LAUSR.org creates dashboard-style pages of related content for over 1.5 million academic articles. Sign Up to like articles & get recommendations!

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

Photo from wikipedia

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… Click to show full 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.

Keywords: multilevel anomaly; video data; detection; self aware; anomaly detection; detection variational

Journal Title: IEEE Transactions on Multimedia
Year Published: 2022

Link to full text (if available)


Share on Social Media:                               Sign Up to like & get
recommendations!

Related content

More Information              News              Social Media              Video              Recommended



                Click one of the above tabs to view related content.