Urban commerce and its distribution have always been an important part of urban research. However, most previous studies were based on statistical data and did not reflect real street experience. Thanks to the Street View image and deep learning technology, researchers are able to carry out large scale studies from real human visual experience. In this article, we aim at sensing the commercial spaces in cities. In order to achieve this ultimate goal, deep learning is applied to process the raw data of Street View image. We disassemble the goal into three tasks: firstly, obtaining all the Street View images in a specific area; then classifying the Street View images according to the commercial facilities in it; and finally creating a visualization of the detected data into a map. For the first task, we get the road network coordinate information from the openstreetmap (OSM) website, set the sampling point on the road, and then download the Street View images of the sampling points' coordinate through the API provided by Baidumap. For the second task, we adopt a two-level learning strategy rather than directly using Deep Convolutional Neural Network for classification. For the final task, we choose the heat map as the expression of the results and draw the map by the existing GIS software. Furthermore, the results from this study can be conveniently combined with other data because of the use of street-network-based data structure. An application of this method combines with street-network data, the calculation of a city's 15-minute commercial service circle coverage is also shown in this study. INDEX TERMS Smart cities, urban commerce, deep learning, urban planning, street view image, object detection.

Danwei compounds have experienced a steady decline since the 1997 Urban Housing System Reform. Existing research suggests that Danwei compounds, which were characteristically walled neighbourhoods of work and residence, have experienced socio-spatial changes in social structure, community management and spatial form. However, there is limited understanding of its current spatial function and relation to the city. This study analysed the spatial distribution of Danwei compounds, their spatial features and accessibility to selected public facilities in comparison with non-Danwei residential sites in the old town of Hefei city. ArcGIS was used to analyse building density, plot ratio of the residential sites and their accessibility to public facilities. Further quantitative analysis was done using binary logistic regression and descriptive statistics to identify spatial features of the residential sites. The results show that even though the urban land reforms have led to a steady rise in non-Danwei residential sites, Danwei compounds predominate the urban spatial structure. Comparatively, Danwei compounds have lower plot ratios with higher levels of accessibility to commercial centres and hospitals but poor accessibility to schools. The paper suggests the need for local planning officials to support the revitalisation of old residential compounds through integrated and community-centred spatial planning.

This paper analysed socio-spatial changes in old urban neighbourhoods (Danwei compounds) in Chinese cities as a result of two major national level reforms: the Reform and Opening Up and the Urban Housing reform in 1978 and 1997, respectively. Existing research indicates fundamental changes have taken place in the political, economic and social aspects of Danwei compounds. However, there is a paucity of research on micro-level changes. To understand how these reforms have affected the social-spatial schema of Danwei Compounds, the study utilised mapping, key person interviews and field observation in AMS compound, Hefei city of Anhui province. This paper compared the AMS Danwei Compound before and after the reforms in terms of public spaces, building features and compound management. The study found that the AMS Danwei Compound has experienced a significant reduction in public space, an increase in building density and a reconfiguration of compound management actors. The study suggests the need for local planning authorities and government to pay attention to planning and design of the old city core by emphasising improvement in public spaces, attention to compact design principles for urban neighbourhood planning, and establishment of local community management body.

No abstract

No abstract