Loading [a11y]/accessibility-menu.js
Multilevel Anomaly Detection Through Variational Autoencoders and Bayesian Models for Self-Aware Embodied Agents | IEEE Journals & Magazine | IEEE Xplore

Multilevel Anomaly Detection Through Variational Autoencoders and Bayesian Models for Self-Aware Embodied Agents


Abstract:

Anomaly detection constitutes a fundamental step in developing self-aware autonomous agents capable of continuously learning from new situations, as it enables to disting...Show More

Abstract:

Anomaly detection constitutes a fundamental step in developing self-aware autonomous agents capable of continuously learning from new situations, as it enables to distinguish novel experiences from already encountered ones. This paper combines Dynamic Bayesian Networks (DBNs) and Neural Networks (NNs) and proposes a method for detecting anomalies in video data at different abstraction levels. We use a Variational Autoencoder (VAE) to reduce the dimensionality of video frames, and Optical Flows between subsequent images, generating a latent space that captures both visual and dynamical information and that is comparable to low-dimensional sensory data (e.g., positioning, steering angle). An Adapted Markov Jump Particle Filter is employed to predict the following frames and detect anomalies in video data. Our method’s evaluation is executed using different video data from a semi-autonomous vehicle performing different tasks in a closed environment. Tests on benchmark anomaly detection datasets have additionally been conducted.
Published in: IEEE Transactions on Multimedia ( Volume: 24)
Page(s): 1399 - 1414
Date of Publication: 12 March 2021

ISSN Information:


Contact IEEE to Subscribe

References

References is not available for this document.