Learning Multi-scale Features for Foreground Segmentation
This work addresses robust foreground segmentation for video analysis, offering incremental improvements by enhancing feature pooling to handle camera motion without multi-scale inputs.
The paper tackles foreground segmentation by proposing a novel encoder-decoder neural network that integrates multi-scale features through feature fusion, achieving state-of-the-art performance with an average F-Measure of 0.9847 on the CDnet2014 dataset.
Foreground segmentation algorithms aim segmenting moving objects from the background in a robust way under various challenging scenarios. Encoder-decoder type deep neural networks that are used in this domain recently perform impressive segmentation results. In this work, we propose a novel robust encoder-decoder structure neural network that can be trained end-to-end using only a few training examples. The proposed method extends the Feature Pooling Module (FPM) of FgSegNet by introducing features fusions inside this module, which is capable of extracting multi-scale features within images; resulting in a robust feature pooling against camera motion, which can alleviate the need of multi-scale inputs to the network. Our method outperforms all existing state-of-the-art methods in CDnet2014 dataset by an average overall F-Measure of 0.9847. We also evaluate the effectiveness of our method on SBI2015 and UCSD Background Subtraction datasets. The source code of the proposed method is made available at https://github.com/lim-anggun/FgSegNet_v2 .