An Autoencoder Based Background Subtraction for Public Surveillance
Yue Li, Xiaosheng Yu, Haijun Cao, Ming Xu · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · 2021
An autoencoder is trained to generate the background from the surveillance image by setting the training label as the shuffled input, instead of the input itself in a traditional autoencoder. Then the multi-scale features are extracted by a sparse autoencoder from the surveillance image and the corresponding background to detect foreground.