清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

Hyperspectral image classification based on deep separable residual attention network

高光谱成像 残余物 计算机科学 可分离空间 人工智能 图像(数学) 模式识别(心理学) 遥感 计算机视觉 地质学 算法 数学 数学分析
作者
Chao Tu,Wanjun Liu,Linlin Zhao,Tinghao Yan
出处
期刊:Infrared Physics & Technology [Elsevier BV]
卷期号:140: 105401-105401 被引量:1
标识
DOI:10.1016/j.infrared.2024.105401
摘要

Hyperspectral image have rich spatial and spectral information, and how to fully extract and utilize the features of these two dimensions is a research hotspot in hyperspectral classification methods. At present, the unique convolutional operation and deep feature extraction structure of convolutional neural network enable them to have stronger feature representation capabilities and achieve good results in hyperspectral image classification. However, CNN methods do not assign different weights based on the importance of features in the feature extraction process, making it difficult to effectively utilize key features, and most importantly, using fixed shaped convolution kernel can easily overlook the differences between hyperspectral image features. A hyperspectral image classification method based on deep separable residual attention network is proposed to address the above issues. Firstly, to reduce the correlation between hyperspectral image data and minimize the interference of redundant information, principal component analysis is used to reduce the dimensionality of hyperspectral image. Secondly, a shallow feature extraction module is constructed, which can dynamically adjust the size of the receptive field according to the actual situation of the image, adaptively extract shallow features, and reduce the loss of original image features. Then, a depthwise separable residual attention mechanism module is proposed, based on which features are extracted. Starting from global and local features, contextual information on image features in channel and spatial domains is extracted. Finally, use a multi-scale feature fusion module to fully integrate feature maps at different scales. Using Indian Pines, Pavia University and Botswana as experimental datasets, the overall classification accuracy of this paper's method is 98.47 %, 98.70 %, 98.83 % with only 50, 50, 30 training samples per class. The Kappa coefficient is 98.25 %, 98.27 %, and 98.73 %, respectively. Compared with advanced methods, this method not only has higher classification accuracy, but also fully utilizes key features at various network levels.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
科研通AI2S应助科研通管家采纳,获得10
18秒前
18秒前
科研通AI2S应助科研通管家采纳,获得10
18秒前
Owen应助科研通管家采纳,获得200
18秒前
Ava应助青柏采纳,获得10
30秒前
科研通AI2S应助sugarmei采纳,获得10
31秒前
王洋洋完成签到 ,获得积分10
35秒前
53秒前
56秒前
青柏发布了新的文献求助10
58秒前
冬1完成签到 ,获得积分10
1分钟前
JackFan完成签到,获得积分10
1分钟前
1分钟前
游01完成签到 ,获得积分10
1分钟前
2分钟前
2分钟前
cappuccino完成签到 ,获得积分10
2分钟前
无限的以亦完成签到,获得积分10
2分钟前
Kevin完成签到,获得积分10
2分钟前
ChatGPT完成签到,获得积分10
3分钟前
zzhui完成签到,获得积分10
3分钟前
3分钟前
3分钟前
3分钟前
3分钟前
elisa828发布了新的文献求助10
4分钟前
adinaaaalala关注了科研通微信公众号
4分钟前
朴实以丹完成签到 ,获得积分10
4分钟前
情怀应助科研通管家采纳,获得10
4分钟前
Owen应助科研通管家采纳,获得10
4分钟前
cadcae完成签到,获得积分10
4分钟前
GYQ完成签到,获得积分20
4分钟前
光合作用完成签到,获得积分10
4分钟前
yueyueyahoo完成签到,获得积分10
5分钟前
5分钟前
呆呆的猕猴桃完成签到 ,获得积分10
5分钟前
1111完成签到 ,获得积分10
5分钟前
今后应助傲娇的夜山采纳,获得10
6分钟前
cgs完成签到 ,获得积分10
6分钟前
zpc猪猪完成签到,获得积分10
6分钟前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968520
求助须知:如何正确求助?哪些是违规求助? 3513331
关于积分的说明 11167298
捐赠科研通 3248700
什么是DOI,文献DOI怎么找? 1794417
邀请新用户注册赠送积分活动 875030
科研通“疑难数据库(出版商)”最低求助积分说明 804664