基于城市功能和深度学习评分方法的社区感知研究——以海口市为例  

Community Perception Based on City Function and Deep Learning Scoring Method:A Case Study of Haikou City

在线阅读下载全文

作  者:潘璐 李清云 许先升 Pan Lu;Li Qingyun;Xu Xiansheng

机构地区:[1]海南大学热带农林学院 [2]中国热带农业科学院香料饮料研究所

出  处:《华中建筑》2024年第10期170-175,共6页Huazhong Architecture

基  金:国家自然科学基金“耗散理论视野下街道空间活力形成肌理实证研究——以海南湿热型旅游城市为例”(编号:52268011)。

摘  要:大数据和机器学习技术的发展为定量评估街道感知提供了全新的技术手段,本研究使用深度学习方法,以海口市中心城区为研究对象,利用该区域的街景图片,构建评分模型,从美丽、富有、安全、活力、压抑、无聊六个维度进行感知打分。将六个维度感知进一步分为积极感知与消极感知,最后将感知得分与海口市九类POI进行拟合。结果表明,高度城市化社区街道被认为更安全、更有活力,但同时伴随着更高的压抑感,社区感知在不同的POI类型(城市功能)上有明显差异。因此,从主观感知角度印证了城市功能在促进城市可持续发展方面的关键作用,并在基础设施服务供给方面为规划政策提供科学支撑。通过探索社区感知和城市功能模式的关系,阐述了所提出的深度学习评分方法在促进社区感知评估方面的有效性。The development of big data and computer science provides a new technique for quantitative evaluation of street perception.The downtown area of Haikou city was taken as the research object to verify the method of this study.Street images of this area were used to construct a deep learning scoring model,and six dimensions of beauty,wealth,safety,vitality,depression and boredom were used to score perceptions.The six dimensions of perception are further divided into positive perception and negative perception,and finally the perception scores are fitted with nine types of POI in Haikou City.The results showed that streets in highly urbanized neighborhoods were perceived to be safer and more vibrant,but at the same time were associated with higher feelings of repression,and community perception differed significantly in different types of POI(urban function).Therefore,from the perspective of subjective perception,the key role of urban functions in promoting urban sustainable development is confirmed,and scientific support is provided for planning policies in terms of infrastructure service supply.By exploring the correlation between community perception and urban functional patterns,the effectiveness of the proposed deep learning scoring method in promoting community perception evaluation is expounded.

关 键 词:居民感知 深度学习模型 ResNet 视觉智能 POI兴趣点 

分 类 号:TU984.1[建筑科学—城市规划与设计]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象