Anomaly Detection in Video Data Based on Probabilistic Latent Space Models
Authors:
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
This paper proposes a method for detecting anomalies in video data. A Variational Autoencoder (VAE) is used for reducing the dimensionality of video frames, generating latent space information that is comparable to low-dimensional sensory data (e.g., positioning, steering angle), making feasible the development of a consistent multi-modal architecture for autonomous vehicles. An Adapted Markov Jump Particle Filter defined by discrete and continuous inference levels is employed to predict the following frames and detecting anomalies in new video sequences. Our method is evaluated on different video scenarios where a semi-autonomous vehicle performs a set of tasks in a closed environment.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Motor Anomaly Detection for Unmanned Aerial Vehicles Using Reinforcement LearningIEEE Internet of Things Journal, 2017
- A Study and Comparison of Human and Deep Learning Recognition Performance under Visual Distortions2017
- Action recognition: From static datasets to moving robots2017
- Realtime Anomaly Detection Using Trajectory-Level Crowd Behavior Learning2016
- A Neurocognitive Robot Assistant for Robust Event Detection2016
- Online Nonparametric Bayesian Activity Mining and Analysis From Surveillance VideoIEEE Transactions on Image Processing, 2016
- Stereo Vision-based Local Occupancy Grid Map for Autonomous Navigation in ROS2016
- Summarizing surveillance videos with local-patch-learning-based abnormality detection, blob sequence optimization, and type-based synopsisNeurocomputing, 2015
- A context-aware approach for long-term behavioural change detection and abnormality prediction in ambient assisted livingPattern Recognition, 2015
- The unscented Kalman filter for nonlinear estimation2002