基于特征增强和混合可变形卷积网络的高光谱图像分类方法

IF 1.4 4区地球科学 Q3 IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY

Remote Sensing Letters Pub Date : 2024-02-09 DOI:10.1080/2150704x.2024.2311782

Yunji Zhao, Zhihao Zhang, Wenming Bao, Xiaozhuo Xu, Zhifang Gao

引用次数: 0

摘要

近年来，一些基于深度模型的高光谱图像（HSI）分类方法表现出了卓越的性能。大多数深度模型接收三维（3D）块结构作为输入数据，然后将这些数据进行分类。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A hyperspectral image classification method based on feature enhancement and a hybrid deformable convolution network

In recent years, some hyperspectral image (HSI) classification methods based on deep models have shown excellent performance. Most deep models receive three-dimensional (3D) block structures as inp...

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Remote Sensing Letters REMOTE SENSING-IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY

CiteScore

4.10

自引率

4.30%

发文量

审稿时长

6-12 weeks

期刊介绍： Remote Sensing Letters is a peer-reviewed international journal committed to the rapid publication of articles advancing the science and technology of remote sensing as well as its applications. The journal originates from a successful section, of the same name, contained in the International Journal of Remote Sensing from 1983 –2009. Articles may address any aspect of remote sensing of relevance to the journal’s readership, including – but not limited to – developments in sensor technology, advances in image processing and Earth-orientated applications, whether terrestrial, oceanic or atmospheric. Articles should make a positive impact on the subject by either contributing new and original information or through provision of theoretical, methodological or commentary material that acts to strengthen the subject.