Crowd-Sourced City Images: Decoding Multidimensional Interaction between Imagery Elements with Volunteered Photos

Abstract

The built environment reshapes various scenes that can be perceived, experienced, and interpreted, which are known as city images. City images emerge as the complex composite of various imagery elements. Previous studies demonstrated the coincide between the city images produced by experts with prior knowledge and that are extracted from the high-frequency photo contents generated by citizens. The realistic city images hidden behind the volunteered geo-tagged photos, however, are more complex than assumed. The dominating elements are only one side of the city image; more importantly, the interactions between elements are also crucial for understanding how city images are structured in people’s minds. This paper focuses on the composition of city image–the various interactions between imagery elements and areas of a city. These interactions are identified as four aspects: co-presence, hierarchy, heterogeneity, and differentiation, which are quantified and visualized respectively as correlation network, dendrogram, spatial clusters, and scattergrams in a framework using scene recognition with volunteered and georeferenced photos. The outputs are interdependent elements, typologies of elements, imagery areas, and preferences for groups, which are essential for urban design processes. In the application in Central Beijing, the significant interdependency between two elements is complex and is not necessarily an interaction between the elements with higher frequency only. The main typologies and the principal imagery elements are different from what were prefixed in the image recognition model. The detected imagery areas with adaptive thresholds suggest the spatially varying spill over effects of named areas and their typologies can be well annotated by the detected principal imagery elements. The aggregation of the data from different social media platforms is proven as a necessity of calibrating the unbiased scope of the city image. Any specific data can hardly capture the whole sample. The differentiation across the local and non-local is found to be related to their preference and activity space. The results provide more comprehensive insights on the complex composition of city images and its effects on placemaking.

Social Media Image and Computer Vision Method Application in Landscape Studies: A Systematic Literature Review

“…The dominant theme was the comprehensive assessment of these services. In the urban planning and management branch, researchers use crowdsourced images to develop an overall image of a city comprising various intentional elements or to focus on the public perception and use of certain places [42,43]. Distinguishing different urban styles through landscape feature quantification is another important research theme [44].…”

“…Based on the overall information expressed by an image, a neural network is used to assign and label images to the most likely scene categories [16,42]. [45] Image clustering An unsupervised learning method that uses algorithms to cluster semantically similar images by extracting the images' features and converting them into vectors [34,51].…”

Social Media Data in Urban Design and Landscape Research: A Comprehensive Literature Review

“…In urban design and landscape studies, the introduction of a deep learning image classification frameworks can answer the major research questions of resident/tourist behavior and perception, the identification of urban landscape features, landscape assessment, and natural disaster assessment. ResNet-50 [17,136], ResNet-101 [137], ResNet-152 [138,139], VGGNet [18,114,[140][141][142], Densenet-161 [143], and Inception v3 [144] are the deep learning frameworks used in these studies, with VGG-16 and ResNet being the most commonly used. Essentially, the deep learning approach straddles the limits of traditional approaches in terms of accuracy and data volume for the purpose of image content analysis.…”