Visible to the public Anomaly Detection in Video Data Based on Probabilistic Latent Space Models

TitleAnomaly Detection in Video Data Based on Probabilistic Latent Space Models
Publication TypeConference Paper
Year of Publication2020
AuthorsSlavic, G., Campo, D., Baydoun, M., Marin, P., Martin, D., Marcenaro, L., Regazzoni, C.
Conference Name2020 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)
Date PublishedMay 2020
ISBN Number978-1-7281-4384-2
KeywordsAdapted Markov Jump Particle Filter, adaptive filtering, anomaly detection, Autonomous vehicles, continuous inference levels, discrete inference levels, image sequences, Kalman filtering, latent space information generation, Markov processes, Metrics, mobile robots, multimodal architecture, neural nets, object detection, particle filtering, particle filtering (numerical methods), probabilistic latent space models, probability, pubcrawl, resilience, Resiliency, robot vision, Scalability, security of data, semiautonomous vehicle, Variational autoencoder, Vehicles, video data, video frames, video sequences, video signal processing

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.

Citation Keyslavic_anomaly_2020