Cascaded Feature-Mask Fusion for Foreground Segmentation

Abstract

Foreground segmentation aims at extracting moving objects from the background in a robust manner under various challenging scenarios. The deep learning-based methods have achieved remarkable improvement in this field. These methods produce semantically correct predictions based on extracted rich semantic features yet perform poorly on segmentation of edge details. The main reason is that the high-level features extracted by the deep network lose the high-frequency information for the successful edge segmentation. On this basis, we propose a novel segmentation network with a cascade architecture to refine segmentation results step by step by introducing detailed information into high-level features. The network recorrects and optimizes the segmentation maps in each step so that more accurate segmentation results are obtained. Furthermore, we evaluate our approach on the challenging CDnet2014 dataset and achieve an F-measure of 0.9868. Our approach thus outperforms previous methods, such as FgSegNet_v2, FgSegNet, BSPVGan, Cascade CNN, IUTIS-5, WeSamBE, DeepBS, and GMM-Stauffer.

Keywords

• Deep learning
• feature-mask fusion
• foreground segmentation
• high-level features
• video surveillance