OPT OpenIR  > 光学影像学习与分析中心
A CNN–RNN architecture for multi-label weather recognition
Zhao, Bin1; Li, Xuelong2; Lu, Xiaoqiang2; Wang, Zhigang1
作者部门光学影像学习与分析中心
2018-12-17
发表期刊Neurocomputing
ISSN09252312;18728286
卷号322页码:47-57
产权排序2
摘要

Weather Recognition plays an important role in our daily lives and many computer vision applications. However, recognizing the weather conditions from a single image remains challenging and has not been studied thoroughly. Generally, most previous works treat weather recognition as a single-label classification task, namely, determining whether an image belongs to a specific weather class or not. This treatment is not always appropriate, since more than one weather conditions may appear simultaneously in a single image. To address this problem, we make the first attempt to view weather recognition as a multi-label classification task, i.e., assigning an image more than one labels according to the displayed weather conditions. Specifically, a CNN–RNN based multi-label classification approach is proposed in this paper. The convolutional neural network (CNN) is extended with a channel-wise attention model to extract the most correlated visual features. The Recurrent Neural Network (RNN) further processes the features and excavates the dependencies among weather classes. Finally, the weather labels are predicted step by step. Besides, we construct two datasets for the weather recognition task and explore the relationships among different weather conditions. Experimental results demonstrate the superiority and effectiveness of the proposed approach. The new constructed datasets will be available at https://github.com/wzgwzg/Multi-Label-Weather-Recognition. © 2018 Elsevier B.V.

关键词Weather Recognition Multi-label Classification Convolutional Lstm
DOI10.1016/j.neucom.2018.09.048
收录类别SCI ; EI
语种英语
WOS记录号WOS:000447624800005
出版者Elsevier B.V.
EI入藏号20184105925756
引用统计
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/30672
专题光学影像学习与分析中心
通讯作者Lu, Xiaoqiang
作者单位1.School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an; Shaanxi; 710072, China;
2.Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an; Shaanxi; 710119, China
推荐引用方式
GB/T 7714
Zhao, Bin,Li, Xuelong,Lu, Xiaoqiang,等. A CNN–RNN architecture for multi-label weather recognition[J]. Neurocomputing,2018,322:47-57.
APA Zhao, Bin,Li, Xuelong,Lu, Xiaoqiang,&Wang, Zhigang.(2018).A CNN–RNN architecture for multi-label weather recognition.Neurocomputing,322,47-57.
MLA Zhao, Bin,et al."A CNN–RNN architecture for multi-label weather recognition".Neurocomputing 322(2018):47-57.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
A CNN–RNN architectu(3261KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhao, Bin]的文章
[Li, Xuelong]的文章
[Lu, Xiaoqiang]的文章
百度学术
百度学术中相似的文章
[Zhao, Bin]的文章
[Li, Xuelong]的文章
[Lu, Xiaoqiang]的文章
必应学术
必应学术中相似的文章
[Zhao, Bin]的文章
[Li, Xuelong]的文章
[Lu, Xiaoqiang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: A CNN–RNN architecture for multi-label weather recognition.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。