Using a Supervised Method without supervision for foreground segmentation

TL;DR

This paper introduces a novel approach to foreground segmentation that automatically generates training data, enabling supervised neural networks to outperform traditional unsupervised methods without manual annotation.

Contribution

It proposes an automatic data creation technique that enhances supervised segmentation methods, eliminating the need for manual annotation and improving performance.

Findings

Supervised methods outperform unsupervised ones on CDnet sequences.

Automatic data generation improves segmentation accuracy.

Method reduces manual labeling effort.

Abstract

Neural networks are a powerful framework for foreground segmentation in video acquired by static cameras, segmenting moving objects from the background in a robust way in various challenging scenarios. The premier methods are those based on supervision requiring a final training stage on a database of tens to hundreds of manually segmented images from the specific static camera. In this work, we propose a method to automatically create an "artificial" database that is sufficient for training the supervised methods so that it performs better than current unsupervised methods. It is based on combining a weak foreground segmenter, compared to the supervised method, to extract suitable objects from the training images and randomly inserting these objects back into a background image. Test results are shown on the test sequences in CDnet.