基于层级Transformer的高光谱图像分类方法

doi:10.11947/j.AGCS.2023.20220540

测绘学报 ›› 2023, Vol. 52 ›› Issue (7): 1139-1147.doi: 10.11947/j.AGCS.2023.20220540

基于层级Transformer的高光谱图像分类方法

张艺超^1,2, 郑向涛^1,3, 卢孝强^1,3

1. 中国科学院西安光学精密机械研究所光谱成像技术重点实验室, 陕西西安 710119;
2. 中国科学院大学, 北京 100049;
3. 福州大学物理与信息工程学院, 福建福州 350100

收稿日期:2022-08-25 修回日期:2023-04-16 发布日期:2023-07-31
通讯作者: 郑向涛 E-mail:xiangtaoz@gmail.com
作者简介:张艺超(1992-),男,博士,研究方向为计算机视觉、人工智能和遥感图像处理。E-mail:yczhang0819@gmail.com
基金资助:
国家自然科学基金（62271484）；国家杰出青年科学基金（61925112）；陕西省重点研发计划（2023-YBGY-225）

Hyperspectral image classification method based on hierarchical transformer network

ZHANG Yichao^1,2, ZHENG Xiangtao^1,3, LU Xiaoqiang^1,3

1. Key Laboratory of Spectral Imaging Technology CAS, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710119, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China;
3. College of Physics and Information Engineering, Fuzhou University, Fuzhou 350100, China

Received:2022-08-25 Revised:2023-04-16 Published:2023-07-31
Supported by:
The National Natural Science Foundation of China (No. 62271484); The National Science Fund for Distinguished Young Scholars (No. 61925112); The Key Research and Development Program of Shaanxi (No. 2023-YBGY-225)

摘要/Abstract

摘要： 高光谱图像分类将每个像素分类至预设的地物类别，对环境测绘等各类地球科学任务有着至关重要的意义。近年来，学者们尝试利用深度学习框架进行高光谱图像分类，取得了令人满意的效果。然而这些方法在光谱特征的提取上仍存在一定缺陷。本文提出一个基于自注意力机制的层级融合高光谱图像分类框架（hierarchical self-attention network，HSAN）。首先，构建跳层自注意力模块进行特征学习，利用Transformer结构中的自注意力机制捕获上下文信息，增强有效信息贡献。然后，设计层级融合方式，进一步缓解特征学习过程中的有效信息损失，增强各层级特征联动。在Pavia University及Houston2013数据集上的试验表明，本文提出的框架相较于其他高光谱图像分类框架具有更好的分类性能。

关键词: 高光谱图像分类, Transformer, 自注意力机制, 层级融合

Abstract: Hyperspectral image classification, which assigns each pixel to predefined land cover categories, is of crucial importance in various Earth science tasks such as environmental mapping and other related fields. In recent years, scholars have attempted to utilize deep learning frameworks for hyperspectral image classification and achieved satisfactory results. However, these methods still have certain deficiencies in extracting spectral features. This paper proposes a hierarchical self-attention network (HSAN) for hyperspectral image classification based on the self-attention mechanism. Firstly, a skip-layer self-attention module is constructed for feature learning, leveraging the self-attention mechanism of Transformer to capture contextual information and enhance the contribution of relevant information. Secondly, a hierarchical fusion method is designed to further alleviate the loss of relevant information during the feature learning process and enhance the interplay of features at different hierarchical levels. Experimental results on the Pavia University and Houston2013 datasets demonstrate that the proposed framework outperforms other state-of-the-art hyperspectral image classification frameworks.

Key words: hyperspectral image classification, transformer, self-attention mechanism, hierarchical fusion

中图分类号:

P237

张艺超, 郑向涛, 卢孝强. 基于层级Transformer的高光谱图像分类方法[J]. 测绘学报, 2023, 52(7): 1139-1147.

ZHANG Yichao, ZHENG Xiangtao, LU Xiaoqiang. Hyperspectral image classification method based on hierarchical transformer network[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(7): 1139-1147.

