[1]谭云飞,李明,罗勇航,等.结合组像素嵌入的双注意力高光谱图像分类[J].计算机技术与发展,2024,34(09):147-153.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0158]
　TAN Yun-fei,LI Ming,LUO Yong-hang,et al.Hyperspectral Image Classification Using Dual Attention with Grouped Pixel Embedding[J].,2024,34(09):147-153.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0158]
点击复制

结合组像素嵌入的双注意力高光谱图像分类()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年09期
页码:
147-153
栏目:
人工智能
出版日期:
2024-09-10

文章信息/Info

Title:
Hyperspectral Image Classification Using Dual Attention with Grouped Pixel Embedding
文章编号:
1673-629X(2024)09-0147-07
作者:
谭云飞; 李明; 罗勇航; 石超山; 文贵豪
重庆师范大学 计算机与信息科学学院,重庆 401331
Author(s):
TAN Yun-fei; LI Ming; LUO Yong-hang; SHI Chao-shan; WEN Gui-hao
School of Computer and Information Science,Chongqing Normal University,Chongqing 401331,China
关键词:
高光谱图像分类; 卷积神经网络; 通道空间卷积分离; 双注意力机制; 组像素嵌入Transformer
Keywords:
hyperspectral image classification;  convolutional neural networks;  channel spatial separation convolution;  dual attention mechanism; grouped pixel embedding Transformer
分类号:
TP391.41
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0158
摘要:
近年来,基于深度学习的框架在高光谱图像分类领域中取得了令人满意的结果。 然而,多数方法仍使用卷积神经网络作为主干网络,其存在感受野过小,对特征信息的挖掘不充分,序列建模的能力较弱,模型复杂和分类精度低等问题。为克服上述局限性,该文提出一种结合组像素嵌入的双注意力高光谱图像分类的方法。 该方法主要分成三个部分,首先,使用含有点卷积组和深度卷积组的通道空间卷积分离模块来高效学习空间光谱的特征信息;其次,添加通道空间双注意力机制,抑制冗余信息的干扰,增强高光谱图像空间与光谱的特征权重;最后,通过组像素嵌入 Transformer 来进一步强化空间与光谱之间的联系,建立全局长距离依赖关系,缓解精度下降的问题,保证了网络良好的分类性能。 实验结果表明,该方法与现有的网络模型相比具有更优越的性能,在 Pavia University 和 WHU-Hi-LongKou 两个数据集中的总体准确率分别达到 99. 26% 和 99. 73% 。
Abstract:
In recent years, frameworks based on deep learning have yielded satisfactory results in hyperspectral image classification.However,most methods still rely on convolutional neural networks as the backbone network,which suffer from limitations such as small receptive fields, insufficient exploration of feature information, weak sequential modeling capabilities, complex models, and low classification accuracy. To address these limitations,we propose a method that hyperspectral image classification using dual attention with grouped pixel embedding. The proposed method is divided into three main parts. Firstly,it achieves efficient learning of spatial-spectral feature information through channel spatial separation convolution module comprising point convolution groups and depth convolution groups. Secondly,it incorporates a channel spatial dual attention mechanism to suppress interference from redundant information and enhance the feature weights of spatial and spectral characteristics in hyperspectral images. Finally,it utilizes a grouped pixel embedding transformer to strengthen the relationship between spatial and spectral information, establish global long - distance dependency relationships,alleviate accuracy degradation issues,and ensure the network’s robust classification performance. Experimental results dem-onstrate that the proposed method outperforms existing network models,achieving overall accuracies of 99. 26% and 99. 73% on the Pavia University and WHU-Hi-LongKou datasets,respectively.

相似文献/References:

[1]张丹丹,李雷. 基于PCANet-RF的人脸检测系统[J].计算机技术与发展,2016,26(02):31.
　ZHANG Dan-dan,LI Lei. Face Detection System Based on PCANet-RF[J].,2016,26(09):31.
[2]邓宗平,赵启军,陈虎. 基于深度学习的人脸姿态分类方法[J].计算机技术与发展,2016,26(07):11.
　DEND Zong-ping,ZHAO Qi-jun,CHEN Hu. Face Pose Classification Method Based on Deep Learning[J].,2016,26(09):11.
[3]戴晓薇,赵启军. 基于回归的指纹方向场估计[J].计算机技术与发展,2017,27(01):1.
　DAI Xiao-wei,ZHAO Qi-jun. Fingerprint Orientation Field Estimation Based on Regression[J].,2017,27(09):1.
[4]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(09):7.
[5]周成伟. 基于卷积神经网络的自然场景中数字识别[J].计算机技术与发展,2017,27(11):101.
　ZHOU Cheng-wei. Recognition of Numbers in Natural Scene with Convolutional Neural Network[J].,2017,27(09):101.
[6]曲之琳,胡晓飞.基于改进激活函数的卷积神经网络研究[J].计算机技术与发展,2017,27(12):77.[doi:10.3969/ j. issn.1673-629X.2017.12.017]
　QU Zhi-lin,HU Xiao-fei.Research on Convolutional Neural Network Based on Improved Activation Function[J].,2017,27(09):77.[doi:10.3969/ j. issn.1673-629X.2017.12.017]
[7]傅 鹏,谢世朋.基于级联卷积神经网络的车牌定位[J].计算机技术与发展,2018,28(01):134.[doi:10.3969/ j. issn.1673-629X.2018.01.029]
　FU Peng,XIE Shi-peng.License Plate Location Based on Cascaded Convolution Neural Network[J].,2018,28(09):134.[doi:10.3969/ j. issn.1673-629X.2018.01.029]
[8]崔凤焦.表情识别算法研究进展与性能比较[J].计算机技术与发展,2018,28(02):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
　CUI Feng-jiao.Ｒesearch and Performance Comparison of Facial Expression Ｒecognition Algorithm[J].,2018,28(09):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
[9]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(09):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[10]郭子琰,舒心,刘常燕,等.基于ReLU 函数的卷积神经网络的花卉识别算法[J].计算机技术与发展,2018,28(05):154.[doi:10．3969/j．issn．1673－629X．2018．05．035]
　GUO Ziyan,SHU Xin,LIU Changyan,et al.A Recognition Algorithm of Flower Based on Convolution Neural Network with ReLU Function[J].,2018,28(09):154.[doi:10．3969/j．issn．1673－629X．2018．05．035]

更新日期/Last Update: 2024-09-10