城市研究中的计算机视觉应用进展与展望
|
摘要
城市图像一直是记录城市发展变迁的重要信息载体,在当前的互联网与大数据时代,随着图片分享网站、社交媒体、街景地图等线上平台的蓬勃发展,可获取的图像数据正在以前所未有的速度增加。同时,来自人工智能领域的计算机视觉技术经过40余年的发展取得了大量进展,使对海量城市图像的大规模、自动化判别与解析成为可能。近年来,计算机视觉与城市研究的交叉催生了一系列创新性研究,形成一个具有重大潜力的跨学科研究领域。本文通过对这一领域前沿成果的梳理指出,当前计算机视觉在城市研究领域的应用主要体现在城市环境认知评价、城市与建筑文化识别、建成环境与社会经济耦合分析、城市风貌与城市设计评估四个方面。同时,计算机视觉在视觉认知研究拓展、城市文化计算模拟、城市设计技术创新等方面都展现出了较大的发展前景,但也存在着技术方法、研究对象、价值取向等方面的局限与挑战。
Urban images, in various types of format, are always important sources of records for urban development and transition. In the era of Internet and big data, the burgeoning photo sharing websites, social media, and street views have further generated an unprecedented volume of online urban images. Meanwhile, the computer vision technique in the field of artificial intelligence has made great progress after more than forty years' development. It is now possible to let a computer read and interpret urban images automatically and in a large scale, which has given rise to a few highly interesting studies, as well as an emerging field of interdisciplinary research. By reviewing the works that innovatively apply computer vision in urban studies, the paper points out that such applications are mainly in the aspects of urban environment perception and evaluation, urban and architectural culture identification, coupling analysis on the built environment and socio-economic development, and landscape and urban design evaluation. In addition, the paper discusses the potential of computer vision in the urban cognitive research, computational urban cultural modelling, technical innovation of urban design, etc., and also points out that this field is confronted with constraints and challenges in terms of technical method, research object, as well as value choice.
Urban images, in various types of format, are always important sources of records for urban development and transition. In the era of Internet and big data, the burgeoning photo sharing websites, social media, and street views have further generated an unprecedented volume of online urban images. Meanwhile, the computer vision technique in the field of artificial intelligence has made great progress after more than forty years' development. It is now possible to let a computer read and interpret urban images automatically and in a large scale, which has given rise to a few highly interesting studies, as well as an emerging field of interdisciplinary research. By reviewing the works that innovatively apply computer vision in urban studies, the paper points out that such applications are mainly in the aspects of urban environment perception and evaluation, urban and architectural culture identification, coupling analysis on the built environment and socio-economic development, and landscape and urban design evaluation. In addition, the paper discusses the potential of computer vision in the urban cognitive research, computational urban cultural modelling, technical innovation of urban design, etc., and also points out that this field is confronted with constraints and challenges in terms of technical method, research object, as well as value choice.
引文
1 LEE S,MAISONNEUVE N,CRANDALL D,et al.Linking Past to Present:Discovering Style in Two Centuries of Architecture[C]//Proceedings of 2015 IEEE International Conference on Computational Photography.IEEE,2015:1-10.
2 SZELISKI R.Computer Vision:Algorithms and Applications[J].Journal of Polymer Science Part A:Polymer Chemistry Edition,2011,21(8):2601-2605.
3孙剑.计算机视觉:让冰冷的机器看懂这个多彩的世界[EB/OL].http://www.msra.cn/zh-cn/news/features/computer-vision-20150210.aspx.SUN Jian.Computer Vision:Let the Cold Machine Understand the Colourful World[EB/OL].http://www.msra.cn/zh-cn/news/features/computervision-20150210.aspx.
4卢宏涛,张秦川.深度卷积神经网络在计算机视觉中的应用研究综述[J].数据采集与处理,2016,31(1):1-17.LU Hongtao,ZHANG Qinchuan.Application of Deep Convoluntional Neural Network in Computer Vision[J].Journal of Data Acquisition and Processing,2016,31(1):1-17.
5 DHAR S,ORDONEZ V,BERG T L.High Level Describable Attributes for Predicting Aesthetics and Interestingness[C]//Proceedings of 2011 IEEE Conference on Computer Vision&Pattern Recognition.IEEE,2011:1657-1664.
