Use of Tencent Street View Imagery for Visual Perception of Streets

Liang Cheng,Sensen Chu,Manchun Li,Wenwen Zong,Shuyi Li,Jie Wu

doi:10.3390/ijgi6090265

Abstract

The visual perception of streets plays an important role in urban planning, and contributes to the quality of residents’ lives. However, evaluation of the visual perception of streetscapes has been restricted by inadequate techniques and the availability of data sources. The emergence of street view services (Google Street View, Tencent Street View, etc.) has provided an enormous number of new images at street level, thus shattering the restrictions imposed by the limited availability of data sources for evaluating streetscapes. This study explored the possibility of analyzing the visual perception of an urban street based on Tencent Street View images, and led to the proposal of four indices for characterizing the visual perception of streets: salient region saturation, visual entropy, a green view index, and a sky-openness index. We selected the Jianye District of Nanjing City, China, as the study area, where Tencent Street View is available. The results of this experiment indicated that the four indices proposed in this work can effectively reflect the visual attributes of streets. Thus, the proposed indices could facilitate the assessment of urban landscapes based on visual perception. In summary, this study suggests a new type of data for landscape study, and provides a technique for automatic information acquisition to determine the visual perception of streets.

Highlights

Streets represent the most direct connection between urban residents and the city landscape [1]
At present, research on the landscapes and aesthetics of roads remains constrained by inadequate techniques and a shortage of data sources, a situation that results in complex information acquisition and landscape assessment
Based on our review of the studies published in the literature, there remain several unresolved issues in urban studies based on street views: (1) Some studies are based on street view images taken from a small number of angles and do not form a true panoramic image, resulting in gaps or overlaps in the visual field; and (2) visual perception has been treated as an abstract concept that requires evaluation from multiple aspects; currently, the single index is insufficient to describe the visual perception from multiple angles. In view of these issues, in our approach, we first process street view images into panoramic images that are compatible with human visual perspectives. Based on these panoramic images, we propose a technical procedure that involves a set of image processing methods, including image segmentation and the detection of salient regions, to extract the characteristics from a vast quantity of street view images

Summary

Introduction

Streets represent the most direct connection between urban residents and the city landscape [1]. The visual perception of streets often receives considerable attention in urban planning and construction [2]. Most departments in the U.S have their own methods for assessing landscape aesthetics [3]. Different schools of thought have formed various theories and methods based on urban landscape research, including visual impact assessment methods, scenic quality estimation models, landscape comparative assessment methods, and environmental assessment models [5,6]. At present, research on the landscapes and aesthetics of roads remains constrained by inadequate techniques and a shortage of data sources, a situation that results in complex information acquisition and landscape assessment

Methods

Results

Conclusion