Human action recognition based on action forests model using kinect camera

Chi Hung Chuan; Ying Nong Chen; Kuo Chin Fan

doi:10.1109/WAINA.2016.14

Human action recognition based on action forests model using kinect camera

Chi Hung Chuan, Ying Nong Chen, Kuo Chin Fan

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

8 Scopus citations

Abstract

Human action recognition is one of the most important issues in computer vision. In this paper, the main idea is to design a general approach to recognize the human behavior. This approach is based on a pre-collected action database, which extracted by the depth images and forms the sequences of skeletons, and trained by the proposed Action Forests (AF) model. AF extends the random forest algorithm by using different decision functions to fit the skeletal features in 3D space. The system achieves the real-time classification result without the limitation of background and camera position. In the experiments, we collected several human behavior with single-character actions and two-character interactions to train the AF model. The skeleton features were retrieved from the depth sensor Kinect. We investigated the effect of several training parameters in AF. In conclusion, AF can learn the skeletal features efficiently and runs at 30 frames per second on action classification with high accuracy.

Original language	English
Title of host publication	Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016
Editors	Antonio J. Jara, Makoto Takizawa, Yann Bocchi, Leonard Barolli, Tomoya Enokido
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	914-917
Number of pages	4
ISBN (Electronic)	9781509018574
DOIs	https://doi.org/10.1109/WAINA.2016.14
State	Published - 17 May 2016
Event	30th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016 - Crans-Montana, Switzerland Duration: 23 Mar 2016 → 25 Mar 2016

Publication series

Name	Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016

Conference

Conference	30th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016
Country/Territory	Switzerland
City	Crans-Montana
Period	23/03/16 → 25/03/16

Keywords

Action forests
Action recognition
Depth image
Kinect
Random forests

Access to Document

10.1109/WAINA.2016.14

Cite this

Chuan, C. H., Chen, Y. N., & Fan, K. C. (2016). Human action recognition based on action forests model using kinect camera. In A. J. Jara, M. Takizawa, Y. Bocchi, L. Barolli, & T. Enokido (Eds.), Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016 (pp. 914-917). Article 7471320 (Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WAINA.2016.14

Chuan, Chi Hung ; Chen, Ying Nong ; Fan, Kuo Chin. / Human action recognition based on action forests model using kinect camera. Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016. editor / Antonio J. Jara ; Makoto Takizawa ; Yann Bocchi ; Leonard Barolli ; Tomoya Enokido. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 914-917 (Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016).

@inproceedings{308df32002874bc0a3472fdf5f53bb6a,

title = "Human action recognition based on action forests model using kinect camera",

abstract = "Human action recognition is one of the most important issues in computer vision. In this paper, the main idea is to design a general approach to recognize the human behavior. This approach is based on a pre-collected action database, which extracted by the depth images and forms the sequences of skeletons, and trained by the proposed Action Forests (AF) model. AF extends the random forest algorithm by using different decision functions to fit the skeletal features in 3D space. The system achieves the real-time classification result without the limitation of background and camera position. In the experiments, we collected several human behavior with single-character actions and two-character interactions to train the AF model. The skeleton features were retrieved from the depth sensor Kinect. We investigated the effect of several training parameters in AF. In conclusion, AF can learn the skeletal features efficiently and runs at 30 frames per second on action classification with high accuracy.",

keywords = "Action forests, Action recognition, Depth image, Kinect, Random forests",

author = "Chuan, {Chi Hung} and Chen, {Ying Nong} and Fan, {Kuo Chin}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 30th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016 ; Conference date: 23-03-2016 Through 25-03-2016",

year = "2016",

month = may,

day = "17",

doi = "10.1109/WAINA.2016.14",

language = "???core.languages.en_GB???",

series = "Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016",

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

pages = "914--917",

editor = "Jara, {Antonio J.} and Makoto Takizawa and Yann Bocchi and Leonard Barolli and Tomoya Enokido",

booktitle = "Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016",

}

Chuan, CH, Chen, YN & Fan, KC 2016, Human action recognition based on action forests model using kinect camera. in AJ Jara, M Takizawa, Y Bocchi, L Barolli & T Enokido (eds), Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016., 7471320, Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016, Institute of Electrical and Electronics Engineers Inc., pp. 914-917, 30th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016, Crans-Montana, Switzerland, 23/03/16. https://doi.org/10.1109/WAINA.2016.14

Human action recognition based on action forests model using kinect camera. / Chuan, Chi Hung; Chen, Ying Nong ; Fan, Kuo Chin.
Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016. ed. / Antonio J. Jara; Makoto Takizawa; Yann Bocchi; Leonard Barolli; Tomoya Enokido. Institute of Electrical and Electronics Engineers Inc., 2016. p. 914-917 7471320 (Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016).

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

TY - GEN

T1 - Human action recognition based on action forests model using kinect camera

AU - Chuan, Chi Hung

AU - Chen, Ying Nong

AU - Fan, Kuo Chin

PY - 2016/5/17

Y1 - 2016/5/17

N2 - Human action recognition is one of the most important issues in computer vision. In this paper, the main idea is to design a general approach to recognize the human behavior. This approach is based on a pre-collected action database, which extracted by the depth images and forms the sequences of skeletons, and trained by the proposed Action Forests (AF) model. AF extends the random forest algorithm by using different decision functions to fit the skeletal features in 3D space. The system achieves the real-time classification result without the limitation of background and camera position. In the experiments, we collected several human behavior with single-character actions and two-character interactions to train the AF model. The skeleton features were retrieved from the depth sensor Kinect. We investigated the effect of several training parameters in AF. In conclusion, AF can learn the skeletal features efficiently and runs at 30 frames per second on action classification with high accuracy.

AB - Human action recognition is one of the most important issues in computer vision. In this paper, the main idea is to design a general approach to recognize the human behavior. This approach is based on a pre-collected action database, which extracted by the depth images and forms the sequences of skeletons, and trained by the proposed Action Forests (AF) model. AF extends the random forest algorithm by using different decision functions to fit the skeletal features in 3D space. The system achieves the real-time classification result without the limitation of background and camera position. In the experiments, we collected several human behavior with single-character actions and two-character interactions to train the AF model. The skeleton features were retrieved from the depth sensor Kinect. We investigated the effect of several training parameters in AF. In conclusion, AF can learn the skeletal features efficiently and runs at 30 frames per second on action classification with high accuracy.

KW - Action forests

KW - Action recognition

KW - Depth image

KW - Kinect

KW - Random forests

UR - http://www.scopus.com/inward/record.url?scp=84983564557&partnerID=8YFLogxK

U2 - 10.1109/WAINA.2016.14

DO - 10.1109/WAINA.2016.14

M3 - 會議論文篇章

AN - SCOPUS:84983564557

T3 - Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016

SP - 914

EP - 917

BT - Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016

A2 - Jara, Antonio J.

A2 - Takizawa, Makoto

A2 - Bocchi, Yann

A2 - Barolli, Leonard

A2 - Enokido, Tomoya

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 30th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016

Y2 - 23 March 2016 through 25 March 2016

ER -

Chuan CH, Chen YN , Fan KC. Human action recognition based on action forests model using kinect camera. In Jara AJ, Takizawa M, Bocchi Y, Barolli L, Enokido T, editors, Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 914-917. 7471320. (Proceedings - IEEE 30th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2016). doi: 10.1109/WAINA.2016.14

Human action recognition based on action forests model using kinect camera

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this