6 MARCHESOTTI L,PERRONNIN F,LARLUS D,et al.Assessing the Aesthetic Quality of Photographs Using Generic Image Descriptors[C]//Proceedings of 2011 IEEEInternational Conference on Computer Vision.IEEE Computer Society,2011:1784-1791.
7 ISOLA P,PARIKH D,TORRALBA A,et al.Understanding the Intrinsic Memorability of Images[C]//Advances in Neural Information Processing Systems 24.NIPS,2011:2429-2437.
8 YONG J L,EFROS A A,HEBERT M.StyleAware Mid-Level Representation for Discovering Visual Connections in Space and Time[C]//Proceedings of 2013IEEE International Conference on Computer Vision.IEEE,2013:1857-1864.
9 PATTERSON G,HAYS J.SUN Attribute Database:Discovering,Annotating,and Recognizing Scene Attributes[C]//Proceedings of 2012 IEEE Conference on Computer Vision&Pattern Recognition.IEEE,2012:2751-2758.
10 XIAO J,HAYS J,EHINGER K A,et al.SUNDatabase:Large-Scale Scene Recognition from Abbey to Zoo[C]//Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision&Pattern Recognition.IEEE,2010:3485-3492.
11 SUDDERTH E B,TORRALBA A,FREEMAN W T,et al.Learning Hierarchical Models of Scenes,Objects,and Parts[C]//Proceedings of the 10th IEEE International Conference on Computer Vision.IEEE,2005:1331-1338.
12 LI L J,SU H,LIM Y,et al.Objects as Attributes for Scene Classification[C]//Trends and Topics in Computer Vision.Berlin and Heidelberg:Springer,2012:57-69.
13 LAZEBNIK S,SCHMID C,PONCE J.Beyond Bags of Features:Spatial Pyramid Matching for Recognizing Natural Scene Categories[C]//Proceedings of 2006 IEEEComputer Society Conference on Computer Vision and Pattern Recognition.IEEE,2006:2169-2178.
14 TIGHE J,LAZEBNIK S.Finding Things:Image Parsing with Regions and Per-Exemplar Detectors[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2013:3001-3008.
15 LADICKYL U,RUSSELL C,KOHLI P,et al.Associative Hierarchical CRFs for Object Class Image Segmentation[C]//Proceedings of the 12th International Conference on Computer Vision.IEEE,2009:739-746.
16 GOULD S,FULTON R,KOLLER D.Decomposing a Scene into Geometric and Semantically Consistent Regions[C]//Proceedings of the IEEE 12th International Conference on Computer Vision.IEEE,2009:1-8.
17 IOVAN C,PICARD D,THOME N,et al.Classification of Urban Scenes from Geo-Referenced Images in Urban Street-View Context[C]//Proceedings of the11th International Conference on Machine Learning and Applications.IEEE,2012:339-344.
18 HAYS J,EFROS A.IM2GPS:Estimating Geographic Information from a Single Image[C]//Proceedings of2008 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2008:1-8.
19 ZAMIR A R,SHAH M.Accurate Image Localization Based on Google Maps Street View[C]//Computer Vision-ECCV2010.Berlin and Heidelberg:Springer,2010:255-268.
20 QUERCIA D,O’HARE N K,CRAMER H.Aesthetic Capital:What Makes London Look Beautiful,Quiet,and Happy?[C]//CSCW’14 Proceedings of the 17th ACMConference on Computer Supported Cooperative Work&Social Computing.New York:ACM,2014:945-955.
21 SALESSES P,SCHECHTNER K,HIDALGO C A.The Collaborative Image of the City:Mapping the Inequality of Urban Perception[J].Plos One,2013,8(7):e68400.
22 QUERCIA D,PESCE J P,ALMEIDA V,et al.Psychological Maps 2.0:A Web Gamification Enterprise Starting in London[C]//WWW’13 Proceedings of the 22nd International Conference on World Wide Web.New York:ACM,2013:1065-1076.
23 NAIK N,PHILIPOOM J,RASKAR R,et al.Streetscore:Predicting the Perceived Safety of One Million Streetscapes[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.IEEE,2014:793-799.
