Abnormal Event Detection in Videos Using Hybrid Spatio-Temporal Autoencoder
Authors:
- 1 October 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2276-2280
Abstract
The LSTM Encoder-Decoder framework is used to learn representation of video sequences and applied for detect abnormal event in complex environment. However, it generally fails to account for the global context of the learned representation with a fixed dimension representation and the learned representation is crucial for decoder phase. Based on the LSTM Encoder-Decoder and the Convolutional Autoencoder, we explore a hybrid autoencoder architecture, which not only extracts better spatio-temporal context, but also improves the extrapolate capability of the corresponding decoder with the shortcut connection. The experimental results demonstrate that our approach outperforms lots of state-of-the-art methods on benchmark datasets.Keywords
This publication has 3 references indexed in Scilit:
- Video anomaly detection and localisation based on the sparsity and reconstruction error of auto‐encoderElectronics Letters, 2016
- Histograms of optical flow orientation for abnormal events detection2013
- Robust Real-Time Unusual Event Detection using Multiple Fixed-Location MonitorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008