Review of Application Progress of Panoramic Imagery in Urban Research

Abstract

The advances of panoramic imaging technology, the growing popularity of street view imagery tools, and the development in artificial intelligence such as computer vision, machine learning and deep learning, have led to the use of panoramic imagery for large-scale, automated discrimination and parsing in urban research. The rapid development of the aforementioned fields has led to a large number of cross-cutting results between the fields of panoramic imagery, artificial intelligence and urban research in the last two decades. In this paper, CiteSpace and VOSviewer are utilized as analysis platforms to investigate the advancement of panoramic imagery applications in urban research. Firstly, three developmental stages of panoramic imagery in urban research are identified using a literature co-citation clustering network and a terminology time zone map. Subsequently, co-authorship network and keyword clustering analysis are employed to investigate the co-authorship relationships, acquisition methods and image information extraction techniques. Four main application fields of panoramic imagery in urban research are summarized: urban built environment, urban landscape environment, urban physical environment and smart city. Finally, the primary driving factors for the advancement of panoramic imagery application areas are summarized from a historical perspective. Additionally, current challenges and future trends of panoramic imagery application in urban research are discussed.

Keywords

• panoramic imagery; street view imagery; urban research; artificial intelligence; deep learning