Increasing computational power and improving deep learning methods have made computer vision technologies pervasively common in urban environments. Their applications in policing, traffic management, and documenting public spaces are increasingly common. Despite the often-discussed biases in the algorithms' training and unequally borne benefits, almost all applications similarly reduce urban experiences to simplistic, reductive, and mechanistic measures. There is a lack of context, depth, and specificity in these practices that enables semantic knowledge or analysis within urban contexts, especially within the context of using and occupying urban space. This paper will critique existing uses of artificial intelligence and computer vision in urban practices to propose a new framework for understanding people, action, and public space. This paper revisits Geertz's use of thick descriptions in generating interpretive theories of culture and activity and uses this lens to establish a framework to evaluate the varied uses of computer vision technologies that weigh meaning. We discuss how the framework's positioning may differ (and conflict) between different users of the technology. This paper also discusses the current use and training of deep learning algorithms and how this process limits semantic learning and proposes three potential methodologies for gaining a more contextually specific, urban-semantic, description of urban space relevant to urbanists. This paper contributes to the critical conversations regarding the proliferation of artificial intelligence by challenging the current applications of these technologies in the urban environment by highlighting their failures within this context while also proposing an evolution of these algorithms that may ultimately make them sensitive and useful within this spatial and cultural milieu.