Published on Mon Apr 23 2018

STAN: Spatio-Temporal Adversarial Networks for Abnormal Event Detection

Sangmin Lee, Hak Gu Kim, Yong Man Ro

In this paper, we propose a novel abnormal event detection method. We devise a spatio-temporal generator which synthesizes an inter-frame. A proposed spatio/temporal discriminator determines whether an input sequence is real-normal or not.

0
0
0
Abstract

In this paper, we propose a novel abnormal event detection method with spatio-temporal adversarial networks (STAN). We devise a spatio-temporal generator which synthesizes an inter-frame by considering spatio-temporal characteristics with bidirectional ConvLSTM. A proposed spatio-temporal discriminator determines whether an input sequence is real-normal or not with 3D convolutional layers. These two networks are trained in an adversarial way to effectively encode spatio-temporal features of normal patterns. After the learning, the generator and the discriminator can be independently used as detectors, and deviations from the learned normal patterns are detected as abnormalities. Experimental results show that the proposed method achieved competitive performance compared to the state-of-the-art methods. Further, for the interpretation, we visualize the location of abnormal events detected by the proposed networks using a generator loss and discriminator gradients.

Thu Aug 31 2017
Computer Vision
Abnormal Event Detection in Videos using Generative Adversarial Nets
We propose to use Generative Adversarial Nets (GANs), which are trained using normal frames and corresponding optical-flow images. Since our GANs are trained with only normal data, they are not able to generate abnormal events. abnormal areas are detected by computing local differences.
0
0
0
Fri Jan 06 2017
Computer Vision
Abnormal Event Detection in Videos using Spatiotemporal Autoencoder
We present an efficient method for detecting anomalies in videos. Our method is comparable to state-of-the-art methods at a considerable speed of up to 140 fps.
0
0
0
Sat Apr 03 2021
Computer Vision
"Forget" the Forget Gate: Estimating Anomalies in Videos using Self-contained Long Short-Term Memory Networks
0
0
0
Thu Jul 29 2021
Computer Vision
Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection
Convolutional Transformer based Dual Discriminator Generative Adversarial Networks (CT-D2GAN) to perform unsupervised video anomaly detection. It contains three key components, i.e., a convolutional encoder to capture spatial information of the input video clips, a temporal self-attention
1
0
1
Wed Jun 16 2021
Computer Vision
Anomaly Detection in Video Sequences: A Benchmark and Computational Model
Large-scale Anomaly Detection (LAD) database is the benchmark for anomaly detection in video sequences. LAD database contains 2000 video sequences including normal and abnormal video clips with 14 anomaly categories including crash, fire, violence, etc.
0
0
0
Thu Nov 19 2020
Machine Learning
Abnormal Event Detection in Urban Surveillance Videos Using GAN and Transfer Learning
Abnormal event detection (AED) in urban surveillance videos has multiple challenges. This paper is based on deep learning methods and provides an effective way to detect and locate abnormal events in videos by handling spatio temporal data.
0
0
0