Crowd emotion evaluation based on fuzzy inference of arousal and valence

Xuguang Zhang, Xiuxin Yang, Weiguang Zhang, Gongfa Li, Hui Yu

Research output: Contribution to journalArticlepeer-review

Abstract

Crowd behavior analysis is an important research topic in the field of video surveillance and public safety management. Crowd emotion has a strong relation with the crowd behavior. However, it is very challenging to predict crowd emotion using conventional emotion clues of humans from the video surveillance data, e.g. facial expression or body gesture. To tackle this challenge, this paper presents a crowd emotion evaluation method using fuzzy inference according to the arousal-valence model of the crowd movement. Specifically, the enthalpy, magnitude variance, confusion index and crowd density are extracted to describe crowd emotion. The enthalpy value and magnitude variance are taken as the input of the fuzzy inference system of arousal. And the confusion index and crowd density are used as the input of the fuzzy system of valence. The arousal value and valence value are the output respectively. Through establishing the relationship between arousal, valence and crowd features, the fuzzy rules are constructed to infer the emotion in the crowd scene. Experimental results show that the proposed method can effectively evaluate the arousal and valence in crowd emotion.
Original languageEnglish
JournalNeurocomputing
Publication statusAccepted for publication - 15 Feb 2021

Fingerprint

Dive into the research topics of 'Crowd emotion evaluation based on fuzzy inference of arousal and valence'. Together they form a unique fingerprint.

Cite this