划,2015(1):3-4.
[2]龙瀛,叶宇.人本尺度城市形态:测度、效应评估及规划设计响应[J].南方建筑,2016(5):41-47.
[3]叶宇.新城市科学背景下的城市设计新可能[J].西部人居环境学刊,2019,34(1):1-11.
[4]张梦宇,李钢,陈静勇.保护与更新视角下城市色彩规划的探讨:以北京老城历史文化街区为例[J].北京规划建设,2018(4):93-97.
[5]盖湘涛.城市的色彩美[J].住宅科技,1986(10):24-26.
[6]范榕,吴寒玉,赵锴铮.基于文献计量学的城市景观色彩研究现状与前景[J].现代城市研究,2018(7):18.
[7]龙瀛,周垠.图片城市主义:人本尺度城市形态研究的新思路[J].规划师,2017,33(2):54-60.
[8]叶宇,戴晓玲.新技术与新数据条件下的空间感知与设计运用可能[J].时代建筑,2017(5):6-13.
[9]BADRINARAYANAN V,KENDALL A,CIPOLLA R.Segnet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE transactions on pattern analysis and machine intelligence,2017,39(12):2481-2495.
[10]叶宇,张灵珠,颜文涛,曾伟.街道绿化品质的人本视角测度框架:基于百度街景数据和机器学习的大规模分析[J].风景园林,2018(8):24-29.
[11]NAIK N,PHILIPOOM J,RASKAR R,et al.Streetscore-predicting the perceived safety of one million streetscapes[C].2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops,2014:793-799.
[12]LI X,ZHANG C,LI W,et al.Assessing street-level urban greenery using Google Street View and a modified green view index[J].Urban Forestry&Urban Greening,2015,14(3):675-685..
[13]叶宇,张昭希,张啸虎,曾伟.人本尺度的街道空间品质测度:结合街景数据和新分析技术的大规模、高精度评价框架[J].国际城市规划,2019(1):18-27.
[14]GEHL J.Cities for people[M].London:Island press,2013.
[15]LONG Y,LIU L.How green are the streets?An analysis for central areas of Chinese cities using Tencent Street View[J].Plo S one,2017,12(2):e0171110.
[16]DAWSON-HOWE K.A practical introduction to computer vision with Open CV[M].New Jersey:John Wiley&Sons,2014.
[17]叶宇.新城市科学背景下的城市设计新可能[J].西部人居环境学刊,2019,34(1):13-21.
[2]龙瀛,叶宇.人本尺度城市形态:测度、效应评估及规划设计响应[J].南方建筑,2016(5):41-47.
[3]叶宇.新城市科学背景下的城市设计新可能[J].西部人居环境学刊,2019,34(1):1-11.
[4]张梦宇,李钢,陈静勇.保护与更新视角下城市色彩规划的探讨:以北京老城历史文化街区为例[J].北京规划建设,2018(4):93-97.
[5]盖湘涛.城市的色彩美[J].住宅科技,1986(10):24-26.
[6]范榕,吴寒玉,赵锴铮.基于文献计量学的城市景观色彩研究现状与前景[J].现代城市研究,2018(7):18.
[7]龙瀛,周垠.图片城市主义:人本尺度城市形态研究的新思路[J].规划师,2017,33(2):54-60.
[8]叶宇,戴晓玲.新技术与新数据条件下的空间感知与设计运用可能[J].时代建筑,2017(5):6-13.
[9]BADRINARAYANAN V,KENDALL A,CIPOLLA R.Segnet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE transactions on pattern analysis and machine intelligence,2017,39(12):2481-2495.
[10]叶宇,张灵珠,颜文涛,曾伟.街道绿化品质的人本视角测度框架:基于百度街景数据和机器学习的大规模分析[J].风景园林,2018(8):24-29.
[11]NAIK N,PHILIPOOM J,RASKAR R,et al.Streetscore-predicting the perceived safety of one million streetscapes[C].2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops,2014:793-799.
[12]LI X,ZHANG C,LI W,et al.Assessing street-level urban greenery using Google Street View and a modified green view index[J].Urban Forestry&Urban Greening,2015,14(3):675-685..
[13]叶宇,张昭希,张啸虎,曾伟.人本尺度的街道空间品质测度:结合街景数据和新分析技术的大规模、高精度评价框架[J].国际城市规划,2019(1):18-27.
[14]GEHL J.Cities for people[M].London:Island press,2013.
[15]LONG Y,LIU L.How green are the streets?An analysis for central areas of Chinese cities using Tencent Street View[J].Plo S one,2017,12(2):e0171110.
[16]DAWSON-HOWE K.A practical introduction to computer vision with Open CV[M].New Jersey:John Wiley&Sons,2014.
[17]叶宇.新城市科学背景下的城市设计新可能[J].西部人居环境学刊,2019,34(1):13-21.