Cargando…

Video Anomaly Detection Based on Convolutional Recurrent AutoEncoder

As an essential task in computer vision, video anomaly detection technology is used in video surveillance, scene understanding, road traffic analysis and other fields. However, the definition of anomaly, scene change and complex background present great challenges for video anomaly detection tasks....

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Bokun, Yang, Caiqian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9230876/
https://www.ncbi.nlm.nih.gov/pubmed/35746427
http://dx.doi.org/10.3390/s22124647
_version_ 1784735181704265728
author Wang, Bokun
Yang, Caiqian
author_facet Wang, Bokun
Yang, Caiqian
author_sort Wang, Bokun
collection PubMed
description As an essential task in computer vision, video anomaly detection technology is used in video surveillance, scene understanding, road traffic analysis and other fields. However, the definition of anomaly, scene change and complex background present great challenges for video anomaly detection tasks. The insight that motivates this study is that the reconstruction error for normal samples would be lower since they are closer to the training data, while the anomalies could not be reconstructed well. In this paper, we proposed a Convolutional Recurrent AutoEncoder (CR-AE), which combines an attention-based Convolutional Long–Short-Term Memory (ConvLSTM) network and a Convolutional AutoEncoder. The ConvLSTM network and the Convolutional AutoEncoder could capture the irregularity of the temporal pattern and spatial irregularity, respectively. The attention mechanism was used to obtain the current output characteristics from the hidden state of each Covn-LSTM layer. Then, a convolutional decoder was utilized to reconstruct the input video clip and the testing video clip with higher reconstruction error, which were further judged to be anomalies. The proposed method was tested on two popular benchmarks (UCSD ped2 Dataset and Avenue Dataset), and the experimental results demonstrated that CR-AE achieved 95.6% and 73.1% frame-level AUC on two public datasets, respectively.
format Online
Article
Text
id pubmed-9230876
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-92308762022-06-25 Video Anomaly Detection Based on Convolutional Recurrent AutoEncoder Wang, Bokun Yang, Caiqian Sensors (Basel) Article As an essential task in computer vision, video anomaly detection technology is used in video surveillance, scene understanding, road traffic analysis and other fields. However, the definition of anomaly, scene change and complex background present great challenges for video anomaly detection tasks. The insight that motivates this study is that the reconstruction error for normal samples would be lower since they are closer to the training data, while the anomalies could not be reconstructed well. In this paper, we proposed a Convolutional Recurrent AutoEncoder (CR-AE), which combines an attention-based Convolutional Long–Short-Term Memory (ConvLSTM) network and a Convolutional AutoEncoder. The ConvLSTM network and the Convolutional AutoEncoder could capture the irregularity of the temporal pattern and spatial irregularity, respectively. The attention mechanism was used to obtain the current output characteristics from the hidden state of each Covn-LSTM layer. Then, a convolutional decoder was utilized to reconstruct the input video clip and the testing video clip with higher reconstruction error, which were further judged to be anomalies. The proposed method was tested on two popular benchmarks (UCSD ped2 Dataset and Avenue Dataset), and the experimental results demonstrated that CR-AE achieved 95.6% and 73.1% frame-level AUC on two public datasets, respectively. MDPI 2022-06-20 /pmc/articles/PMC9230876/ /pubmed/35746427 http://dx.doi.org/10.3390/s22124647 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Bokun
Yang, Caiqian
Video Anomaly Detection Based on Convolutional Recurrent AutoEncoder
title Video Anomaly Detection Based on Convolutional Recurrent AutoEncoder
title_full Video Anomaly Detection Based on Convolutional Recurrent AutoEncoder
title_fullStr Video Anomaly Detection Based on Convolutional Recurrent AutoEncoder
title_full_unstemmed Video Anomaly Detection Based on Convolutional Recurrent AutoEncoder
title_short Video Anomaly Detection Based on Convolutional Recurrent AutoEncoder
title_sort video anomaly detection based on convolutional recurrent autoencoder
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9230876/
https://www.ncbi.nlm.nih.gov/pubmed/35746427
http://dx.doi.org/10.3390/s22124647
work_keys_str_mv AT wangbokun videoanomalydetectionbasedonconvolutionalrecurrentautoencoder
AT yangcaiqian videoanomalydetectionbasedonconvolutionalrecurrentautoencoder