Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification

Claudio Coppola; Serhan Cosar; Diego R. Faria; Nicola Bellotto

doi:10.1109/ROMAN.2017.8172405

Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification

Claudio Coppola, Serhan Cosar, Diego R. Faria, Nicola Bellotto

College of Engineering and Physical Sciences

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

We present a system for temporal detection of social interactions. Many of the works until now have succeeded in recognising activities from clipped videos in datasets, but for robotic applications, it is important to be able to move to
more realistic data. For this reason, the proposed approach temporally detects intervals where individual or social activity is occurring. Recognition of human activities is a key feature for analysing the human behaviour. In particular, recognition of social activities is useful to trigger human-robot interactions
or to detect situations of potential danger. Based on that, this research has three goals: (1) define a new set of descriptors, which are able to characterise human interactions; (2) develop a computational model to segment temporal intervals with
social interaction or individual behaviour; (3) provide a public
dataset with RGB-D data with continuous stream of individual
activities and social interactions. Results show that the proposed
approach attained relevant performance with temporal
segmentation of social activities.

Original language	English
Title of host publication	IEEE RO-MAN'17: IEEE International Symposium on Robot and Human Interactive Communication, Lisbon, Portugal
Publisher	IEEE
ISBN (Electronic)	978-1-5386-3518-6
ISBN (Print)	978-1-5386-3519-3
DOIs	https://doi.org/10.1109/ROMAN.2017.8172405
Publication status	E-pub ahead of print - 14 Dec 2017

Publication series

Name	2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)
Publisher	IEEE
ISSN (Electronic)	1944-9437

Bibliographical note

© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Access to Document

10.1109/ROMAN.2017.8172405

Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification
© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 1.96 MB

Cite this

Coppola, C., Cosar, S., Faria, D. R., & Bellotto, N. (2017). Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification. In IEEE RO-MAN'17: IEEE International Symposium on Robot and Human Interactive Communication, Lisbon, Portugal (2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)). IEEE. Advance online publication. https://doi.org/10.1109/ROMAN.2017.8172405

Coppola, Claudio ; Cosar, Serhan ; Faria, Diego R. et al. / Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification. IEEE RO-MAN'17: IEEE International Symposium on Robot and Human Interactive Communication, Lisbon, Portugal. IEEE, 2017. (2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)).

@inproceedings{1be7e41073584c44b5154a7d339ccec9,

title = "Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification",

abstract = "We present a system for temporal detection of social interactions. Many of the works until now have succeeded in recognising activities from clipped videos in datasets, but for robotic applications, it is important to be able to move tomore realistic data. For this reason, the proposed approach temporally detects intervals where individual or social activity is occurring. Recognition of human activities is a key feature for analysing the human behaviour. In particular, recognition of social activities is useful to trigger human-robot interactionsor to detect situations of potential danger. Based on that, this research has three goals: (1) define a new set of descriptors, which are able to characterise human interactions; (2) develop a computational model to segment temporal intervals withsocial interaction or individual behaviour; (3) provide a publicdataset with RGB-D data with continuous stream of individualactivities and social interactions. Results show that the proposedapproach attained relevant performance with temporalsegmentation of social activities.",

author = "Claudio Coppola and Serhan Cosar and Faria, {Diego R.} and Nicola Bellotto",

note = "{\textcopyright} 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. ",

year = "2017",

month = dec,

day = "14",

doi = "10.1109/ROMAN.2017.8172405",

language = "English",

isbn = " 978-1-5386-3519-3",

series = "2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)",

publisher = "IEEE",

booktitle = "IEEE RO-MAN'17: IEEE International Symposium on Robot and Human Interactive Communication, Lisbon, Portugal",

address = "United States",

}

Coppola, C, Cosar, S, Faria, DR & Bellotto, N 2017, Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification. in IEEE RO-MAN'17: IEEE International Symposium on Robot and Human Interactive Communication, Lisbon, Portugal. 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), IEEE. https://doi.org/10.1109/ROMAN.2017.8172405

Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification. / Coppola, Claudio; Cosar, Serhan; Faria, Diego R. et al.
IEEE RO-MAN'17: IEEE International Symposium on Robot and Human Interactive Communication, Lisbon, Portugal. IEEE, 2017. (2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification

AU - Coppola, Claudio

AU - Cosar, Serhan

AU - Faria, Diego R.

AU - Bellotto, Nicola

N1 - © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2017/12/14

Y1 - 2017/12/14

N2 - We present a system for temporal detection of social interactions. Many of the works until now have succeeded in recognising activities from clipped videos in datasets, but for robotic applications, it is important to be able to move tomore realistic data. For this reason, the proposed approach temporally detects intervals where individual or social activity is occurring. Recognition of human activities is a key feature for analysing the human behaviour. In particular, recognition of social activities is useful to trigger human-robot interactionsor to detect situations of potential danger. Based on that, this research has three goals: (1) define a new set of descriptors, which are able to characterise human interactions; (2) develop a computational model to segment temporal intervals withsocial interaction or individual behaviour; (3) provide a publicdataset with RGB-D data with continuous stream of individualactivities and social interactions. Results show that the proposedapproach attained relevant performance with temporalsegmentation of social activities.

AB - We present a system for temporal detection of social interactions. Many of the works until now have succeeded in recognising activities from clipped videos in datasets, but for robotic applications, it is important to be able to move tomore realistic data. For this reason, the proposed approach temporally detects intervals where individual or social activity is occurring. Recognition of human activities is a key feature for analysing the human behaviour. In particular, recognition of social activities is useful to trigger human-robot interactionsor to detect situations of potential danger. Based on that, this research has three goals: (1) define a new set of descriptors, which are able to characterise human interactions; (2) develop a computational model to segment temporal intervals withsocial interaction or individual behaviour; (3) provide a publicdataset with RGB-D data with continuous stream of individualactivities and social interactions. Results show that the proposedapproach attained relevant performance with temporalsegmentation of social activities.

U2 - 10.1109/ROMAN.2017.8172405

DO - 10.1109/ROMAN.2017.8172405

M3 - Conference publication

SN - 978-1-5386-3519-3

T3 - 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)

BT - IEEE RO-MAN'17: IEEE International Symposium on Robot and Human Interactive Communication, Lisbon, Portugal

PB - IEEE

ER -

Coppola C, Cosar S, Faria DR, Bellotto N. Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification. In IEEE RO-MAN'17: IEEE International Symposium on Robot and Human Interactive Communication, Lisbon, Portugal. IEEE. 2017. (2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)). Epub 2017 Dec 14. doi: 10.1109/ROMAN.2017.8172405

Automatic Detection of Human Interactions from RGB-D Data for Social Activity Classification

Abstract

Publication series

Bibliographical note

Access to Document

Fingerprint

Cite this