Human abnormal behavior detection based on RGBD video’s skeleton information entropy

Ziyang Bian; Tingfa Xu; Chang Su; Xuan Luo

doi:10.1007/978-3-662-49831-6_74

Human abnormal behavior detection based on RGBD video’s skeleton information entropy

Ziyang Bian, Tingfa Xu^*, Chang Su, Xuan Luo

^*Corresponding author for this work

School of Optics and Photonics

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

Abstract

Conventional human abnormal behavior detection is mostly done in videos taken by visible-light cameras, and it is usually designed for a certain task. In order to solve the human abnormal behavior detection problem in general situation, this paper proposes a detection algorithm based on skeleton information entropy, by using the information from RGBD videos. In this paper, we assume that abnormal behavior is disordered. To sample the accurate features of human, we use RGBD cameras to get the skeleton information. Then, we analyze the information entropy of the angles of the skeleton, and find that the values of the information entropy are significantly higher in abnormal videos than in normal videos. The methods are tested in our database taken by Kinect in our lab and we present superior results whose recall is 92% and precision is 95.83%, and accuracy is 94%.

Original language	English
Title of host publication	Proceedings of the 2015 International Conference on Communications, Signal Processing, and Systems
Editors	Jiasong Mu, Wei Wang, Baoju Zhang, Qilian Liang
Publisher	Springer Verlag
Pages	715-723
Number of pages	9
ISBN (Print)	9783662498293
DOIs	https://doi.org/10.1007/978-3-662-49831-6_74
Publication status	Published - 2016
Event	4th International Conference on Communications, Signal Processing, and Systems, CSPS 2015 - Chengdu, Sichuan, China Duration: 23 Oct 2015 → 24 Oct 2015

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	386
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	4th International Conference on Communications, Signal Processing, and Systems, CSPS 2015
Country/Territory	China
City	Chengdu, Sichuan
Period	23/10/15 → 24/10/15

Keywords

Human abnormal behavior detection
Information entropy
RGBD video

Access to Document

10.1007/978-3-662-49831-6_74

Cite this

Bian, Z., Xu, T., Su, C., & Luo, X. (2016). Human abnormal behavior detection based on RGBD video’s skeleton information entropy. In J. Mu, W. Wang, B. Zhang, & Q. Liang (Eds.), Proceedings of the 2015 International Conference on Communications, Signal Processing, and Systems (pp. 715-723). (Lecture Notes in Electrical Engineering; Vol. 386). Springer Verlag. https://doi.org/10.1007/978-3-662-49831-6_74

Bian, Ziyang ; Xu, Tingfa ; Su, Chang et al. / Human abnormal behavior detection based on RGBD video’s skeleton information entropy. Proceedings of the 2015 International Conference on Communications, Signal Processing, and Systems. editor / Jiasong Mu ; Wei Wang ; Baoju Zhang ; Qilian Liang. Springer Verlag, 2016. pp. 715-723 (Lecture Notes in Electrical Engineering).

@inproceedings{408611dbe81e439da9c9d63077d7547d,

title = "Human abnormal behavior detection based on RGBD video{\textquoteright}s skeleton information entropy",

abstract = "Conventional human abnormal behavior detection is mostly done in videos taken by visible-light cameras, and it is usually designed for a certain task. In order to solve the human abnormal behavior detection problem in general situation, this paper proposes a detection algorithm based on skeleton information entropy, by using the information from RGBD videos. In this paper, we assume that abnormal behavior is disordered. To sample the accurate features of human, we use RGBD cameras to get the skeleton information. Then, we analyze the information entropy of the angles of the skeleton, and find that the values of the information entropy are significantly higher in abnormal videos than in normal videos. The methods are tested in our database taken by Kinect in our lab and we present superior results whose recall is 92% and precision is 95.83%, and accuracy is 94%.",

keywords = "Human abnormal behavior detection, Information entropy, RGBD video",

author = "Ziyang Bian and Tingfa Xu and Chang Su and Xuan Luo",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2016.; 4th International Conference on Communications, Signal Processing, and Systems, CSPS 2015 ; Conference date: 23-10-2015 Through 24-10-2015",

year = "2016",

doi = "10.1007/978-3-662-49831-6_74",

language = "English",

isbn = "9783662498293",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Verlag",

