Action recognition based on depth image sequence

Liangcan Liao; Guitao Cao; Wenming Cao

doi:10.1109/BIBM.2017.8217896

Action recognition based on depth image sequence

Liangcan Liao
, Guitao Cao
, Wenming Cao

Software Engineering Institute

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

5 Scopus citations

Abstract

Human action recognition is the process of labeling image sequences with action labels. Robust solutions to this problem have applications in domains such as medical care, human-computer interaction and virtual training. The task is challenging for feature extraction due to variations in motion performance, recording settings and inter-personal differences. To meet these challenges, we propose two types of feature extraction methods based on the Kinect depth image sequences in this paper. One is assuming that there exists even distribute position lines in the three-dimensional space of frame difference, it will be active when the moving object touches them. The other is mapping the 16 successive frame sequences to a single image by Speed Time Mapping (STM) or Time Depth Mapping (STDM), obtaining 36-dimensiona spatial-temporal features in this image. These features are fed into Support Vector Machine (SVM) to identify the action categories. The experiments compare their performance and demonstrate the effectiveness of STDM.

Original language	English
Title of host publication	Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017
Editors	Illhoi Yoo, Jane Huiru Zheng, Yang Gong, Xiaohua Tony Hu, Chi-Ren Shyu, Yana Bromberg, Jean Gao, Dmitry Korkin
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1583-1587
Number of pages	5
ISBN (Electronic)	9781509030491
DOIs	https://doi.org/10.1109/BIBM.2017.8217896
State	Published - 15 Dec 2017
Event	2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017 - Kansas City, United States Duration: 13 Nov 2017 → 16 Nov 2017

Publication series

Name	Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017
Volume	2017-January

Conference

Conference	2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017
Country/Territory	United States
City	Kansas City
Period	13/11/17 → 16/11/17

Keywords

Action recognition
Depth image
Feature extraction
Kinect
SVM

Access to Document

10.1109/BIBM.2017.8217896

Cite this

Liao, L., Cao, G., & Cao, W. (2017). Action recognition based on depth image sequence. In I. Yoo, J. H. Zheng, Y. Gong, X. T. Hu, C.-R. Shyu, Y. Bromberg, J. Gao, & D. Korkin (Eds.), Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017 (pp. 1583-1587). (Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2017.8217896

Liao, Liangcan ; Cao, Guitao ; Cao, Wenming. / Action recognition based on depth image sequence. Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. editor / Illhoi Yoo ; Jane Huiru Zheng ; Yang Gong ; Xiaohua Tony Hu ; Chi-Ren Shyu ; Yana Bromberg ; Jean Gao ; Dmitry Korkin. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1583-1587 (Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017).

@inproceedings{e2418aa2ee074e0aa89ebdd6c7f693ac,

title = "Action recognition based on depth image sequence",

abstract = "Human action recognition is the process of labeling image sequences with action labels. Robust solutions to this problem have applications in domains such as medical care, human-computer interaction and virtual training. The task is challenging for feature extraction due to variations in motion performance, recording settings and inter-personal differences. To meet these challenges, we propose two types of feature extraction methods based on the Kinect depth image sequences in this paper. One is assuming that there exists even distribute position lines in the three-dimensional space of frame difference, it will be active when the moving object touches them. The other is mapping the 16 successive frame sequences to a single image by Speed Time Mapping (STM) or Time Depth Mapping (STDM), obtaining 36-dimensiona spatial-temporal features in this image. These features are fed into Support Vector Machine (SVM) to identify the action categories. The experiments compare their performance and demonstrate the effectiveness of STDM.",

keywords = "Action recognition, Depth image, Feature extraction, Kinect, SVM",

author = "Liangcan Liao and Guitao Cao and Wenming Cao",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017 ; Conference date: 13-11-2017 Through 16-11-2017",