24 ORDONEZ V,BERG T L.Learning High-Level Judgments of Urban Perception[C]//Computer Vision-ECCV 2014.Springer,2014:494-510.
25 DOERSCH C,SINGH S,GUPTA A,et al.What Makes Paris Look Like Paris?[J].ACM Transactions on Graphics,2012,31(4).
26 SHALUNTS G,HAXHIMUSA Y,SABLATNIG R.Architectural Style Classification of Building Facade Windows[C]//Advances in Visual Computing.Berlin and Heidelberg:Springer,2011:280-289.
27 SHALUNTS G,HAXHIMUSA Y,SABLATNIG R.Architectural Style Classification of Domes[C]//Advances in Visual Computing.Berlin and Heidelberg:Springer,2012:420-429.
28 XU Z,TAO D,ZHANG Y,et al.Architectural Style Classification Using Multinomial Latent Logistic Regression[C]//Computer Vision-ECCV 2014.Berlin and Heidelberg:Springer,2014:600-615.
29 QUERCIA D.Urban:Crowdsourcing for the Good of London[C]/Proceedings of the 22nd International Conference on World Wide Web Companion.New York:ACM,2013:591-592.
30 QUERCIA D,SCHIFANELLA R,AIELLO L M.The Shortest Path to Happiness:Recommending Beautiful,Quiet,and Happy Routes in the City[C]//Proceedings of the 25th ACM Conference on Hypertext and Social Media.2014:116-125.
31 MILGRAM S.A Psychological Map of New York City[J].American Scientist,1972,60:194-200.
32 ZHOU B,LIU L,OLIVA A,et al.Recognizing City Identity via Attribute Analysis of Geo-Tagged Images[C]//Computer Vision-ECCV 2014.Berlin and Heidelberg:Springer International Publishing,2014:519-534.
33 GOEL A,JUNEJA M,JAWAHAR C.Are Buildings Only Instances?:Exploration in Architectural Style Categories[C]/Proceedings of the Eighth Indian Conference on Computer Vision,Graphics and Image Processing.New York:ACM,2012:Article No.1.
34 NAIK N,KOMINERS S D,RASKAR R,et al.Do People Shape Cities,or Do Cities Shape People?The Co-Evolution of Physical,Social,and Economic Change in Five Major U.S.Cities[Z].National Bureau of Economic Research Working Paper Series,2015,No.21620.
35 LIU L,SILVA E A,WU C,et al.A Machine LearningBased Method for the Large-Scale Evaluation of the Qualities of the Urban Environment[J].Computers,Environment and Urban Systems,2017,65:113-125.
36 PETERSON G L.A Model of Preference:Quantitative Analysis of the Perception of the Visual Appearance of Residential Neighborhoods[J].Journal of Regional Science,1967,7(1):19-31.
37 STAMPS A E.Physical Determinants of Preferences for Residential Facades[J].Environment and Behavior,1999,31(6):723-751.
38 LINDAL P J,HARTIG T.Architectural Variation,Building Height,and the Restorative Quality of Urban Residential Streetscapes[J].Journal of Environmental Psychology,2013,33(2):26-36.
39希利尔B.空间是机器[M].北京:中国建筑工业出版社,2008.HILLIER B.Space Is the Machine[M].Beijing:China Architecture&Building Press,2008.
(1)https://www.flickr.com/photos/franckmichel/6855169886。
(2)http://www.geograph.org.uk,致力于众包提供英国和爱尔兰“每平方公里最具代表性的”照片。
(3)AlexN et和GoogL eN et是分别在2012和2014年的ImageN et大规模视觉识别挑战赛(ILSVRC)中获胜的深度学习算法。
2 SZELISKI R.Computer Vision:Algorithms and Applications[J].Journal of Polymer Science Part A:Polymer Chemistry Edition,2011,21(8):2601-2605.
3孙剑.计算机视觉:让冰冷的机器看懂这个多彩的世界[EB/OL].http://www.msra.cn/zh-cn/news/features/computer-vision-20150210.aspx.SUN Jian.Computer Vision:Let the Cold Machine Understand the Colourful World[EB/OL].http://www.msra.cn/zh-cn/news/features/computervision-20150210.aspx.