pages = "715--723",

editor = "Jiasong Mu and Wei Wang and Baoju Zhang and Qilian Liang",

booktitle = "Proceedings of the 2015 International Conference on Communications, Signal Processing, and Systems",

address = "Germany",

}

Bian, Z, Xu, T, Su, C & Luo, X 2016, Human abnormal behavior detection based on RGBD video’s skeleton information entropy. in J Mu, W Wang, B Zhang & Q Liang (eds), Proceedings of the 2015 International Conference on Communications, Signal Processing, and Systems. Lecture Notes in Electrical Engineering, vol. 386, Springer Verlag, pp. 715-723, 4th International Conference on Communications, Signal Processing, and Systems, CSPS 2015, Chengdu, Sichuan, China, 23/10/15. https://doi.org/10.1007/978-3-662-49831-6_74

Human abnormal behavior detection based on RGBD video’s skeleton information entropy. / Bian, Ziyang; Xu, Tingfa; Su, Chang et al.
Proceedings of the 2015 International Conference on Communications, Signal Processing, and Systems. ed. / Jiasong Mu; Wei Wang; Baoju Zhang; Qilian Liang. Springer Verlag, 2016. p. 715-723 (Lecture Notes in Electrical Engineering; Vol. 386).

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

TY - GEN

T1 - Human abnormal behavior detection based on RGBD video’s skeleton information entropy

AU - Bian, Ziyang

AU - Xu, Tingfa

AU - Su, Chang

AU - Luo, Xuan

N1 - Publisher Copyright: © Springer-Verlag Berlin Heidelberg 2016.

PY - 2016

Y1 - 2016

N2 - Conventional human abnormal behavior detection is mostly done in videos taken by visible-light cameras, and it is usually designed for a certain task. In order to solve the human abnormal behavior detection problem in general situation, this paper proposes a detection algorithm based on skeleton information entropy, by using the information from RGBD videos. In this paper, we assume that abnormal behavior is disordered. To sample the accurate features of human, we use RGBD cameras to get the skeleton information. Then, we analyze the information entropy of the angles of the skeleton, and find that the values of the information entropy are significantly higher in abnormal videos than in normal videos. The methods are tested in our database taken by Kinect in our lab and we present superior results whose recall is 92% and precision is 95.83%, and accuracy is 94%.

AB - Conventional human abnormal behavior detection is mostly done in videos taken by visible-light cameras, and it is usually designed for a certain task. In order to solve the human abnormal behavior detection problem in general situation, this paper proposes a detection algorithm based on skeleton information entropy, by using the information from RGBD videos. In this paper, we assume that abnormal behavior is disordered. To sample the accurate features of human, we use RGBD cameras to get the skeleton information. Then, we analyze the information entropy of the angles of the skeleton, and find that the values of the information entropy are significantly higher in abnormal videos than in normal videos. The methods are tested in our database taken by Kinect in our lab and we present superior results whose recall is 92% and precision is 95.83%, and accuracy is 94%.

KW - Human abnormal behavior detection

KW - Information entropy

KW - RGBD video

UR - http://www.scopus.com/inward/record.url?scp=84978286065&partnerID=8YFLogxK

U2 - 10.1007/978-3-662-49831-6_74

DO - 10.1007/978-3-662-49831-6_74

M3 - Conference contribution

AN - SCOPUS:84978286065

SN - 9783662498293

T3 - Lecture Notes in Electrical Engineering

SP - 715

EP - 723

BT - Proceedings of the 2015 International Conference on Communications, Signal Processing, and Systems

A2 - Mu, Jiasong

A2 - Wang, Wei

A2 - Zhang, Baoju

A2 - Liang, Qilian

PB - Springer Verlag

T2 - 4th International Conference on Communications, Signal Processing, and Systems, CSPS 2015

Y2 - 23 October 2015 through 24 October 2015

ER -

Bian Z, Xu T, Su C, Luo X. Human abnormal behavior detection based on RGBD video’s skeleton information entropy. In Mu J, Wang W, Zhang B, Liang Q, editors, Proceedings of the 2015 International Conference on Communications, Signal Processing, and Systems. Springer Verlag. 2016. p. 715-723. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-3-662-49831-6_74

Human abnormal behavior detection based on RGBD video’s skeleton information entropy

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this