参考文献

[1] AHMAD M, SHABBIR S, ROY S K, et al.Hyperspectral image classification-traditional to deep models:a survey for future prospects[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021.
[2] RASTI B, HONG Danfeng, HANG Renlong, et al. Feature extraction for hyperspectral imagery:the evolution from shallow to deep:overview and toolbox[J]. IEEE Geoscience and Remote Sensing Magazine, 2020, 8(4):60-88.
[3] XUE Zhaohui, NIE Xiangyu. Low-rank and sparse representation with adaptive neighborhood regularization for hyperspectral image classification[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(1):73-90. DOI:10.11947/j.JGGS.2022.0108
[4] 左溪冰,刘冰,余旭初,等.高光谱影像小样本分类的图卷积网络方法[J].测绘学报, 2021, 50(10):1358-1369. DOI:10.11947/j.AGCS.2021.20200155. ZUO Xibing, LIU Bing, YU Xuchu, et al. Graph convolutional network method for small sample classification of hyperspectral images[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(10):1358-1369. DOI:10.11947/j. AGCS.2021.20200155.
[5] HAM J, CHEN Yangchi, CRAWFORD M M, et al. Investigation of the random forest framework for classification of hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3):492-501.
[6] CAMPS-VALLS G, BRUZZONE L. Kernel-based methods for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(6):1351-1362.
[7] MA Li, CRAWFORD M M, TIAN Jinwei. Local manifold learning-based K-nearest-neighbor for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(11):4099-4109.
[8] HU Wei, HUANG Yangyu, WEI Li, et al. Deep convolutional neural networks for hyperspectral image classification[J]. Journal of Sensors, 2015.
[9] ZHAO Wenzhi, DU Shihong. Spectral-spatial feature extraction for hyperspectral image classification:a dimension reduction and deep learning approach[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(8):4544-4554.
[10] WANG Kexian, ZHENG Shunyi, LI Rui, et al. A deep double-channel dense network for hyperspectral image classification[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(4):46-62.
[11] LIU Xun, DENG Chenwei, CHANUSSOT J, et al. StfNet:a two-stream convolutional neural network for spatiotemporal image fusion[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(9):6552-6564.
[12] WU Hao, PRASAD S. Convolutional recurrent neural networks for hyperspectral data classification[J]. Remote Sensing, 2017, 9(3):298.
[13] YU Shiqi, JIA Sen, XU Chunyan. Convolutional neural networks for hyperspectral image classification[J]. Neurocomputing, 2017, 219:88-98.
[14] GAO Hongmin, YANG Yao, LI Chenming, et al. Joint alternate small convolution and feature reuse for hyperspectral image classification[J]. ISPRS International Journal of Geo-Information, 2018, 7(9):349.
[15] RAN Lingyan, ZHANG Yanning, WEI Wei, et al. A hyperspectral image classification framework with spatial pixel pair features[J]. Sensors, 2017, 17(10):2421.
[16] ZHONG Zilong, LI Jin, LUO Zhinming, et al. Spectral-spatial residual network for hyperspectral image classification:a 3D deep learning framework[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 56(2):847-858.
[17] LI Simin, ZHU Xueyu, LIU Yang, et al. Adaptive spatial-spectral feature learning for hyperspectral image classification[J]. IEEE Access, 2019, 7:61534-61547.
[18] ROY S K, MANNA S, SONG Tiecheng, et al. Attention-based adaptive spectral-spatial kernel ResNet for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 59(9):7831-7843.
[19] MOU Lichao, LU Xiaoqiang, LI Xuelong, et al. Nonlocal graph convolutional networks for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(12):8246-8257.
[20] WAN Sheng, GONG Chen, ZHONG Ping, et al.Multiscale dynamic graph convolutional network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 58(5):3162-3177.
[21] WAN Sheng, PAN Shirui, ZHONG Ping, et al. Dual interactive graph convolutional networks for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60:1-14.
[22] HONG Danfeng, GAO Lianru, YAO Jing, et al. Graph convolutional networks for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 59(7):5966-5978.
[23] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.
[24] HAN Kai, WANG Yunhe, CHEN Hanting, et al. A survey on vision transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(1):87-110.
[25] SUN Hao, ZHENG Xiangtao, LU Xiaoqiang, et al. Spectral-spatial attention network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 58(5):3232-3245.
[26] HONG Danfeng, HAN Zhu, YAO Jing, et al. Spectralformer:rethinking hyperspectral image classification with transformers[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60:1-15.
[27] MA Wenping, Yang Qifan, Wu Yue, et al. Double-branch multi-attention mechanism network for hyperspectral image classification[J]. Remote Sensing, 2019, 11(11):1307.
[28] WOO S, PARK J, LEE J Y, et al.Cbam:convolutional block attention module[C]//Proceedings of 2018 European conference on computer vision. Switzerland:Springer, 2018:3-19.
[29] YANG Kai, SUN Hao, ZOU Chunbo, et al. Cross-attention spectral-spatial network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60:1-14.
[30] LI Rui, ZHENG Shunyi, DUAN C, et al. Classification of hyperspectral image based on double-branch dual-attention mechanism network[J]. Remote Sensing, 2020, 12(3):582.
[31] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE conference on computer vision and pattern recognition. Cham:IEEE 2016:770-778.

基于层级Transformer的高光谱图像分类方法

Hyperspectral image classification method based on hierarchical transformer network

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	吴晨昊, 向隆刚, 张叶廷, 吴华意. 基于地理空间感知型表征学习的轨迹相似度计算[J]. 测绘学报, 2023, 52(4): 670-678.
[2]	谷雨, 徐英, 郭宝峰. 融合空谱特征和集成超限学习机的高光谱图像分类[J]. 测绘学报, 2018, 47(9): 1238-1249.
[3]	侯榜焕, 王锟, 姚敏立, 贾维敏, 王榕. 面向高光谱图像分类的半监督空谱判别分析[J]. 测绘学报, 2017, 46(9): 1098-1106.
[4]	邵远杰吴国平马丽. 属类概率距离构图的半监督高光谱图像分类[J]. 测绘学报, 2014, 43(11): 1182-1189.