A Vision Sensor Network to Study Viewers' Visible Behavior of Art Appreciation

摘要

Since the empathic processes are essential to the aesthetic experience, the empathy-enabling technology for behavioral sensing is gaining its popularity to support the study of anonymized viewers' cognition in art appreciation. Because such behavior is highly dynamic and divergent among viewers, it is a challenge to observe the multiple dynamic features from the streaming data. In this study, we propose a vision sensor network (VSN) to support the visual interpretation of viewers' appreciation on visual arts. It firstly annotates the features in the captured frames based on CloudAPI (here the Google Cloud Vision API is used), and secondly the query on nested documents in MongoDB provides universal access to the annotated features. Comparing with the traditional approaches with subjective evidence, such as the questionnaire or social listening methods, the proposed VSN can interpret the visible behavior of viewers in real-time. In addition, it also has less selective bias because of more objective evidence being captured.