Anomaly detection in video sequences: A benchmark and computational model
Abstract Anomaly detection has attracted considerable search attention. However, existing anomaly detection databases encounter two major problems. Firstly, they are limited in scale. Secondly, training sets contain only video‐level labels indicating the existence of an abnormal event during the ful...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-12-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/ipr2.12258 |
_version_ | 1798027628115918848 |
---|---|
author | Boyang Wan Wenhui Jiang Yuming Fang Zhiyuan Luo Guanqun Ding |
author_facet | Boyang Wan Wenhui Jiang Yuming Fang Zhiyuan Luo Guanqun Ding |
author_sort | Boyang Wan |
collection | DOAJ |
description | Abstract Anomaly detection has attracted considerable search attention. However, existing anomaly detection databases encounter two major problems. Firstly, they are limited in scale. Secondly, training sets contain only video‐level labels indicating the existence of an abnormal event during the full video while lacking annotations of precise time durations. To tackle these problems, we contribute a new Large‐scale Anomaly Detection (LAD) database as the benchmark for anomaly detection in video sequences, which is featured in two aspects. 1) It contains 2000 video sequences including normal and abnormal video clips with 14 anomaly categories including crash, fire, violence etc. with large scene varieties, making it the largest anomaly analysis database to date. 2) It provides the annotation data, including video‐level labels (abnormal/normal video, anomaly type) and frame‐level labels (abnormal/normal video frame) to facilitate anomaly detection. Leveraging the above benefits from the LAD database, we further formulate anomaly detection as a fully supervised learning problem and propose a multi‐task deep neural network to solve it. We firstly obtain the local spatiotemporal contextual feature by using an Inflated 3D convolutional (I3D) network. Then we construct a recurrent convolutional neural network fed the local spatiotemporal contextual feature to extract the spatiotemporal contextual feature. With the global spatiotemporal contextual feature, the anomaly type and score can be computed simultaneously by a multi‐task neural network. Experimental results show that the proposed method outperforms the state‐of‐the‐art anomaly detection methods on our database and other public databases of anomaly detection. Supplementary materials are available at http://sim.jxufe.cn/JDMKL/ymfang/anomaly‐detection.html. |
first_indexed | 2024-04-11T18:54:30Z |
format | Article |
id | doaj.art-c060f34ff9c543b384db6115e37fb8a6 |
institution | Directory Open Access Journal |
issn | 1751-9659 1751-9667 |
language | English |
last_indexed | 2024-04-11T18:54:30Z |
publishDate | 2021-12-01 |
publisher | Wiley |
record_format | Article |
series | IET Image Processing |
spelling | doaj.art-c060f34ff9c543b384db6115e37fb8a62022-12-22T04:08:14ZengWileyIET Image Processing1751-96591751-96672021-12-0115143454346510.1049/ipr2.12258Anomaly detection in video sequences: A benchmark and computational modelBoyang Wan0Wenhui Jiang1Yuming Fang2Zhiyuan Luo3Guanqun Ding4School of Information Management Jiangxi University of Finance and Economics Nanchang ChinaSchool of Information Management Jiangxi University of Finance and Economics Nanchang ChinaSchool of Information Management Jiangxi University of Finance and Economics Nanchang ChinaSchool of Information Management Jiangxi University of Finance and Economics Nanchang ChinaSchool of Information Management Jiangxi University of Finance and Economics Nanchang ChinaAbstract Anomaly detection has attracted considerable search attention. However, existing anomaly detection databases encounter two major problems. Firstly, they are limited in scale. Secondly, training sets contain only video‐level labels indicating the existence of an abnormal event during the full video while lacking annotations of precise time durations. To tackle these problems, we contribute a new Large‐scale Anomaly Detection (LAD) database as the benchmark for anomaly detection in video sequences, which is featured in two aspects. 1) It contains 2000 video sequences including normal and abnormal video clips with 14 anomaly categories including crash, fire, violence etc. with large scene varieties, making it the largest anomaly analysis database to date. 2) It provides the annotation data, including video‐level labels (abnormal/normal video, anomaly type) and frame‐level labels (abnormal/normal video frame) to facilitate anomaly detection. Leveraging the above benefits from the LAD database, we further formulate anomaly detection as a fully supervised learning problem and propose a multi‐task deep neural network to solve it. We firstly obtain the local spatiotemporal contextual feature by using an Inflated 3D convolutional (I3D) network. Then we construct a recurrent convolutional neural network fed the local spatiotemporal contextual feature to extract the spatiotemporal contextual feature. With the global spatiotemporal contextual feature, the anomaly type and score can be computed simultaneously by a multi‐task neural network. Experimental results show that the proposed method outperforms the state‐of‐the‐art anomaly detection methods on our database and other public databases of anomaly detection. Supplementary materials are available at http://sim.jxufe.cn/JDMKL/ymfang/anomaly‐detection.html.https://doi.org/10.1049/ipr2.12258Image recognitionComputer vision and image processing techniquesVideo signal processingData handling techniquesSupervised learningNeural nets |
spellingShingle | Boyang Wan Wenhui Jiang Yuming Fang Zhiyuan Luo Guanqun Ding Anomaly detection in video sequences: A benchmark and computational model IET Image Processing Image recognition Computer vision and image processing techniques Video signal processing Data handling techniques Supervised learning Neural nets |
title | Anomaly detection in video sequences: A benchmark and computational model |
title_full | Anomaly detection in video sequences: A benchmark and computational model |
title_fullStr | Anomaly detection in video sequences: A benchmark and computational model |
title_full_unstemmed | Anomaly detection in video sequences: A benchmark and computational model |
title_short | Anomaly detection in video sequences: A benchmark and computational model |
title_sort | anomaly detection in video sequences a benchmark and computational model |
topic | Image recognition Computer vision and image processing techniques Video signal processing Data handling techniques Supervised learning Neural nets |
url | https://doi.org/10.1049/ipr2.12258 |
work_keys_str_mv | AT boyangwan anomalydetectioninvideosequencesabenchmarkandcomputationalmodel AT wenhuijiang anomalydetectioninvideosequencesabenchmarkandcomputationalmodel AT yumingfang anomalydetectioninvideosequencesabenchmarkandcomputationalmodel AT zhiyuanluo anomalydetectioninvideosequencesabenchmarkandcomputationalmodel AT guanqunding anomalydetectioninvideosequencesabenchmarkandcomputationalmodel |