City safety perception model based on visual content of street images

Safety perception measurement has been a subject of interest in many cities of the world. This is due to its social relevance, and to its effect on some local economic activities. Even though people safety perception is a subjective topic, sometimes it is possible to find out common beliefs given a restricted sociocultural context. This paper presents an approach that makes use of image processing and machine learning techniques to model citizen’s safety perception using visual information of city images. The proposed method predicts how safe a given street of Bogotá City can be. This is done based on people judgment of the visual appearance of a street image. Results suggest that the obtained model is able to detect city streets, where a visual feature is linked to an activity or street condition that has a significant influence on their associated safety perception. This feature makes the proposed model an alternative tool for decision makers with regard to urban planning, safety and health public policies, as well as a collective memory associated to a particular urban environment.