Anomaly Detection in Videos Using Optical Flow and Convolutional Autoencoder
Today, public areas, such as airports, hospitals, city centers are monitored by surveillance systems. The widespread use of surveillance systems reduces security concerns while creating an amount of video data that cannot be examined by people in real-time. Therefore, the concept of automatic unders...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8936359/ |
| _version_ | 1819132976665985024 |
|---|---|
| author | Elvan Duman Osman Ayhan Erdem |
| author_facet | Elvan Duman Osman Ayhan Erdem |
| author_sort | Elvan Duman |
| collection | DOAJ |
| description | Today, public areas, such as airports, hospitals, city centers are monitored by surveillance systems. The widespread use of surveillance systems reduces security concerns while creating an amount of video data that cannot be examined by people in real-time. Therefore, the concept of automatic understanding of video activities has raised the standards of security camera systems. In this paper, we propose a framework (OF-ConvAE-LSTM) to detect anomalies using Convolutional Autoencoder and Convolutional Long Short-Term Memory in an unsupervised manner. Besides the deep learning model, the feature extraction stage based on dense optical flow is applied in the framework to obtain the velocity and direction information of foreground objects. The experiments were carried out on three popular public datasets consisting of Avenue, UCSD Ped1, and UCSD Peds2. The experimental results have shown that the proposed framework models the complex distribution of the pattern of regular motion changes with high accuracy. Besides, this method was observed to outperform state-of-the-art approaches based on unsupervised and semi-supervised deep learning models. |
| first_indexed | 2024-12-22T09:39:57Z |
| format | Article |
| id | doaj.art-db6664ad887d4415b2701096bfaf8f0c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T09:39:57Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-db6664ad887d4415b2701096bfaf8f0c2022-12-21T18:30:44ZengIEEEIEEE Access2169-35362019-01-01718391418392310.1109/ACCESS.2019.29606548936359Anomaly Detection in Videos Using Optical Flow and Convolutional AutoencoderElvan Duman0https://orcid.org/0000-0003-2247-0452Osman Ayhan Erdem1https://orcid.org/0000-0001-7761-1078Department of Computer Engineering, Technology Faculty, Gazi University, Ankara, TurkeyDepartment of Computer Engineering, Technology Faculty, Gazi University, Ankara, TurkeyToday, public areas, such as airports, hospitals, city centers are monitored by surveillance systems. The widespread use of surveillance systems reduces security concerns while creating an amount of video data that cannot be examined by people in real-time. Therefore, the concept of automatic understanding of video activities has raised the standards of security camera systems. In this paper, we propose a framework (OF-ConvAE-LSTM) to detect anomalies using Convolutional Autoencoder and Convolutional Long Short-Term Memory in an unsupervised manner. Besides the deep learning model, the feature extraction stage based on dense optical flow is applied in the framework to obtain the velocity and direction information of foreground objects. The experiments were carried out on three popular public datasets consisting of Avenue, UCSD Ped1, and UCSD Peds2. The experimental results have shown that the proposed framework models the complex distribution of the pattern of regular motion changes with high accuracy. Besides, this method was observed to outperform state-of-the-art approaches based on unsupervised and semi-supervised deep learning models.https://ieeexplore.ieee.org/document/8936359/Abnormal event detectionconvolutional autoencoderlong short-term memoryoptical flow |
| spellingShingle | Elvan Duman Osman Ayhan Erdem Anomaly Detection in Videos Using Optical Flow and Convolutional Autoencoder IEEE Access Abnormal event detection convolutional autoencoder long short-term memory optical flow |
| title | Anomaly Detection in Videos Using Optical Flow and Convolutional Autoencoder |
| title_full | Anomaly Detection in Videos Using Optical Flow and Convolutional Autoencoder |
| title_fullStr | Anomaly Detection in Videos Using Optical Flow and Convolutional Autoencoder |
| title_full_unstemmed | Anomaly Detection in Videos Using Optical Flow and Convolutional Autoencoder |
| title_short | Anomaly Detection in Videos Using Optical Flow and Convolutional Autoencoder |
| title_sort | anomaly detection in videos using optical flow and convolutional autoencoder |
| topic | Abnormal event detection convolutional autoencoder long short-term memory optical flow |
| url | https://ieeexplore.ieee.org/document/8936359/ |
| work_keys_str_mv | AT elvanduman anomalydetectioninvideosusingopticalflowandconvolutionalautoencoder AT osmanayhanerdem anomalydetectioninvideosusingopticalflowandconvolutionalautoencoder |