| 摘要: |
| 新技术条件下测度街道绿化品质，实现人眼视角绿化可见度与街道可达性的整合分析。抓取上海的大规模街景数据，基于机器学习算法提取绿化可见度，将其与基于空间网络分析的街道可达性开展叠合分析，并与基于卫星遥感影像的绿化率比较，发现绿化率难以准确展现市民日常生活中绿化接触度。运用新技术和新数据推动精细化规划导控，实践上能实现大规模分析并保证高精度结果，理论上能为规划政策的人本视角转型提供支撑。 |
| 关键词: 风景园林 街道绿化 百度街景 机器学习 人本视角 空间网络分析 |
| DOI： |
| 分类号:TU986 |
| 基金项目:国家自然科学基金青年项目“街道空间界面宜步行性的精细化测度及设计导控研究——以上海为例”（编号51708410）；上海市浦江人才计划（编号17PGC107）；住房和城乡建设部科学技术计划北京建筑大学北京未来城市设计高精尖创新中心开放课题资助项目“基于多源城市大数据与深度学习的城市空间品质评价与设计导控”（编号UDC2017010412)；同济大学高密度人居环境生态与节能教育部重点实验室开放课题 |
|
| Measuring Street Greening Quality from Humanistic Perspective: A Large-scale Analysis Based on Baidu Street View Images and Machine Learning Algorithms |
|
YE Yu1, ZHANG Lingzhu2, YAN Wentao1, ZENG Wei3
|
|
1.Tongji University;2.University of Hong Kong;3.Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
|
| Abstract: |
| This paper proposed an approach for quantifying daily exposure of urban residents to eye-level greenery. 280,000 street view images in Shanghai central area are collected for greenery analyses via machine learning. The integration of the street greenery with street accessibility helps to provide detailed guidance for better spatial quality on streets and efficient urban greenery planning. The comparison between this new index and the traditional urban green cover shows that the latter one might not accurately reflect accessed greenery for citizens. This study helps to achieve the co-present of large-scale but also high-resolution analysis. Moreover, it makes a step forward for a more human-centered planning policy. |
| Key words: landscape architecture street greenery BAIDU street view machine learning human-centered perspective spatial network analysis |
| 引用本文: | 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，2018，25（8）：24-29. |
| YE Yu,ZHANG Lingzhu,YAN Wentao,ZENG Wei.Measuring Street Greening Quality from Humanistic Perspective: A Large-scale Analysis Based on Baidu Street View Images and Machine Learning Algorithms[J].Landscape Architecture Journal, 2018, 25(8):24-29. |
|
