Detecting personality and emotion traits in crowds from video sequences

被引：16

作者：

Favaretto, Rodolfo Migon ^{[1
]}

Knob, Paulo ^{[1
]}

Musse, Soraia Raupp ^{[1
]}

Vilanova, Felipe ^{[2
]}

Costa, Angelo Brandelli ^{[2
]}

机构：

[1] Pontificia Univ Catolica Rio Grande do Sul, Grad Program Comp Sci, VHLab, Av Ipiranga 6681, Porto Alegre, RS, Brazil

[2] Pontificia Univ Catolica Rio Grande do Sul, Grad Program Psychol, Av Ipiranga 6681, Porto Alegre, RS, Brazil

来源：

MACHINE VISION AND APPLICATIONS | 2019年 / 30卷 / 05期

关键词：

Computer vision; Crowd features; Big Five model; Cultural dimensions; Crowd emotion; BEHAVIORS; CULTURES; SCENES;

D O I：

10.1007/s00138-018-0979-y

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a methodology to detect personality and basic emotion characteristics of crowds in video sequences. Firstly, individuals are detected and tracked, and then groups are recognized and characterized. Such information is then mapped to OCEAN dimensions, used to find out personality and emotion in videos, based on OCC emotion models. Although it is a clear challenge to validate our results with real life experiments, we evaluate our method with the available literature information regarding OCEAN values of different Countries and also emergent Personal distance among people. Hence, such analysis refer to cultural differences of each country too. Our results indicate that this model generates coherent information when compared to data provided in available literature, as shown in qualitative and quantitative results.

引用

页码：999 / 1012

页数：14

共 45 条

[1]

[Anonymous], 2008, P 7 INT JOINT C AUT

[2]

[Anonymous], 2016, ARXIV160707646

[3]

Baig MW, 2015, 2015 IEEE INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING (DSP), P703, DOI 10.1109/ICDSP.2015.7251966

[4] Composition, process, and performance in self-managed groups: The role of personality [J].