year = "2017",

month = dec,

day = "15",

doi = "10.1109/BIBM.2017.8217896",

language = "英语",

series = "Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017",

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

pages = "1583--1587",

editor = "Illhoi Yoo and Zheng, \{Jane Huiru\} and Yang Gong and Hu, \{Xiaohua Tony\} and Chi-Ren Shyu and Yana Bromberg and Jean Gao and Dmitry Korkin",

booktitle = "Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017",

address = "美国",

}

Liao, L, Cao, G & Cao, W 2017, Action recognition based on depth image sequence. in I Yoo, JH Zheng, Y Gong, XT Hu, C-R Shyu, Y Bromberg, J Gao & D Korkin (eds), Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 1583-1587, 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017, Kansas City, United States, 13/11/17. https://doi.org/10.1109/BIBM.2017.8217896

Action recognition based on depth image sequence. / Liao, Liangcan; Cao, Guitao; Cao, Wenming.
Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. ed. / Illhoi Yoo; Jane Huiru Zheng; Yang Gong; Xiaohua Tony Hu; Chi-Ren Shyu; Yana Bromberg; Jean Gao; Dmitry Korkin. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1583-1587 (Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017; Vol. 2017-January).

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

TY - GEN

T1 - Action recognition based on depth image sequence

AU - Liao, Liangcan

AU - Cao, Guitao

AU - Cao, Wenming

PY - 2017/12/15

Y1 - 2017/12/15

N2 - Human action recognition is the process of labeling image sequences with action labels. Robust solutions to this problem have applications in domains such as medical care, human-computer interaction and virtual training. The task is challenging for feature extraction due to variations in motion performance, recording settings and inter-personal differences. To meet these challenges, we propose two types of feature extraction methods based on the Kinect depth image sequences in this paper. One is assuming that there exists even distribute position lines in the three-dimensional space of frame difference, it will be active when the moving object touches them. The other is mapping the 16 successive frame sequences to a single image by Speed Time Mapping (STM) or Time Depth Mapping (STDM), obtaining 36-dimensiona spatial-temporal features in this image. These features are fed into Support Vector Machine (SVM) to identify the action categories. The experiments compare their performance and demonstrate the effectiveness of STDM.

AB - Human action recognition is the process of labeling image sequences with action labels. Robust solutions to this problem have applications in domains such as medical care, human-computer interaction and virtual training. The task is challenging for feature extraction due to variations in motion performance, recording settings and inter-personal differences. To meet these challenges, we propose two types of feature extraction methods based on the Kinect depth image sequences in this paper. One is assuming that there exists even distribute position lines in the three-dimensional space of frame difference, it will be active when the moving object touches them. The other is mapping the 16 successive frame sequences to a single image by Speed Time Mapping (STM) or Time Depth Mapping (STDM), obtaining 36-dimensiona spatial-temporal features in this image. These features are fed into Support Vector Machine (SVM) to identify the action categories. The experiments compare their performance and demonstrate the effectiveness of STDM.

KW - Action recognition

KW - Depth image

KW - Feature extraction

KW - Kinect

KW - SVM

UR - https://www.scopus.com/pages/publications/85045983761

U2 - 10.1109/BIBM.2017.8217896

DO - 10.1109/BIBM.2017.8217896

M3 - 会议稿件

AN - SCOPUS:85045983761

T3 - Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017

SP - 1583

EP - 1587

BT - Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017

A2 - Yoo, Illhoi

A2 - Zheng, Jane Huiru

A2 - Gong, Yang

A2 - Hu, Xiaohua Tony

A2 - Shyu, Chi-Ren

A2 - Bromberg, Yana

A2 - Gao, Jean

A2 - Korkin, Dmitry

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017

Y2 - 13 November 2017 through 16 November 2017

ER -

Liao L, Cao G, Cao W. Action recognition based on depth image sequence. In Yoo I, Zheng JH, Gong Y, Hu XT, Shyu CR, Bromberg Y, Gao J, Korkin D, editors, Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1583-1587. (Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017). doi: 10.1109/BIBM.2017.8217896

Action recognition based on depth image sequence

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this