Multispectral background subtraction with deep learning

Rongrong Liu; Yassine Ruichek; Mohammed El Bagdouri

首页> 外文期刊>Journal of visual communication & image representation >Multispectral background subtraction with deep learning

【24h】

Multispectral background subtraction with deep learning

机译：Multispectral background subtraction with deep learning

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

In this paper, we follow the trend of deep learning and make an attempt to investigate the potential benefitof using multispectral images via convolutional neural networks for background subtraction task. The majorcontributions of this work lie in two aspects, based on the impressive algorithm FgSegNet_v2. Firstly, weextract three channels out of the seven of the FluxData FD-1665 multispectral dataset to match the numberof input channels of the VGG16 deep model. Some combinations of three-channel based multispectral imagesperform better than RGB images. Secondly, a new convolutional encoder is designed to use all the multispectralchannels available to further explore the information of multispectral images. The results outperform the RGBimages and also other approaches using the same multispectral dataset.

著录项

来源
《Journal of visual communication & image representation》 |2021年第10期|103267.1-103267.10|共10页
作者
Rongrong Liu; Yassine Ruichek; Mohammed El Bagdouri;
展开▼
作者单位

Connaissance et Intelligence Artificielle Distribuees (CIAD), University Bourgogne Franche-Comte, UTBM, 12 Rue Thierry Mieg, 90000, Belfort, France;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类
关键词
Background subtraction; Multispectral images; Deep learning; Convolutional neural networks;

Multispectral background subtraction with deep learning

摘要

著录项

相关主题

期刊订阅