Abnormal activity recognition in office based on ℜ transform

Ying Wang; Kaiqi Huang; Tieniu Tan

doi:10.1109/ICIP.2007.4378961

Abnormal activity recognition in office based on ℜ transform

Ying Wang^*, Kaiqi Huang, Tieniu Tan

^*Corresponding author for this work

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

23 Citations (Scopus)

Abstract

This paper introduces an abnormal activity recognition method based on a new feature descriptor for human silhouette. For a binary human silhouette, an extended radon transform, ℜ transform, is employed to represent low-level features. The information that the initial silhouette carries is transformed in a compact way preserving important spatial information of the activities. Then a set of HMMs based on the features extracted by our method are trained to recognize abnormal activities. Experiments have proved the accuracy and efficiency of the proposed method, and the comparison with Fourier descriptor illustrates its robustness to disjoint shapes and shapes with holes.

Original language	English
Title of host publication	2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	341-344
Number of pages	4
Volume	1
ISBN (Print)	1424414377, 9781424414376
DOIs	https://doi.org/10.1109/ICIP.2007.4378961
Publication status	Published - 2006
Externally published	Yes
Event	14th IEEE International Conference on Image Processing, ICIP 2007 - San Antonio, TX, United States Duration: 16 Sep 2007 → 19 Sep 2007

Other

Other	14th IEEE International Conference on Image Processing, ICIP 2007
Country/Territory	United States
City	San Antonio, TX
Period	16/09/07 → 19/09/07

Keywords

ℜ
Abnormality recognition
Feature descriptor
HMM
Surveillance
Transform

Access to Document

10.1109/ICIP.2007.4378961

Cite this

@inproceedings{d5662a604d004b04b470e0ecf168a296,

title = "Abnormal activity recognition in office based on ℜ transform",

abstract = "This paper introduces an abnormal activity recognition method based on a new feature descriptor for human silhouette. For a binary human silhouette, an extended radon transform, ℜ transform, is employed to represent low-level features. The information that the initial silhouette carries is transformed in a compact way preserving important spatial information of the activities. Then a set of HMMs based on the features extracted by our method are trained to recognize abnormal activities. Experiments have proved the accuracy and efficiency of the proposed method, and the comparison with Fourier descriptor illustrates its robustness to disjoint shapes and shapes with holes.",

keywords = "ℜ, Abnormality recognition, Feature descriptor, HMM, Surveillance, Transform",

author = "Ying Wang and Kaiqi Huang and Tieniu Tan",

year = "2006",

doi = "10.1109/ICIP.2007.4378961",

language = "English",

isbn = "1424414377",

volume = "1",

pages = "341--344",

booktitle = "2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "14th IEEE International Conference on Image Processing, ICIP 2007 ; Conference date: 16-09-2007 Through 19-09-2007",

}

Wang, Y, Huang, K & Tan, T 2006, Abnormal activity recognition in office based on ℜ transform. in 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. vol. 1, 4378961, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 341-344, 14th IEEE International Conference on Image Processing, ICIP 2007, San Antonio, TX, United States, 16/09/07. https://doi.org/10.1109/ICIP.2007.4378961

Abnormal activity recognition in office based on ℜ transform. / Wang, Ying; Huang, Kaiqi; Tan, Tieniu.

2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. Vol. 1 Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2006. p. 341-344 4378961.

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

TY - GEN

T1 - Abnormal activity recognition in office based on ℜ transform

AU - Wang, Ying

AU - Huang, Kaiqi

AU - Tan, Tieniu

PY - 2006

Y1 - 2006

N2 - This paper introduces an abnormal activity recognition method based on a new feature descriptor for human silhouette. For a binary human silhouette, an extended radon transform, ℜ transform, is employed to represent low-level features. The information that the initial silhouette carries is transformed in a compact way preserving important spatial information of the activities. Then a set of HMMs based on the features extracted by our method are trained to recognize abnormal activities. Experiments have proved the accuracy and efficiency of the proposed method, and the comparison with Fourier descriptor illustrates its robustness to disjoint shapes and shapes with holes.

AB - This paper introduces an abnormal activity recognition method based on a new feature descriptor for human silhouette. For a binary human silhouette, an extended radon transform, ℜ transform, is employed to represent low-level features. The information that the initial silhouette carries is transformed in a compact way preserving important spatial information of the activities. Then a set of HMMs based on the features extracted by our method are trained to recognize abnormal activities. Experiments have proved the accuracy and efficiency of the proposed method, and the comparison with Fourier descriptor illustrates its robustness to disjoint shapes and shapes with holes.

KW - ℜ

KW - Abnormality recognition

KW - Feature descriptor

KW - HMM

KW - Surveillance

KW - Transform

UR - http://www.scopus.com/inward/record.url?scp=48149085384&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2007.4378961

DO - 10.1109/ICIP.2007.4378961

M3 - Conference proceeding contribution

AN - SCOPUS:48149085384

SN - 1424414377

SN - 9781424414376

VL - 1

SP - 341

EP - 344

BT - 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

T2 - 14th IEEE International Conference on Image Processing, ICIP 2007

Y2 - 16 September 2007 through 19 September 2007

ER -

Abnormal activity recognition in office based on ℜ transform

Abstract

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this