Next Article in Journal
Systematic Performance Evaluation of a Novel Optimized Differential Localization Method for Capsule Endoscopes
Previous Article in Journal
Dielectric Spectroscopy Based Detection of Specific and Nonspecific Cellular Mechanisms
Previous Article in Special Issue
Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification
Open AccessArticle

Multi-Channel Generative Framework and Supervised Learning for Anomaly Detection in Surveillance Videos

1
CERI SN, IMT Lille Douai, 941 Rue Charles Bourseul, 59500 Douai, France
2
COSYS Department, LEOST, Gustave Eiffel University, 59666 Villeneuve d’Ascq, France
3
Opto-Acoustic-Electronics Department, IEMN, CNRS, UMR 8520, Université Polytechnique Hauts de France, 59313 Valenciennes, France
*
Author to whom correspondence should be addressed.
Academic Editors: Fakhreddine Ababsa and Cyrille Migniot
Sensors 2021, 21(9), 3179; https://doi.org/10.3390/s21093179
Received: 23 March 2021 / Revised: 26 April 2021 / Accepted: 30 April 2021 / Published: 3 May 2021
(This article belongs to the Special Issue Human Activity Recognition Based on Image Sensors and Deep Learning)
Recently, most state-of-the-art anomaly detection methods are based on apparent motion and appearance reconstruction networks and use error estimation between generated and real information as detection features. These approaches achieve promising results by only using normal samples for training steps. In this paper, our contributions are two-fold. On the one hand, we propose a flexible multi-channel framework to generate multi-type frame-level features. On the other hand, we study how it is possible to improve the detection performance by supervised learning. The multi-channel framework is based on four Conditional GANs (CGANs) taking various type of appearance and motion information as input and producing prediction information as output. These CGANs provide a better feature space to represent the distinction between normal and abnormal events. Then, the difference between those generative and ground-truth information is encoded by Peak Signal-to-Noise Ratio (PSNR). We propose to classify those features in a classical supervised scenario by building a small training set with some abnormal samples of the original test set of the dataset. The binary Support Vector Machine (SVM) is applied for frame-level anomaly detection. Finally, we use Mask R-CNN as detector to perform object-centric anomaly localization. Our solution is largely evaluated on Avenue, Ped1, Ped2, and ShanghaiTech datasets. Our experiment results demonstrate that PSNR features combined with supervised SVM are better than error maps computed by previous methods. We achieve state-of-the-art performance for frame-level AUC on Ped1 and ShanghaiTech. Especially, for the most challenging Shanghaitech dataset, a supervised training model outperforms up to 9% the state-of-the-art an unsupervised strategy. View Full-Text
Keywords: anomaly detection; deep learning; generative model; Conditional GAN; supervised learning; video processing; transportation application anomaly detection; deep learning; generative model; Conditional GAN; supervised learning; video processing; transportation application
Show Figures

Figure 1

MDPI and ACS Style

Vu, T.-H.; Boonaert, J.; Ambellouis, S.; Taleb-Ahmed, A. Multi-Channel Generative Framework and Supervised Learning for Anomaly Detection in Surveillance Videos. Sensors 2021, 21, 3179. https://doi.org/10.3390/s21093179

AMA Style

Vu T-H, Boonaert J, Ambellouis S, Taleb-Ahmed A. Multi-Channel Generative Framework and Supervised Learning for Anomaly Detection in Surveillance Videos. Sensors. 2021; 21(9):3179. https://doi.org/10.3390/s21093179

Chicago/Turabian Style

Vu, Tuan-Hung; Boonaert, Jacques; Ambellouis, Sebastien; Taleb-Ahmed, Abdelmalik. 2021. "Multi-Channel Generative Framework and Supervised Learning for Anomaly Detection in Surveillance Videos" Sensors 21, no. 9: 3179. https://doi.org/10.3390/s21093179

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop