Using a Supervised Method without supervision for foreground segmentation
This work addresses the need for manual data annotation in supervised segmentation methods, offering an incremental improvement for video analysis applications.
The paper tackles the problem of foreground segmentation in static camera videos by proposing a method to automatically generate an artificial training database, enabling supervised methods to outperform current unsupervised approaches, achieving better performance on the CDnet test sequences.
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.