Human-human interaction recognition based on spatial and motion trend feature

Bangli Liu; Haibin Cai; Xiaofei Ji; Honghai Liu

doi:10.1109/ICIP.2017.8297143

Human-human interaction recognition based on spatial and motion trend feature

Bangli Liu, Haibin Cai, Xiaofei Ji, Honghai Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

526 Downloads (Pure)

Abstract

Human-human interaction recognition has attracted increasing attention in recent years due to its wide applications in computer vision fields. Currently there are few publicly available RGBD-based human-human interaction datasets collected. This paper introduces a new dataset for human-human interaction recognition. Furthermore, a novel feature descriptor based on spatial relationship and semantic motion trend similarity between body parts is proposed for human-human interaction recognition. The motion trend of each skeleton joint is firstly quantified into the specific semantic word and then a Kernel is built for measuring the similarity of either intra or inter body parts by histogram interaction. Finally, the proposed feature descriptor is evaluated on the SBU interaction dataset and the collected dataset. Experimental results demonstrate the outperformance of our method over the state-of-the-art methods.

Original language	English
Title of host publication	2017 IEEE International Conference on Image Processing (ICIP)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4547-4551
Number of pages	5
ISBN (Electronic)	978-1-5090-2175-8
ISBN (Print)	978-1-5090-2176-5
DOIs	https://doi.org/10.1109/ICIP.2017.8297143
Publication status	Published - 22 Feb 2018
Event	2017 IEEE International Conference on Image Processing - Beijing, China Duration: 17 Sept 2017 → 20 Sept 2017 http://2017.ieeeicip.org/

Publication series

Name	IEEE ICIP Proceedings Series
ISSN (Electronic)	2381-8549

Conference

Conference	2017 IEEE International Conference on Image Processing
Abbreviated title	ICIP 2017
Country/Territory	China
City	Beijing
Period	17/09/17 → 20/09/17
Internet address	http://2017.ieeeicip.org/

Access to Document

10.1109/ICIP.2017.8297143

ICIP_submission_0815
© © 2018 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 (Post-print), 2.99 MB

Cite this

@inproceedings{fdc2020d8af8456989c94c36c47d485f,

title = "Human-human interaction recognition based on spatial and motion trend feature",

abstract = "Human-human interaction recognition has attracted increasing attention in recent years due to its wide applications in computer vision fields. Currently there are few publicly available RGBD-based human-human interaction datasets collected. This paper introduces a new dataset for human-human interaction recognition. Furthermore, a novel feature descriptor based on spatial relationship and semantic motion trend similarity between body parts is proposed for human-human interaction recognition. The motion trend of each skeleton joint is firstly quantified into the specific semantic word and then a Kernel is built for measuring the similarity of either intra or inter body parts by histogram interaction. Finally, the proposed feature descriptor is evaluated on the SBU interaction dataset and the collected dataset. Experimental results demonstrate the outperformance of our method over the state-of-the-art methods.",

author = "Bangli Liu and Haibin Cai and Xiaofei Ji and Honghai Liu",

year = "2018",

month = feb,

day = "22",

doi = "10.1109/ICIP.2017.8297143",

language = "English",

isbn = "978-1-5090-2176-5",

series = "IEEE ICIP Proceedings Series",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4547--4551",

booktitle = "2017 IEEE International Conference on Image Processing (ICIP)",

address = "United States",

note = "2017 IEEE International Conference on Image Processing, ICIP 2017 ; Conference date: 17-09-2017 Through 20-09-2017",

url = "http://2017.ieeeicip.org/",

}

Liu, B, Cai, H, Ji, X & Liu, H 2018, Human-human interaction recognition based on spatial and motion trend feature. in 2017 IEEE International Conference on Image Processing (ICIP). IEEE ICIP Proceedings Series, Institute of Electrical and Electronics Engineers Inc., pp. 4547-4551, 2017 IEEE International Conference on Image Processing, Beijing, China, 17/09/17. https://doi.org/10.1109/ICIP.2017.8297143

Human-human interaction recognition based on spatial and motion trend feature. / Liu, Bangli; Cai, Haibin; Ji, Xiaofei et al.
2017 IEEE International Conference on Image Processing (ICIP). Institute of Electrical and Electronics Engineers Inc., 2018. p. 4547-4551 (IEEE ICIP Proceedings Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Human-human interaction recognition based on spatial and motion trend feature

AU - Liu, Bangli

AU - Cai, Haibin

AU - Ji, Xiaofei

AU - Liu, Honghai

PY - 2018/2/22

Y1 - 2018/2/22

N2 - Human-human interaction recognition has attracted increasing attention in recent years due to its wide applications in computer vision fields. Currently there are few publicly available RGBD-based human-human interaction datasets collected. This paper introduces a new dataset for human-human interaction recognition. Furthermore, a novel feature descriptor based on spatial relationship and semantic motion trend similarity between body parts is proposed for human-human interaction recognition. The motion trend of each skeleton joint is firstly quantified into the specific semantic word and then a Kernel is built for measuring the similarity of either intra or inter body parts by histogram interaction. Finally, the proposed feature descriptor is evaluated on the SBU interaction dataset and the collected dataset. Experimental results demonstrate the outperformance of our method over the state-of-the-art methods.

AB - Human-human interaction recognition has attracted increasing attention in recent years due to its wide applications in computer vision fields. Currently there are few publicly available RGBD-based human-human interaction datasets collected. This paper introduces a new dataset for human-human interaction recognition. Furthermore, a novel feature descriptor based on spatial relationship and semantic motion trend similarity between body parts is proposed for human-human interaction recognition. The motion trend of each skeleton joint is firstly quantified into the specific semantic word and then a Kernel is built for measuring the similarity of either intra or inter body parts by histogram interaction. Finally, the proposed feature descriptor is evaluated on the SBU interaction dataset and the collected dataset. Experimental results demonstrate the outperformance of our method over the state-of-the-art methods.

U2 - 10.1109/ICIP.2017.8297143

DO - 10.1109/ICIP.2017.8297143

M3 - Conference contribution

SN - 978-1-5090-2176-5

T3 - IEEE ICIP Proceedings Series

SP - 4547

EP - 4551

BT - 2017 IEEE International Conference on Image Processing (ICIP)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE International Conference on Image Processing

Y2 - 17 September 2017 through 20 September 2017

ER -

Human-human interaction recognition based on spatial and motion trend feature

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this