风景园林2025，Vol.32Issue(5)：37-44,8.DOI:10.3724/j.fjyl.LA20240048
城市街道绿化泛类结构的视觉感知特征——以天津市市内六区为例
Research on Pedestrians'Visual Perception Characteristics Based on USGGS:A Case Study of the Six Inner-City Districts of Tianjin
摘要
Abstract
[Objective]This research aims to explore in depth the interactions between urban street greening general structure(USGGS),and pedestrians'visual perception,and the influence of USGGS on urban ecological environment and residents'health.USGGS,the vertical hierarchical structure of urban street greening,covers a variety of dimensions such as trees,shrubs,and grasses,which is of great importance for enhancing the quality of urban ecological environment,improving the physiological health of residents,and alleviating the tension between urban residents and the natural environment.The core objective of the research is to propose strategies to optimize the greening structure of urban streets by analyzing the correlation between USGGS and visual perception of pedestrians,so as to enhance the quality of the visual environment of street pedestrians,improve the urban human settlement environment and promote the organic integration of the urban ecological and humanistic environments,thus providing a new way of thinking for urban planning and construction,and promoting the high-quality and sustainable development of urban street space. [Methods]The research selects the six inner-city districts of Tianjin City as the research area,utilizes Baidu street view image(SVI)as data source,and collect SVIs and their coordinates in the six districts in 2019 by calling Baidu API,with a total of 17,326 points selected and 13,281 valid samples obtained after screening.The DeepLabV3+neural network model is used for semantic segmentation of SVIs to accurately recognize and segment various landscape elements in urban SVIs.The model increases the sensory field of the convolution kernel by Atrous convolution technique and null convolution,allowing the model to capture image details at different resolutions and providing more accurate feature recognition support for subsequent SVI segmentation tasks.Based on the study of pedestrians'visual perception,green view index(GVI),openness,and enclosure are selected as quantitative indicators.Through multiple linear regression,anomaly and clustering analysis by ArcGis software,and geographically weighted regression analysis,the influence of different USGGS on pedestrians'visual perception and their spatial distribution characteristics are explored. [Results]The results of the research reveal the significant influence of uneven spatial distribution of USGGS on pedestrians'visual perception.The vegetation hierarchy configuration in the six inner-city districts of Tianjin presents a spatial distribution characteristic of centripetal aggregation,while the proximity of the six inner-city districts and the four ring city districts presents a more homogeneous distribution trend of greening structure.Through the clustering and outlier analysis tools,it is found that the causes of the abnormal areas of pedestrians'visual perception are closely related to the spatial distribution characteristics of USGGS.In addition,the spatial distribution characteristics of pedestrians'visual perception of openness show negative correlation with the distribution characteristics of GVI,while the high values of visual perception of enclosure are mainly concentrated in areas with high building density.These results not only reveal the significant influence of USGGS type on pedestrians'visual perception,but also provide a scientific basis for the optimization of urban street greening structure. [Conclusion]The research emphasizes the importance of rationally configuring USGGS types to enhance the environmental quality of urban streets.USGGS not only changes the physical spatial morphology of urban streets,but also significantly affects the visual perception of pedestrians.The arbor-shrub-grass structure,the arbor-shrub structure,the arbor-grass structure,and the arbor structure have a significant influence on pedestrians'visual perception of GVI and openness,while the structure containing shrubs can significantly increase the level of pedestrians'visual perception of enclosure.These findings emphasize the importance of considering USGGS configurations in urban planning to create visual environments that are better suited to the function of the place,enhance the ecological value of streets as well as the life quality of residents,and promote sustainable urban development.The challenges faced by street greening in Tianjin include uneven spatial distribution,insufficient resilience,low public participation and varying regional management levels.It is recommended to increase the area of street greening space,optimize the allocation of greening resources,and improve community participation and residents'sense of belonging through scientific planning and construction.In addition,measures such as strengthening cross-regional collaboration,sharing practical experience,upgrading management standards and providing technical support are needed to achieve a balanced development of management level among regions.The research also proposes directions for future research,including improving the accuracy of element identification through image correction techniques,utilizing POI place attribute data to conduct a large-scale USGGS research of spatial heterogeneity in pedestrians'visual perception,and incorporating more physical spatial measurement data to expand the depth of research and provide more comprehensive scientific support for urban planning.Through these comprehensive measures,the level of urban street greening can be enhanced more effectively to create a healthier and more comfortable living environment for residents.关键词
风景园林/计算机视觉/城市街道/绿化结构/视觉感知/空间异质性Key words
landscape architecture/computer vision/urban street/green structure/visual perception/spatial heterogeneity分类
土木建筑引用本文复制引用
杨瀚文,邹尚恩,胡一可..城市街道绿化泛类结构的视觉感知特征——以天津市市内六区为例[J].风景园林,2025,32(5):37-44,8.基金项目
国家自然科学基金重点项目"基于中华语境"建筑-人-环境"融贯机制的当代营建体系重构研究"(编号 52038007) （编号 52038007）