4卢宏涛,张秦川.深度卷积神经网络在计算机视觉中的应用研究综述[J].数据采集与处理,2016,31(1):1-17.LU Hongtao,ZHANG Qinchuan.Application of Deep Convoluntional Neural Network in Computer Vision[J].Journal of Data Acquisition and Processing,2016,31(1):1-17.
5 DHAR S,ORDONEZ V,BERG T L.High Level Describable Attributes for Predicting Aesthetics and Interestingness[C]//Proceedings of 2011 IEEE Conference on Computer Vision&Pattern Recognition.IEEE,2011:1657-1664.
6 MARCHESOTTI L,PERRONNIN F,LARLUS D,et al.Assessing the Aesthetic Quality of Photographs Using Generic Image Descriptors[C]//Proceedings of 2011 IEEEInternational Conference on Computer Vision.IEEE Computer Society,2011:1784-1791.
7 ISOLA P,PARIKH D,TORRALBA A,et al.Understanding the Intrinsic Memorability of Images[C]//Advances in Neural Information Processing Systems 24.NIPS,2011:2429-2437.
8 YONG J L,EFROS A A,HEBERT M.StyleAware Mid-Level Representation for Discovering Visual Connections in Space and Time[C]//Proceedings of 2013IEEE International Conference on Computer Vision.IEEE,2013:1857-1864.
9 PATTERSON G,HAYS J.SUN Attribute Database:Discovering,Annotating,and Recognizing Scene Attributes[C]//Proceedings of 2012 IEEE Conference on Computer Vision&Pattern Recognition.IEEE,2012:2751-2758.
10 XIAO J,HAYS J,EHINGER K A,et al.SUNDatabase:Large-Scale Scene Recognition from Abbey to Zoo[C]//Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision&Pattern Recognition.IEEE,2010:3485-3492.
11 SUDDERTH E B,TORRALBA A,FREEMAN W T,et al.Learning Hierarchical Models of Scenes,Objects,and Parts[C]//Proceedings of the 10th IEEE International Conference on Computer Vision.IEEE,2005:1331-1338.
12 LI L J,SU H,LIM Y,et al.Objects as Attributes for Scene Classification[C]//Trends and Topics in Computer Vision.Berlin and Heidelberg:Springer,2012:57-69.
13 LAZEBNIK S,SCHMID C,PONCE J.Beyond Bags of Features:Spatial Pyramid Matching for Recognizing Natural Scene Categories[C]//Proceedings of 2006 IEEEComputer Society Conference on Computer Vision and Pattern Recognition.IEEE,2006:2169-2178.
14 TIGHE J,LAZEBNIK S.Finding Things:Image Parsing with Regions and Per-Exemplar Detectors[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2013:3001-3008.
15 LADICKYL U,RUSSELL C,KOHLI P,et al.Associative Hierarchical CRFs for Object Class Image Segmentation[C]//Proceedings of the 12th International Conference on Computer Vision.IEEE,2009:739-746.
16 GOULD S,FULTON R,KOLLER D.Decomposing a Scene into Geometric and Semantically Consistent Regions[C]//Proceedings of the IEEE 12th International Conference on Computer Vision.IEEE,2009:1-8.
17 IOVAN C,PICARD D,THOME N,et al.Classification of Urban Scenes from Geo-Referenced Images in Urban Street-View Context[C]//Proceedings of the11th International Conference on Machine Learning and Applications.IEEE,2012:339-344.
18 HAYS J,EFROS A.IM2GPS:Estimating Geographic Information from a Single Image[C]//Proceedings of2008 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2008:1-8.
19 ZAMIR A R,SHAH M.Accurate Image Localization Based on Google Maps Street View[C]//Computer Vision-ECCV2010.Berlin and Heidelberg:Springer,2010:255-268.
20 QUERCIA D,O’HARE N K,CRAMER H.Aesthetic Capital:What Makes London Look Beautiful,Quiet,and Happy?[C]//CSCW’14 Proceedings of the 17th ACMConference on Computer Supported Cooperative Work&Social Computing.New York:ACM,2014:945-955.
21 SALESSES P,SCHECHTNER K,HIDALGO C A.The Collaborative Image of the City:Mapping the Inequality of Urban Perception[J].Plos One,2013,8(7):e68400.
