A comprehensive review on deep learning-based methods for video anomaly detection

Surveillance video anomaly detection via non-local U-Net frame prediction

A semi-supervised deep learning based video anomaly detection framework using RGB-D for surveillance of real-world critical environments

An automated teller machine is an electronics telecommunications device which is utilized by people, mostly to withdraw money. In the present scenario, a fair amount of the population using an ATM machine to withdraw cash are facing a problem of robberies and theft due to lack of security guards. Surveillance cameras being used in the ATM cells, however monitoring capabilities of law enforcement agencies has not kept pace. So, in this system anomalous behavior is detected using CNN and LSTM on the surveillance videos. Accurate recognition of anomalous behavior at a point in time is the most challenging problem for systems. The anomaly as well as non anomaly dataset is fed to a machine and trained to identify abnormal behavior. Classifying the video is quite difficult as it contains spatial as well as temporal data. Remembering the temporal data is what is needed for the successful classification of videos. Previous research that had taken place were only on activity detection of humans and none were proposed for abnormal behaviors in ATMs. Therefore, this system has proposed a method to identify and classify whether it is abnormal behavior or not. As it is becoming very crucial for well beings of our society.

A New Approach to Detect Anomalous Behaviour in ATMs

Video Anomaly Event Detection (VAED) is the core technology of intelligent surveillance systems aiming to temporally or spatially locate anomalous events in videos. With the penetration of deep learning, the recent advances in VAED have diverged various routes and achieved significant success. However, most existing reviews focus on traditional and unsupervised VAED methods, lacking attention to emerging weakly-supervised and fully-unsupervised routes. Therefore, this review extends the narrow VAED concept from unsupervised video anomaly detection to Generalized Video Anomaly Event Detection (GVAED), which provides a comprehensive survey that integrates recent works based on different assumptions and learning frameworks into an intuitive taxonomy and coordinates unsupervised, weakly-supervised, fully-unsupervised, and supervised VAED routes. To facilitate future researchers, this review collates and releases research resources such as datasets, available codes, programming tools, and literature. Moreover, this review quantitatively compares the model performance and analyzes the research challenges and possible trends for future work.

Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models

In this paper the problem of anomaly detection in surveillance videos is addressed, which refers to the detection of events that do not conform to normal behaviour. To solve this problem, this paper proposes an approach that utilizes a Deep Neural Network (DNN) to model normal behaviour. Specifically, a DNN is built that learns to predict future frames from past frames using a normal (anomaly free) dataset. The predictions from the model are then compared with testing video for similarity, and the resulting error is used to detect anomalies. Benchmarks of the proposed approach on two datasets common in the anomaly detection literature show that it performs comparably to other methods in the literature, even though it does not rely on any hand-crafted features. Moreover, comparison to other deep learning techniques in the literature shows that the proposed approach is significantly less complex.

Prakhar Singh

Papers

A Deep Learning Based Technique for Anomaly Detection in Surveillance Videos