8. 基于情绪改善的街道设计策略 9. 海珠区街道规划设计 (1)规划层面:开发靠近高品质自然景观的街道,如提高偏远地区的绿色空间与蓝色空间的可达性,提升可达性高的微小绿色空间和水体空间提升空间质量。通过管理建筑密度、引入绿色空间、提升绿化覆盖率等优化高密度城区的街道。在居住区周边街道建设慢行交通系统、提供社交空间等。 (2)设计层面:使用屋顶绿化、垂直绿化等绿化形式提高绿化覆盖率,使用能刺激感官的植物配置(如使用芳香植物、色彩艳丽的植物等)。结合微地形建设运动步道、种植池等。在建筑密度高的街道空间利用艺术装置(如镜子、灯光等)增加天空可视率,在空旷、炎热的街道空间提供遮荫设施或种植行道树以减少天空可视率。对人视范围内的建筑表面进行优化或种植透光的行道树等,以减少建筑带来的压迫感。 5 不足与展望 本研究仍存在一定的局限性。首先,本研究采用的数据为横断面数据,无法判断自变量与因变量之间的因果关系。在探讨街景要素对情绪状态的影响的数据分析方法上,采用了直接从SVM模型输出重要性的方法,无法真正从统计学意义上清晰地确定显著的重要特征。因此,未来可以开展相关纵向研究,并采用更深入的统计分析方法。其次,研究结果易受到街景图像数据与算法本身的局限性的影响。一方面,目前公开的街景图像数据集主要由安装在汽车上的摄像头进行采集,与人行视角存在偏差,且不包括许多仅限于行人通行的街区。同时,这些数据无法捕捉时间、天气变化等因素。在这一点上,从多时空尺度、人视角度收集的图片、视频或三维重建模型数据[54]等可成为未来相关研究数据的补充。另一方面,用于语义切割的PSPNet模型只能识别19类语义对象,图像特征有被错误分类的可能性,且无法考虑其他如光线、色彩、轮廓线等其他视觉特征或街道卫生、建筑高度、空气污染等其他环境因素。从这点而言,未来的研究可以结合更多元的城市环境数据如兴趣点(POI)、空气质量指数[55-56]等,以更进一步探讨影响情绪状态的环境因素。最后,由于采取的是人工评估的方式获取的情绪状态感知得分,难免可能会存在由于性别、年龄、职业等人口统计学特征因素导致的个体主观偏差。因此,未来可以结合可穿戴设备[57]等客观测量手段对情绪进行测量,或进一步探讨不同类型人群、不同人口统计学特征对情绪状态的影响。 (图片来源: 图片均由作者自绘) 参考文献: [1] SCHACHTER S, SINGER J. Cognitive, social, and physiological determinants of emotional state [J]. Psychological review, 1962, 69(5): 379. [2] CORREIA A W, PETERS J L, LEVY J I, et al. Residential exposure to aircraft noise and hospital admissions for cardiovascular diseases: multi-airport retrospective study[J]. British Medical Journal, 2013, 347: f5561. [3] KUO M. How might contact with nature promote human health? Promising mechanisms and a possible central pathway[J]. Frontiers in Psychology, 2015(6): 1093. [4] Using functional Magnetic Resonance Imaging (fMRI) to analyze brain region activity when viewing landscapes[J].Landscape and Urban Planning, 2017,162: 137-144. [5] YU C, LEE H, LUO X. The effect of virtual reality forest and urban environments on physiological and psychological responses[J]. Urban Forestry & Urban Greening, 2018, 35: 106-114. [6] JIANG B, ZHANG T, SULLIVAN W C. Healthy Cities: Mechanisms and research questions regarding the impacts of urban green landscapes on public health and well-being[J]. Landscape Architecture Frontiers, 2015, 3: 24-35. [7] HOULDEN V, WEICH S, DE ALBUQUERQUE J P, et al. The relationship between greenspace and the mental wellbeing of adults: A systematic review[J]. PloS one, 2018,13(9): e203000. [8] LIN W, CHEN Q, JIANG M, et al. The effect of green space behaviour and per capita area in small urban green spaces on psychophysiological responses[J]. Landscape and Urban Planning, 2019, 192: 103637. [9] GAO T, ZHANG T, ZHU L, et al. Exploring Psychophysiological Restoration and Individual Preference in the Different Environments Based on Virtual Reality[J]. International Journal of Environmental Research and Public Health, 2019, 16(17): 3102.[10] HARTIG T, EVANS G W, JAMNER L D, et al. Tracking restoration in natural and urban field settings[J]. Journal of Environmental Psychology, 2003, 23(2): 109-123.[11] WOOD L, HOOPER P, FOSTER S, et al. Public green spaces and positive mental health – investigating the relationship between access, quantity and types of parks and mental wellbeing[J]. Health & Place, 2017, 48: 63-71.[12] TAYLOR M S, WHEELER B W, WHITE M P, et al. Research note: Urban street tree density and antidepressant prescription rates—A cross-sectional study in London, UK[J]. Landscape and Urban Planning, 2015,136: 174-179.[13] LI D, SULLIVAN W C. Impact of views to school landscapes on recovery from stress and mental fatigue[J] . Landscape and Urban Planning, 2016,148: 149-158.[14] MARSELLE M R, BOWLER D E, WATZEMA J, et al. Urban street tree biodiversity and antidepressant prescriptions[J] . Scientific Reports, 2020, 10(1): 22445.[15] ZHAO J, WU J, WANG H. Characteristics of urban streets in relation to perceived restorativeness[J] . Journal of Exposure Science & Environmental Epidemiology, 2020,30(2): 309-319.[16] CHEN X, CUI Z, HAO L. Research on the methodology of evidence-based design based on VR Technology[J]. China Illuminating Eng, 2019, 30(02): 123-129.[17] CHEN Z, ZHU X. Research on Automatic Emotion Recognition for Learners based on Facial Expression: Relevance Research Situation Existing Problems and Development Paths[J]. Journal of distance education, 2019, 37(04): 64-72.[18] WATSON D, CLARK L A, TELLEGEN A. Development and validation of brief measures of positive and negative affect: the PANAS scales[J]. Journal of personality and social psychology, 1988, 54(6): 1063.[19] SPIELBERGER C D, GONZALEZ-REIGOSA F, MARTINEZ-URRUTIA A, et al. The state-trait anxiety inventory[J]. Revista Interamericana de Psicologia/Interamerican Journal of Psychology, 1971, 5(3 & 4).[20] JIANG B, XU W, JI W, et al. Impacts of nature and built acoustic-visual environments on human's multidimensional mood states: A cross-continent experiment[J] . Journal of Environmental Psychology, 2021, 77: 101659.[21] WILKIE S, CLEMENTS H. Further exploration of environment preference and environment type congruence on restoration and perceived restoration potential[J]. Landscape and Urban Planning, 2018, 170: 314-319.[22] YIN J, YUAN J, ARFAEI N, et al. Effects of biophilic indoor environment on stress and anxiety recovery: A between-subjects experiment in virtual reality[J]. Environment International, 2020, 136: 105427.[23] QIN J, ZHOU X, SUN C, et al. Influence of green spaces on environmental satisfaction and physiological status of urban residents[J]. Urban Forestry & Urban Greening, 2013, 12(4): 490-497.[24] LI J, JIN Y, LU S, et al. Building environment information and human perceptual feedback collected through a combined virtual reality (VR) and electroencephalogram (EEG) method[J]. Energy and Buildings, 2020, 224: 110259.[25] OJHA V K, GRIEGO D, KULIGA S, et al. Machine learning approaches to understand the influence of urban environments on human's physiological response[J]. Information Sciences, 2019, 474: 154-169.[26] CHEN Z, SCHULZ S, QIU M, et al. Assessing affective experience of in-situ environmental walk via wearable biosensors for evidence-based design[J]. Cognitive Systems Research, 2018, 52: 970-977.[27]QUERCIA D, O'HARE N K, CRAMER H. Aesthetic capital: what makes London look beautiful, quiet, and happy? [C]. Proceedings of the 17th ACM Conference on Computer Supported Cooperative Work and Social Computing. New York: ACM, 2014: 945–955.[28] SERESINHE C I, PREIS T, MOAT H S. Quantifying the Impact of Scenic Environments on Health[J]. Scientific Reports, 2015, 5(1): 16899.[29] DUBEY A, NAIK N, PARIKH D, et al. Deep Learning the City: Quantifying Urban Perception at a Global Scale[M]. Cham: Springer International Publishing, 2016. [30] WANG R, LU Y, ZHANG J, et al. The relationship between visual enclosure for neighbourhood street walkability and elders' mental health in China: Using street view images[J]. Journal of Transport & Health, 2019, 13: 90-102.[31] LI X, ZHANG C, LI W. Does the Visibility of Greenery Increase Perceived Safety in Urban Areas? Evidence from the Place Pulse 1.0 Dataset[J]. ISPRS International Journal of Geo-Information. 2015, 4(3): 1166-1183.[32] BADER M D M, MOONEY S J, LEE Y J, et al. Development and deployment of the Computer Assisted Neighborhood Visual Assessment System (CANVAS) to measure health-related neighborhood conditions[J]. Health & Place, 2015, 31: 163-172.[33] QUE J, LU L, SHI L. Development and challenges of mental health in China[J]. General Psychiatry, 2019, 32(1).[34] 广州市统计局. 2021年广州市人口规模及分布情况[EB/OL] . (2022-03-04)[2022-07-15]. http://tjj.gz.gov.cn/tjgb/qtgb/content/post_8120709.html.[35] ZHAO H, SHI J, QI X, et al. Pyramid Scene Parsing Network[C]. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 2881-2890. [36] CORDTS M, OMRAN M, RAMOS M, et al. The Cityscapes Dataset for Semantic Urban Scene Understanding[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 3213-3223. [37] TREVIN E G, HUYEN T K L, E. S G, et al. How transport modes, the built and natural environments, and activities influence mood: A GPS smartphone app study[J]. Journal of Environmental Psychology, 2019, 66(C).[38] JIANG B, XU W, JI W, et al. Impacts of nature and built acoustic-visual environments on human's multidimensional mood states: A cross-continent experiment[J]. Journal of Environmental Psychology, 2021 ,77: 101659.[39] DUBEY A, NAIK N, PARIKH D, et al. Deep Learning the City: Quantifying Urban Perception at a Global Scale[M]. Cham: Springer International Publishing, 2016. [40] ZHANG F, ZHOU B, 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.[41] ORDONEZ V, BERG T L. Learning high-level judgments of urban perception[C]. European conference on computer vision. Berlin: Springer, 2014: 494-510. [42] SALESSES P, SCHECHTNER K, HIDALGO C A. The Collaborative Image of The City: Mapping the Inequality of Urban Perception[J]. PLOS ONE, 2013, 8: e684007.[43] ANSELIN L. Local indicators of spatial association—LISA[J]. Geographical analysis, 1995, 27(2): 93-115.[44] TERRY H, GARY W E, LARRY D J, et al. Tracking restoration in natural and urban field settings[J]. Journal of Environmental Psychology, 2003, 23(2): 109-123.[45] 朱晓玥,金凯,余洋. 基于实景图片的恢复性环境空间类型及特征研究[J]. 西部人居环境学刊,2020,35(04):25-33.[46] 西蒙·贝尔. 公众健康和幸福感考量的城市蓝色空间——城市景观研究新领域[J]. 风景园林, 2019,26(09):119-131.[47] MENG L, WEN K, ZENG Z, et al. The impact of street space perception factors on elderly health in high-density cities in Macau—analysis based on street view images and deep learning technology[J]. Sustainability, 2020, 12(5): 1799.[48] YUAN M, YIN C, SUN Y, et al. Examining the associations between urban built environment and noise pollution in high-density high-rise urban areas: A case study in Wuhan, China[J]. Sustainable Cities and Society, 2019, 50: 101678.[49] BIN J, CHUN-YEN C, WILLIAM C S. A dose of nature: Tree cover, stress reduction, and gender differences[J]. Landscape and Urban Planning, 2014,132: 26-36.[50] ZHAO J, WU J, WANG H. Characteristics of urban streets in relation to perceived restorativeness.[J] . Journal of exposure science & environmental epidemiology, 2020, 30(2): 309-319.[51] RUOYU W, YI L, JINBAO Z, et al. The relationship between visual enclosure for neighbourhood street walkability and elders' mental health in China: Using street view images[J]. Journal of Transport & Health, 2019, 13: 90-102.[52] JI Z, CHYE K H, LAI C M, et al. Evaluating environmental implications of density: A comparative case study on the relationship between density, urban block typology and sky exposure[J]. Automation in Construction, 2012, 22: 90-101.[53] HUANG Q, YANG M, JANE H, et al. Trees, grass, or concrete? The effects of different types of environments on stress reduction[J]. Landscape and Urban Planning, 2020, 193: 103654.[54] RAMÍREZ T, HURTUBIA R, LOBEL H, et al. Measuring heterogeneous perception of urban space with massive data and machine learning: An application to safety[J]. Landscape and Urban Planning, 2021, 208: 104002.[55] ZHANG Y, CHEN N, DU W, et al. Multi-source sensor based urban habitat and resident health sensing: A case study of Wuhan, China[J]. Building and Environment, 2021, 198: 107883.[56] TANG Z, YE Y, JIANG Z, et al. A data-informed analytical approach to human-scale greenway planning: Integrating multi-sourced urban data with machine learning algorithms[J]. Urban Forestry & Urban Greening, 2020, 56: 126871.[57] VERMA D, JANA A, RAMAMRITHAM K. Predicting human perception of the urban environment in a spatiotemporal urban setting using locally acquired street view images and audio clips[J]. Building and Environment, 2020, 186: 107340. 如有需要,可扫描下图二维码购买《时代建筑》电子版或纸质版(购买纸质版请标注具体期数)电子版 纸质版