版权说明 操作指南
首页 > 成果 > 详情

Dynamic Large-Small Kernel Convolutional Neural Network for Pansharpening

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Feng, Xi;Hu, Jianwen;Wu, Wanneng;Fan, Shaosheng
通讯作者:
Hu, JW
作者机构:
[Feng, Xi; Hu, JW; Hu, Jianwen; Wu, Wanneng; Fan, Shaosheng] Changsha Univ Sci & Technol, Sch Elect & Informat Engn, Changsha 410114, Peoples R China.
通讯机构:
[Hu, JW ] C
Changsha Univ Sci & Technol, Sch Elect & Informat Engn, Changsha 410114, Peoples R China.
语种:
英文
关键词:
Convolutional neural network;dynamic convolution;dynamic large kernel;dynamic small kernel;pansharpening
期刊:
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
ISSN:
1545-598X
年:
2023
卷:
20
页码:
1-5
基金类别:
10.13039/501100012166-National Key Research and Development Program of China (Grant Number: 2021YFA0715203) 10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 62271087) 10.13039/501100004735-Natural Science Foundation of Hunan Province, China (Grant Number: 2021JJ40609) 10.13039/501100001809-Natural Science Foundation of Changsha, China (Grant Number: kq2208403) Scientific Research Project of Hunan Education Department of China (Grant Number: 21B0330)
机构署名:
本校为第一且通讯机构
院系归属:
电气与信息工程学院
摘要:
Pansharpening is a spatial-spectral fusion technique that fuses low-resolution multispectral (MS) images with high-resolution panchromatic (PAN) images to get high-resolution MS images which are rich in spectral and spatial information. Some pansharpening methods based on dynamic convolution were proposed to improve the adaptivity and generalization of the fusion network. However, these methods either only focus on local small regions or generate dynamic filters with a complex network. Besides, the dynamic filters in the existing methods only convolve with MS or PAN images, resulting in the ex...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com