22 QUERCIA D,PESCE J P,ALMEIDA V,et al.Psychological Maps 2.0:A Web Gamification Enterprise Starting in London[C]//WWW’13 Proceedings of the 22nd International Conference on World Wide Web.New York:ACM,2013:1065-1076.
23 NAIK N,PHILIPOOM J,RASKAR R,et al.Streetscore:Predicting the Perceived Safety of One Million Streetscapes[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.IEEE,2014:793-799.
24 ORDONEZ V,BERG T L.Learning High-Level Judgments of Urban Perception[C]//Computer Vision-ECCV 2014.Springer,2014:494-510.
25 DOERSCH C,SINGH S,GUPTA A,et al.What Makes Paris Look Like Paris?[J].ACM Transactions on Graphics,2012,31(4).
26 SHALUNTS G,HAXHIMUSA Y,SABLATNIG R.Architectural Style Classification of Building Facade Windows[C]//Advances in Visual Computing.Berlin and Heidelberg:Springer,2011:280-289.
27 SHALUNTS G,HAXHIMUSA Y,SABLATNIG R.Architectural Style Classification of Domes[C]//Advances in Visual Computing.Berlin and Heidelberg:Springer,2012:420-429.
28 XU Z,TAO D,ZHANG Y,et al.Architectural Style Classification Using Multinomial Latent Logistic Regression[C]//Computer Vision-ECCV 2014.Berlin and Heidelberg:Springer,2014:600-615.
29 QUERCIA D.Urban:Crowdsourcing for the Good of London[C]/Proceedings of the 22nd International Conference on World Wide Web Companion.New York:ACM,2013:591-592.
30 QUERCIA D,SCHIFANELLA R,AIELLO L M.The Shortest Path to Happiness:Recommending Beautiful,Quiet,and Happy Routes in the City[C]//Proceedings of the 25th ACM Conference on Hypertext and Social Media.2014:116-125.
31 MILGRAM S.A Psychological Map of New York City[J].American Scientist,1972,60:194-200.
32 ZHOU B,LIU L,OLIVA A,et al.Recognizing City Identity via Attribute Analysis of Geo-Tagged Images[C]//Computer Vision-ECCV 2014.Berlin and Heidelberg:Springer International Publishing,2014:519-534.
33 GOEL A,JUNEJA M,JAWAHAR C.Are Buildings Only Instances?:Exploration in Architectural Style Categories[C]/Proceedings of the Eighth Indian Conference on Computer Vision,Graphics and Image Processing.New York:ACM,2012:Article No.1.
34 NAIK N,KOMINERS S D,RASKAR R,et al.Do People Shape Cities,or Do Cities Shape People?The Co-Evolution of Physical,Social,and Economic Change in Five Major U.S.Cities[Z].National Bureau of Economic Research Working Paper Series,2015,No.21620.
35 LIU L,SILVA E A,WU C,et al.A Machine LearningBased Method for the Large-Scale Evaluation of the Qualities of the Urban Environment[J].Computers,Environment and Urban Systems,2017,65:113-125.
36 PETERSON G L.A Model of Preference:Quantitative Analysis of the Perception of the Visual Appearance of Residential Neighborhoods[J].Journal of Regional Science,1967,7(1):19-31.
37 STAMPS A E.Physical Determinants of Preferences for Residential Facades[J].Environment and Behavior,1999,31(6):723-751.
38 LINDAL P J,HARTIG T.Architectural Variation,Building Height,and the Restorative Quality of Urban Residential Streetscapes[J].Journal of Environmental Psychology,2013,33(2):26-36.
39希利尔B.空间是机器[M].北京:中国建筑工业出版社,2008.HILLIER B.Space Is the Machine[M].Beijing:China Architecture&Building Press,2008.
(1)https://www.flickr.com/photos/franckmichel/6855169886。
(2)http://www.geograph.org.uk,致力于众包提供英国和爱尔兰“每平方公里最具代表性的”照片。
(3)AlexN et和GoogL eN et是分别在2012和2014年的ImageN et大规模视觉识别挑战赛(ILSVRC)中获胜的深度学习算法。
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |