HybridSN: Exploring 3-D–2-D CNN Feature Hierarchy for Hyperspectral Image Classification

高光谱成像 卷积神经网络 人工智能 计算机科学 模式识别(心理学) 特征(语言学) 上下文图像分类 特征提取 光谱带 深度学习 代表(政治) 图像(数学) 遥感 政治 地质学 哲学 语言学 法学 政治学
作者
Swalpa Kumar Roy,Gopal Krishna,Shiv Ram Dubey,B.B. Chaudhuri
出处
期刊:IEEE Geoscience and Remote Sensing Letters [Institute of Electrical and Electronics Engineers]
卷期号:17 (2): 277-281 被引量:1242
标识
DOI:10.1109/lgrs.2019.2918719
摘要

Hyperspectral image (HSI) classification is widely used for the analysis of remotely sensed images. Hyperspectral imagery includes varying bands of images. Convolutional Neural Network (CNN) is one of the most frequently used deep learning based methods for visual data processing. The use of CNN for HSI classification is also visible in recent works. These approaches are mostly based on 2D CNN. Whereas, the HSI classification performance is highly dependent on both spatial and spectral information. Very few methods have utilized the 3D CNN because of increased computational complexity. This letter proposes a Hybrid Spectral Convolutional Neural Network (HybridSN) for HSI classification. Basically, the HybridSN is a spectral-spatial 3D-CNN followed by spatial 2D-CNN. The 3D-CNN facilitates the joint spatial-spectral feature representation from a stack of spectral bands. The 2D-CNN on top of the 3D-CNN further learns more abstract level spatial representation. Moreover, the use of hybrid CNNs reduces the complexity of the model compared to 3D-CNN alone. To test the performance of this hybrid approach, very rigorous HSI classification experiments are performed over Indian Pines, Pavia University and Salinas Scene remote sensing datasets. The results are compared with the state-of-the-art hand-crafted as well as end-to-end deep learning based methods. A very satisfactory performance is obtained using the proposed HybridSN for HSI classification. The source code can be found at \url{https://github.com/gokriznastic/HybridSN}.
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
1秒前
迷路的含桃完成签到 ,获得积分10
1秒前
muyi发布了新的文献求助10
2秒前
烟花应助阿仔爱学习采纳,获得30
2秒前
科研通AI2S应助EthanChan采纳,获得10
3秒前
豪豪完成签到,获得积分10
3秒前
岑忘幽完成签到,获得积分20
3秒前
小鹿发布了新的文献求助10
4秒前
符宇新发布了新的文献求助10
5秒前
windy7发布了新的文献求助10
5秒前
5秒前
所所应助xs采纳,获得10
6秒前
jintt发布了新的文献求助10
6秒前
cing完成签到,获得积分10
6秒前
Leukocyte完成签到 ,获得积分10
7秒前
8秒前
飞哥yyds完成签到,获得积分10
8秒前
隐形曼青应助muyi采纳,获得10
10秒前
浮浮世世发布了新的文献求助10
10秒前
Tim完成签到,获得积分10
13秒前
13秒前
英姑应助xixi采纳,获得10
14秒前
小鹿完成签到,获得积分10
15秒前
bing完成签到,获得积分10
15秒前
久违完成签到,获得积分10
15秒前
浮浮世世完成签到,获得积分10
16秒前
17秒前
17秒前
17秒前
17秒前
西红柿完成签到,获得积分10
18秒前
小阿逊发布了新的文献求助10
18秒前
久违发布了新的文献求助10
20秒前
20秒前
21完成签到,获得积分20
22秒前
diaobk发布了新的文献求助10
22秒前
22秒前
Dada应助qdsj2033采纳,获得30
22秒前
大模型应助风花雪月采纳,获得10
24秒前
xs发布了新的文献求助10
24秒前
高分求助中
The Mother of All Tableaux Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 2400
Ophthalmic Equipment Market by Devices(surgical: vitreorentinal,IOLs,OVDs,contact lens,RGP lens,backflush,diagnostic&monitoring:OCT,actorefractor,keratometer,tonometer,ophthalmoscpe,OVD), End User,Buying Criteria-Global Forecast to2029 2000
Cognitive Neuroscience: The Biology of the Mind 1000
Cognitive Neuroscience: The Biology of the Mind (Sixth Edition) 1000
Optimal Transport: A Comprehensive Introduction to Modeling, Analysis, Simulation, Applications 800
Official Methods of Analysis of AOAC INTERNATIONAL 600
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 588
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 3958245
求助须知:如何正确求助?哪些是违规求助? 3504421
关于积分的说明 11118358
捐赠科研通 3235721
什么是DOI,文献DOI怎么找? 1788421
邀请新用户注册赠送积分活动 871211
科研通“疑难数据库(出版商)”最低求助积分说明 802582