Learning Multi-scale Features for Foreground Segmentation

August 04, 2018 · Entered Twilight · 🏛 Pattern Analysis and Applications

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, datasets, fgsegnet_comparison.jpg, fgsegnet_v2.png, scripts, testing_scripts, training_sets

Authors Long Ang Lim, Hacer Yalim Keles arXiv ID 1808.01477 Category cs.CV: Computer Vision Citations 191 Venue Pattern Analysis and Applications Repository https://github.com/lim-anggun/FgSegNet_v2 ⭐ 156 Last Checked 1 month ago

Abstract

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 .