Abstract

Anomaly detection in videos is the task of identifying frames from a video sequence that depict events that do not conform to expected behavior, which is an extremely challenging task due to the ambiguous and unbounded properties of anomalies. With the development of deep learning, video anomaly detection methods based on deep neural networks have made great progress. The existing methods mainly follow two routes, namely, frame reconstruction and frame prediction. Due to the powerful generalization ability of neural networks, the application of reconstruction-based methods is limited. Recently, anomaly detection methods based on prediction have achieved advanced performance. However, their performance suffers when they cannot guarantee lower prediction errors for normal events. In this paper, we propose a novel future frame prediction model based on a bidirectional retrospective generation adversarial network (BR-GAN) for anomaly detection. To predict a future frame with higher quality for normal events, first, we propose a bidirectional prediction combined with a retrospective prediction method to fully mine the bidirectional temporal information between the predicted frame and the input frame sequence. Then, the intensity and gradient loss between the predicted frame and the actual frame together with an adversarial loss are used for appearance (spatial) constraints. In addition, we propose a sequence discriminator composed of a 3-dimensional (3D) convolutional neural network to capture the long-term temporal relationships between frame sequences composed of predicted frames and input frames; this network plays a crucial role in maintaining the motion (temporal) consistency of the predicted frames for normal events. Such appearance and motion constraints further facilitate future frame prediction for normal events, and thus, the prediction network can be highly capable of distinguishing normal and abnormal patterns. Extensive experiments on benchmark datasets demonstrate that our method outperforms most existing state-of-the-art methods, validating the effectiveness of our method for anomaly detection.

Highlights

  • Detecting abnormal behavior in video surveillance plays a vital role in maintaining public safety

  • 3) We propose a sequence discriminator composed of 3D convolutional neural networks to capture the longterm temporal relationships between frame sequences composed of predicted frames and input frames, which play a crucial role in maintaining the motion consistency of predicted frames for normal events

  • In this paper, we propose a novel future frame prediction framework based on a bidirectional retrospective generative adversarial network (BR-GAN) that can be trained end-toend for anomaly detection in video

Read more

Summary

Introduction

Detecting abnormal behavior in video surveillance plays a vital role in maintaining public safety. Video surveillance systems have been gradually deployed across our whole society, and the amount of surveillance video data has increased dramatically It is quite time-consuming and inefficient to rely on manual detection of abnormal events from massive surveillance video data. The study of automatic detection algorithms for abnormal behavior in video surveillance has become a research hotspot. It is an extremely challenging task because abnormal events are ambiguous and unbounded, which makes it difficult to clearly define abnormal events. Abnormal events rarely occur, and it is extremely difficult to collect abnormal samples from a large amount of surveillance video data for the learning of algorithms.

Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.