arrow
返回

Foreground segmentation using convolutional neural networks for multiscale feature encoding

delete2018-09-01
delete217
delete
OA
AI
L
Long Ang Lim
H
Hacer Yalım Keleş *
DOI:10.1016/j.patrec.2018.08.002delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Several methods have been proposed to solve moving objects segmentation problem accurately in different scenes. However, many of them lack the ability of handling various difficult scenarios such as illumination changes, background or camera motion, camouflage effect, shadow etc. To address these issues, we propose two robust encoder-decoder type neural networks that generate multi-scale feature encodings in different ways and can be trained end-to-end using only a few training samples. Using the same encoder-decoder configurations, in the first model, a triplet of encoders take the inputs in three scales to embed an image in a multi-scale feature space; in the second model, a Feature Pooling Module (FPM) is plugged on top of a single input encoder to extract multi-scale features in the middle layers. Both models use a transposed convolutional network in the decoder part to learn a mapping from feature space to image space. In order to evaluate our models, we entered the Change Detection 2014 Challenge (changedetection.net) and our models, namely FgSegNet_M and FgSegNet_S, outperformed all the existing state-of-the-art methods by an average F-Measure of 0.9770 and 0.9804, respectively. We also evaluate our models on SBI2015 and UCSD Background Subtraction datasets. Our source code is made publicly available at https://github.com/lim-anggun/FgSegNet. (c) 2018 Elsevier B.V. All rights reserved.
Keyword:
Foreground segmentation
Background subtraction
Deep learning
Convolutional neural networks
Video surveillance
Pixel classification
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Pattern Recognition Letters 封面图
Pattern Recognition Letters
IF:
3.3
论文数:
8.0K
被引数:
1.6W

机构

A
Ankara University
学者数:
8.5K
论文数: 7.2K
被引数: 5.9K
引用论文

引用论文

In0.53Ga0.47As p-i-n photodiodes with transparent cadmium tin oxide contactsIn0.53Ga0.47As p-i-n光电二极管,具有透明镉锡氧化物接触层
err1992-10-05
err0
PREAI
errPaul R. Berger; Niloy K. Dutta; George Zydzik; H. M. O’Bryan; Ursula Keller; Peter R. Smith; John Lopata; D. Sivco; A. Y. Cho
err分享
err收藏
err分享
err收藏
A deep convolutional neural network for video sequence background subtraction
err2018-04-01
err300
PREAI
errBabaee, Mohammadreza; Duc Tung Dinh; Rigoll, Gerhard
err分享
err收藏
30-Day Readmissions among Seriously Ill Older Adults
err2012-12-01
err0
PREAI
errSusan Enguidanos; Evie Vesper; Karl Lorenz
err分享
err收藏
Relations of Long-Term and Contemporary Lipid Levels and Lipid Genetic Risk Scores With Coronary Artery Calcium in the Framingham Heart Study
err2012-12-01
err0
errOAAI
errConnie W. Tsao; Sarah Rosner Preis; Gina M. Peloso; Shih-Jen Hwang; Sekar Kathiresan; Caroline S. Fox; L. Adrienne Cupples; Udo Hoffmann; Christopher J. O'Donnell
err分享
err收藏
Lobular carcinoma in situ of the breast(Long-term followup
err1974-09-01
err0
errOAAI
errJames E. Wheeler; H. T. Enterline; James M. Roseman; Joseph P. Tomasulo; Cheryl H. McIlvaine; William T. Fitts; James Kirshenbaum
err分享
err收藏
学者 查看更多内容