基于人工智能的城市肌理识别和评价研究

Urban Texture Recognition and Evaluation Based on Artificial Intelligence

基于人工智能技术,以量化和数据分析的方法重新挖掘城市肌理的内涵,以北京、上海、广州等十个城市的肌理数据为例,分别采用图像降维、k-means聚类、卷积神经网络分类以及机器学习等方法,建立城市图像识别和评价体系,最终得出,在现有评价体系内,经济总分值、软经济总分值、环境分值以及卫生分值与城市肌理的识别结果相关性最大,其中,环境分值与卫生分值的相关符合城市研究学者的通常认知,而经济总分值与软经济总分值的计算结果则说明城市建筑规划及其布局与城市的经济情况存在隐藏的相关性,也证明了基于图像识别的人工智能挖掘城市信息并评价的必要性。

In this paper,based on artificial intelligence,the connotation of urban texture is rediscovered by quantitative and data analysis,taking texture data of ten cities such as Beijing,Shanghai and Guangzhou as examples.The methods of image dimension reduction,k-means clustering,convolution neural network classification and machine learning are respectively adopted to establish an urban image recognition and evaluation system,and finally it is found that in the existing evaluation system,the total economic score,the total soft economic score,the environmental score and the sanitary score have the largest correlation with the recognition results of the urban texture,in which the correlation between the environmental score and the sanitary score accords with the common cognition of urban researchers.Therefore,the total economic score and the total soft economic score specifies that there is a hidden correlation between the urban planning layout and the city's economic situation.