Future Frame Prediction Using Convolutional VRNN for Anomaly Detection

Anomaly detection in videos aims at reporting anything that does not conform the normal behaviour or distribution. However, due to the sparsity of abnormal video clips in real life, collecting annotated data for supervised learning is exceptionally cumbersome. Inspired by the practicability of gener...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE International Conference on Advanced Video and Signal Based Surveillance (Online) S. 1 - 8
Hauptverfasser: Lu, Yiwei, Kumar, K Mahesh, Nabavi, Seyed shahabeddin, Wang, Yang
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.09.2019
Schlagworte:
Adaptive optics
Anomaly detection
Feature extraction
Predictive models
Testing
Training
Videos
ISSN:2643-6213
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Anomaly detection in videos aims at reporting anything that does not conform the normal behaviour or distribution. However, due to the sparsity of abnormal video clips in real life, collecting annotated data for supervised learning is exceptionally cumbersome. Inspired by the practicability of generative models for semi-supervised learning, we propose a novel sequential generative model based on variational autoencoder (VAE) for future frame prediction with convolutional LSTM (ConvLSTM). To the best of our knowledge, this is the first work that considers temporal information in future frame prediction based anomaly detection framework from the model perspective. Our experiments demonstrate that our approach is superior to the state-of-the-art methods on three benchmark datasets.
ISSN:2643-6213
DOI:10.1109/AVSS.2019.8909850