Deep Autoencoder Architectures For Foreground Object Detection In Video Sequences Based On Probabilistic Mixture Models
Jorge García-González, Miguel A. Molina‐Cabello, Rafael Marcos Luque‐Baena, Juan Miguel Ortiz-de-Lazcano-Lobato, Ezequiel López‐Rubio · 2020
Foreground object detection algorithms should be insensitive to noise present in the analyzed video sequences. In this work, a study of a type of non-supervised deep learning network, called autoencoder, is performed. They are suited to reduce input dimensionality and capture the most relevant information present in a region or image. Therefore, different types of autoencoders, deterministic and variational, with different architectures, activation functions and number of layers, are analyzed. This neural network is combined with a probabilistic mixture model which attempts to classify each video frame region as background and foreground.