Visual anomaly detection in video by variational autoencoder
This work addresses anomaly detection for applications like surveillance and self-driving cars, but appears incremental as it compares existing methods without clear novelty.
The paper tackled video anomaly detection by comparing convolutional LSTM with a variational convolutional LSTM autoencoder, but no concrete performance numbers or results were provided in the abstract.
Video anomalies detection is the intersection of anomaly detection and visual intelligence. It has commercial applications in surveillance, security, self-driving cars and crop monitoring. Videos can capture a variety of anomalies. Due to efforts needed to label training data, unsupervised approaches to train anomaly detection models for videos is more practical An autoencoder is a neural network that is trained to recreate its input using latent representation of input also called a bottleneck layer. Variational autoencoder uses distribution (mean and variance) as compared to latent vector as bottleneck layer and can have better regularization effect. In this paper we have demonstrated comparison between performance of convolutional LSTM versus a variation convolutional LSTM autoencoder