A new approach for social group detection based on spatio-temporal interpersonal distance measurement
Visual-based social group detection aims to cluster pedestrians in crowd scenes according to social interactions and spatio-temporal position relations by using surveillance video data. It is a basic technique for crowd behaviour analysis and group-based activity understanding. According to the theo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-10-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S240584402202326X |
| _version_ | 1811247855747203072 |
|---|---|
| author | Jie Su Jianglan Huang Linbo Qing Xiaohai He Honggang Chen |
| author_facet | Jie Su Jianglan Huang Linbo Qing Xiaohai He Honggang Chen |
| author_sort | Jie Su |
| collection | DOAJ |
| description | Visual-based social group detection aims to cluster pedestrians in crowd scenes according to social interactions and spatio-temporal position relations by using surveillance video data. It is a basic technique for crowd behaviour analysis and group-based activity understanding. According to the theory of proxemics study, the interpersonal relationship between individuals determines the scope of their self-space, while the spatial distance can reflect the closeness degree of their interpersonal relationship. In this paper, we proposed a new unsupervised approach to address the issues of interaction recognition and social group detection in public spaces, which remits the need to intensely label time-consuming training data. First, based on pedestrians' spatio-temporal trajectories, the interpersonal distances among individuals were measured from static and dynamic perspectives. Combined with proxemics' theory, a social interaction recognition scheme was designed to judge whether there is a social interaction between pedestrians. On this basis, the pedestrians are clustered to identify if they form a social group. Extensive experiments on our pedestrian dataset “SCU-VSD-Social” annotated with multi-group labels demonstrated that the proposed method has outstanding performance in both accuracy and complexity. |
| first_indexed | 2024-04-12T15:16:48Z |
| format | Article |
| id | doaj.art-d162e7d8a284457388708f65bdd7fc7c |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-12T15:16:48Z |
| publishDate | 2022-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-d162e7d8a284457388708f65bdd7fc7c2022-12-22T03:27:36ZengElsevierHeliyon2405-84402022-10-01810e11038A new approach for social group detection based on spatio-temporal interpersonal distance measurementJie Su0Jianglan Huang1Linbo Qing2Xiaohai He3Honggang Chen4College of Electronics and Information Engineering, Sichuan University, Chengdu, Sichuan, 610064, ChinaCollege of Electronics and Information Engineering, Sichuan University, Chengdu, Sichuan, 610064, ChinaCorresponding author.; College of Electronics and Information Engineering, Sichuan University, Chengdu, Sichuan, 610064, ChinaCollege of Electronics and Information Engineering, Sichuan University, Chengdu, Sichuan, 610064, ChinaCollege of Electronics and Information Engineering, Sichuan University, Chengdu, Sichuan, 610064, ChinaVisual-based social group detection aims to cluster pedestrians in crowd scenes according to social interactions and spatio-temporal position relations by using surveillance video data. It is a basic technique for crowd behaviour analysis and group-based activity understanding. According to the theory of proxemics study, the interpersonal relationship between individuals determines the scope of their self-space, while the spatial distance can reflect the closeness degree of their interpersonal relationship. In this paper, we proposed a new unsupervised approach to address the issues of interaction recognition and social group detection in public spaces, which remits the need to intensely label time-consuming training data. First, based on pedestrians' spatio-temporal trajectories, the interpersonal distances among individuals were measured from static and dynamic perspectives. Combined with proxemics' theory, a social interaction recognition scheme was designed to judge whether there is a social interaction between pedestrians. On this basis, the pedestrians are clustered to identify if they form a social group. Extensive experiments on our pedestrian dataset “SCU-VSD-Social” annotated with multi-group labels demonstrated that the proposed method has outstanding performance in both accuracy and complexity.http://www.sciencedirect.com/science/article/pii/S240584402202326XSocial group detectionSocial interactionSpatio-temporal trajectoryInterpersonal distance measurementProxemics |
| spellingShingle | Jie Su Jianglan Huang Linbo Qing Xiaohai He Honggang Chen A new approach for social group detection based on spatio-temporal interpersonal distance measurement Heliyon Social group detection Social interaction Spatio-temporal trajectory Interpersonal distance measurement Proxemics |
| title | A new approach for social group detection based on spatio-temporal interpersonal distance measurement |
| title_full | A new approach for social group detection based on spatio-temporal interpersonal distance measurement |
| title_fullStr | A new approach for social group detection based on spatio-temporal interpersonal distance measurement |
| title_full_unstemmed | A new approach for social group detection based on spatio-temporal interpersonal distance measurement |
| title_short | A new approach for social group detection based on spatio-temporal interpersonal distance measurement |
| title_sort | new approach for social group detection based on spatio temporal interpersonal distance measurement |
| topic | Social group detection Social interaction Spatio-temporal trajectory Interpersonal distance measurement Proxemics |
| url | http://www.sciencedirect.com/science/article/pii/S240584402202326X |
| work_keys_str_mv | AT jiesu anewapproachforsocialgroupdetectionbasedonspatiotemporalinterpersonaldistancemeasurement AT jianglanhuang anewapproachforsocialgroupdetectionbasedonspatiotemporalinterpersonaldistancemeasurement AT linboqing anewapproachforsocialgroupdetectionbasedonspatiotemporalinterpersonaldistancemeasurement AT xiaohaihe anewapproachforsocialgroupdetectionbasedonspatiotemporalinterpersonaldistancemeasurement AT honggangchen anewapproachforsocialgroupdetectionbasedonspatiotemporalinterpersonaldistancemeasurement AT jiesu newapproachforsocialgroupdetectionbasedonspatiotemporalinterpersonaldistancemeasurement AT jianglanhuang newapproachforsocialgroupdetectionbasedonspatiotemporalinterpersonaldistancemeasurement AT linboqing newapproachforsocialgroupdetectionbasedonspatiotemporalinterpersonaldistancemeasurement AT xiaohaihe newapproachforsocialgroupdetectionbasedonspatiotemporalinterpersonaldistancemeasurement AT honggangchen newapproachforsocialgroupdetectionbasedonspatiotemporalinterpersonaldistancemeasurement |