Video anomaly detection based on wake motion descriptors and perspective grids

Roberto Leyva, Victor Sanchez, Chang Tsun Li

Research output: Book chapter/Published conference paperConference paper

8 Citations (Scopus)

Abstract

This paper proposes a video anomaly detection method based on wake motion descriptors. The method analyses the motion characteristics of the video data, on a video volume-by-video volume basis, by computing the wake left behind by moving objects in the scene. It then probabilistically identifies those never previously seen motion patterns in order to detect anomalies. The method also considers the perspective of the scene to compensate for the relative change in an object's size introduced by the camera's view angle. To this end, a perspective grid is proposed to define the size of video volumes for anomaly detection. Evaluation results against several state-of-the-art methods show that the proposed method attains high detection accuracies and competitive computational time.
Original languageEnglish
Title of host publicationProceedings of the 2014 IEEE International Workshop on Information Forensics and Security, WIFS 2014
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages209-214
Number of pages6
ISBN (Electronic)9781479988822
DOIs
Publication statusPublished - 2014
Event2014 IEEE International Workshop on Information Forensics and Security - Georgia Tech Hotel & Conference Centre, Atlanta, United States
Duration: 03 Dec 201405 Dec 2014
https://web.archive.org/web/20140718162151/http://ieeewifs.org/

Conference

Conference2014 IEEE International Workshop on Information Forensics and Security
CountryUnited States
CityAtlanta
Period03/12/1405/12/14
OtherThe IEEE International Workshop on Information Forensics and Security (WIFS) is the primary annual event organized by the IEEE Signal Processing Society?s Information Forensics and Security Technical Committee. The objective of WIFS is to provide the most prominent venue for researchers to exchange ideas and identify potential areas of collaboration. WIFS?14 will feature keynotes, tutorials, special sessions, and lecture & poster sessions. For the first time ever, WIFS is being organized with IEEE GlobalSIP, giving the WIFS community the opportunity to attend a rich selection of research symposia in addition to WIFS.
Internet address

Fingerprint

Cameras
Grid
Anomaly detection
Evaluation
Anomaly

Cite this

Leyva, R., Sanchez, V., & Li, C. T. (2014). Video anomaly detection based on wake motion descriptors and perspective grids. In Proceedings of the 2014 IEEE International Workshop on Information Forensics and Security, WIFS 2014 (pp. 209-214). [7084329] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/WIFS.2014.7084329
Leyva, Roberto ; Sanchez, Victor ; Li, Chang Tsun. / Video anomaly detection based on wake motion descriptors and perspective grids. Proceedings of the 2014 IEEE International Workshop on Information Forensics and Security, WIFS 2014. IEEE, Institute of Electrical and Electronics Engineers, 2014. pp. 209-214
@inproceedings{4824ae5370524c3bb8aceca6a32ab996,
title = "Video anomaly detection based on wake motion descriptors and perspective grids",
abstract = "This paper proposes a video anomaly detection method based on wake motion descriptors. The method analyses the motion characteristics of the video data, on a video volume-by-video volume basis, by computing the wake left behind by moving objects in the scene. It then probabilistically identifies those never previously seen motion patterns in order to detect anomalies. The method also considers the perspective of the scene to compensate for the relative change in an object's size introduced by the camera's view angle. To this end, a perspective grid is proposed to define the size of video volumes for anomaly detection. Evaluation results against several state-of-the-art methods show that the proposed method attains high detection accuracies and competitive computational time.",
keywords = "anomaly detection, spatio temporal video volumes, Video surveillance, wake motion descriptor",
author = "Roberto Leyva and Victor Sanchez and Li, {Chang Tsun}",
year = "2014",
doi = "10.1109/WIFS.2014.7084329",
language = "English",
pages = "209--214",
booktitle = "Proceedings of the 2014 IEEE International Workshop on Information Forensics and Security, WIFS 2014",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Leyva, R, Sanchez, V & Li, CT 2014, Video anomaly detection based on wake motion descriptors and perspective grids. in Proceedings of the 2014 IEEE International Workshop on Information Forensics and Security, WIFS 2014., 7084329, IEEE, Institute of Electrical and Electronics Engineers, pp. 209-214, 2014 IEEE International Workshop on Information Forensics and Security, Atlanta, United States, 03/12/14. https://doi.org/10.1109/WIFS.2014.7084329

Video anomaly detection based on wake motion descriptors and perspective grids. / Leyva, Roberto; Sanchez, Victor; Li, Chang Tsun.

Proceedings of the 2014 IEEE International Workshop on Information Forensics and Security, WIFS 2014. IEEE, Institute of Electrical and Electronics Engineers, 2014. p. 209-214 7084329.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - Video anomaly detection based on wake motion descriptors and perspective grids

AU - Leyva, Roberto

AU - Sanchez, Victor

AU - Li, Chang Tsun

PY - 2014

Y1 - 2014

N2 - This paper proposes a video anomaly detection method based on wake motion descriptors. The method analyses the motion characteristics of the video data, on a video volume-by-video volume basis, by computing the wake left behind by moving objects in the scene. It then probabilistically identifies those never previously seen motion patterns in order to detect anomalies. The method also considers the perspective of the scene to compensate for the relative change in an object's size introduced by the camera's view angle. To this end, a perspective grid is proposed to define the size of video volumes for anomaly detection. Evaluation results against several state-of-the-art methods show that the proposed method attains high detection accuracies and competitive computational time.

AB - This paper proposes a video anomaly detection method based on wake motion descriptors. The method analyses the motion characteristics of the video data, on a video volume-by-video volume basis, by computing the wake left behind by moving objects in the scene. It then probabilistically identifies those never previously seen motion patterns in order to detect anomalies. The method also considers the perspective of the scene to compensate for the relative change in an object's size introduced by the camera's view angle. To this end, a perspective grid is proposed to define the size of video volumes for anomaly detection. Evaluation results against several state-of-the-art methods show that the proposed method attains high detection accuracies and competitive computational time.

KW - anomaly detection

KW - spatio temporal video volumes

KW - Video surveillance

KW - wake motion descriptor

UR - http://www.scopus.com/inward/record.url?scp=84988281730&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988281730&partnerID=8YFLogxK

U2 - 10.1109/WIFS.2014.7084329

DO - 10.1109/WIFS.2014.7084329

M3 - Conference paper

AN - SCOPUS:84988281730

SP - 209

EP - 214

BT - Proceedings of the 2014 IEEE International Workshop on Information Forensics and Security, WIFS 2014

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Leyva R, Sanchez V, Li CT. Video anomaly detection based on wake motion descriptors and perspective grids. In Proceedings of the 2014 IEEE International Workshop on Information Forensics and Security, WIFS 2014. IEEE, Institute of Electrical and Electronics Engineers. 2014. p. 209-214. 7084329 https://doi.org/10.1109/WIFS.2014.7084329