Street Quality Measurement and Accessibility Analysis Based on Streetscape Data: The Case of Mingcheng District in Xi’an City

As the predominant component of public space in urban areas, streets serve as a fundamental framework of a city’s spatial form. The renewal and enhancement of urban street space are integral to the broader processes of urban regeneration and the sustainable development of both urban and rural areas. This study focuses on the Mingcheng area of Xi’an, employing semantic segmentation technology to extract data and analyze the spatial characteristics of factors influencing street quality. The results of spatial network accessibility analysis are then superimposed, creating a “quality–accessibility” evaluation matrix to provide a comprehensive assessment of the streets within the study area. The findings indicate the following: (1) The spatial quality of streets in Mingcheng District ranges from 1.89 to 5.61, based on the scores ranked from highest to lowest; the streets are categorized into five quality levels: very high, high, medium, low, and very low. (2) Using a radius of 0.8 km for calculation, streets with a centrality value of 600 or above are classified as having high accessibility, whereas those below this threshold are considered to have low accessibility. (3) By constructing a “quality–accessibility” evaluation matrix, the following distribution is obtained: 21.4% of streets are classified as high-quality and high-accessibility, 27.1% as high-quality but low-accessibility, 35.3% as low-quality but high-accessibility, and 16.3% as both low-quality and low-accessibility. (4) A significant correlation exists between street quality, accessibility, and the classification of streets in Mingcheng District. Grounded in the community renewal strategy of the study area, this study investigates the practical integration of urban public space quality improvements and streetscape big data analytics. The methodology employed systematically evaluates the spatial quality of streets in Mingcheng District, offering foundational data and technical support for urban planning and renewal initiatives while contributing valuable insights to urban renewal scholarship.