引用本文:[点击复制]
[点击复制]
【打印本页】 【在线阅读全文】【下载PDF全文】 查看/发表评论下载PDF阅读器关闭

←前一篇|后一篇→

过刊浏览    高级检索

本文已被:浏览 266次   下载 0 本文二维码信息
码上扫一扫!
人工智能赋能城市滨水空间秋季景观特征 识别与活力提升——以上海市黄浦江为例
汪洁琼,江卉卿,陈俊延,柯楠,王敏*
0
作者简介:汪洁琼 1981年生/女/上海人/博士/同济大学建筑与城市规划学院景观学 系副主任,副教授,博士生导师/高密度人居环境生态与节能教 育部重点实验室(同济大学)水绿生态智能分实验中心联合创始 人/自然资源部大都市区国土空间生态修复工程技术创新中心成 员/研究方向为水绿生态智能、景观生态规划与设计、水生态、 城市生态修复工程技术与设计/本刊特约编辑(上海 200092)
摘要:
上海市积极深化“一江一河”建设,打造具有全球 影响力的世界级滨水空间,以绿化品质提升的“四化”建设为 引领,促进季节性景观营造,从而激发滨水空间活力。针对城 市滨水空间尺度大、范围广、数据多的特征,以人工智能赋能 下滨水秋季景观特征的全覆盖、多时相、数字化识别为核心, 以上海市黄浦江滨水空间中心城区段为例,训练滨水空间秋季 景观特征识别的深度学习算法构建语义分割模型,实现对实证 案例大批量样本数据的秋季景观特征智能化识别与测度;通过 基于位置的服务(location-based services,LBS)大数据分 析手段,量化揭示上海市黄浦江滨水空间中心城区段活力时空 分布特征。探索影响城市滨水空间活力的秋季景观特征的关键 因素,为城市滨水空间秋季景观的营造与活力激发提供理论依 据与技术支撑。
关键词:  风景园林  人工智能  城市滨水空间  秋季景观特 征  语义分割  基于位置的服务(LBS)
DOI:10.19775/j.cla.2024.09.0015
投稿时间:2024-05-06修订日期:2024-07-09
基金项目:国家自然科学基金面上项目(52178053);上海科 委重点研发项目(22dz1202200);同济大学建筑设计研究院 (集团)有限公司自主课题(2023J-JB02)
Identification of Autumn Landscape Characteristicsand Vitality Improvement in Urban Waterfront SpacesBased on Artificial Intelligence: A Case Study ofHuangpu River in Shanghai
WANG Jieqiong,JIANG Huiqing,CHEN Junyan,KE Nan,WANG Min
Abstract:
Shanghai actively deepens the construction of "One River, One Riverbank" while emphasizing the advancement of the "Four Enhancements" to enhance green quality. This initiative aims to create a globally influential world-class waterfront space, promoting urban ecosystem services and stimulating urban vitality. This research aims to achieve full coverage, multi-temporal, and digitized intelligent recognition for urban waterfront spaces based on artificial intelligence. Taking the central urban area along the Huangpu River waterfront in Shanghai as an example, a deep learning algorithm for identifying autumn landscape characteristics in waterfront spaces was trained to construct a semantic segmentation model. By utilizing LBS big data analysis, the spatiotemporal distribution characteristics of vitality in the central urban area along the Huangpu River waterfront in Shanghai were elucidated. This study efficiently and precisely measured the autumn landscape characteristics of a large batch of empirical case sample data, revealing key factors influencing the vitality of urban waterfront spaces. These findings provide theoretical basis and technical support for urban waterfront space renewal, reconstruction, and landscape design.
Key words:  landscape architecture  artificial intelligence  urban waterfront space  autumn landscape characteristics  semantic segmentation  location-based services (LBS)

京公网安备 11010802028240号

用微信扫一扫

用微信扫一扫