基于G-GhostNets轻量化网络的高光谱图像分类

常佩佩; CHANG Peipei

doi:10.48014/ais.20250314002

基于G-GhostNets轻量化网络的高光谱图像分类

Hyperspectral Image Classification Based on the Lightweight G-GhostNets Network

交叉科学学报 2025年第2卷第1期页码[48-57] 下载全文[3.7MB]

摘要

高光谱图像分类在遥感图像研究中具有广泛用途, 然而在嵌入式设备中应用深度学习模型执行高光谱图像分类任务时, 会面临参数量大和计算速度慢的问题, 本文主要针对GPU设备, 提出了使用轻量化网络G-GhostNets, 该网络同时考虑了图像的光谱特征和空间特征, 并且采用聚合中间特征的G-Ghost Stage使模型在GPU上运行, 保持高精度的同时能够进行高效计算。为验证其性能, 本研究将ResNet50和C-GhostNets作为对比网络, 分别对经过预处理的Pavia University 、Indian Pines以及Salinas数据集进行分类实验。实验结果表明, G-GhostNets在高光谱图像分类任务上具有优异的性能, 在保证高精度的同时能够在GPU上高效运行, 能够在较短的时间内实现对每一类的高精度推理。

Abstract

Hyperspectral image classification (HSIC) has been widely applied in remote sensing image analysis. However, deploying deep learning models on embedded devices for HSIC tasks faces challenges due to excessive parameters and high computational complexity. To address these issues, this paper proposes the lightweight G-GhostNets network optimized for GPU devices. G-GhostNets effectively integrates both spectral and spatial features of hyperspectral images. By introducing the G-Ghost Stage, which aggregates intermediate features, the model achieves high-precision classification while maintaining computational efficiency on GPUs. To validate its performance, this study used ResNet50 and C-GhostNets as comparative networks and conducted classification experiments on preprocessed Pavia University, Indian Pines, and Salinas datasets, respectively. The experimental results demonstrate that G-GhostNets exhibits outstanding performance in HSIC tasks, delivering high accuracy and efficient GPU-based inference with significantly reduced computational time per class.

DOI

10.48014/ais.20250314002

文章类型

研究性论文

收稿日期

2025-03-14

接收日期

2025-03-19

出版日期

2025-03-28

关键词

高光谱图像分类, 特征提取, 深度学习, 轻量化网络

Keywords

Hyperspectral image classification, feature extraction, deep learning, lightweight networks

作者

常佩佩

Author

CHANG Peipei

所在单位

中国海洋大学信息科学与工程学部, 青岛 266100

Company

Faculty of Information Science and Engineering, Ocean University of China, Qingdao 266100, China

浏览量

191

下载量

参考文献

[1] Kang X, Li S, Benediktsson J A. Spectral-spatial hyperspectral image classification with edge-preserving filtering[J]. IEEE transactions on geoscience and remote sensing, 2013, 52(5): 2666-2677.
https://doi.org/10.1109/TGRS.2013.2264508
[2] Li S, Song W, Fang L, et al. Deep learning for hyperspectral image classification: An overview[J]. IEEE transactions on geoscience and remote sensing, 2019, 57(9): 6690-6709.
[3] 白林锋, 陈增俊, 周玲, 等. 深度学习赋能的高光谱图像分类研究进展[J]. 海军航空大学学报, 2024, 39(05): 535-545+586.
https://doi.org/10.7682/j.issn.2097-1427.2024.05.003
[4] Melgani F, Bruzzone L. Classification of hyperspectral remote sensing images with support vector machines[J]. IEEE Transactions on geoscience and remote sensing, 2004, 42(8): 1778-1790.
https://doi.org/10.1109/TGRS.2004.831865
[5] Li J, Bioucas-Dias J M, Plaza A. Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(11): 4085-4098.
https://doi.org/10.1109/TGRS.2010.2060550
[6] Licciardi G, Marpu P R, Chanussot J, et al. Linear versus nonlinear PCA for the classification of hyperspectral data based on the extended morphological profiles[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 9(3): 447-451.
https://doi.org/10.1109/LGRS.2011.2172185
[7] Bandos T V, Bruzzone L, Camps-Valls G. Classification of hyperspectral images with regularized linear discriminant analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(3): 862-873.
[8] Ghamisi P, Maggiori E, Li S, et al. New frontiers in spectral- spatial hyperspectral image classification: The latest advances based on mathematical morphology, Markov random fields, segmentation, sparse representation, and deep learning[J]. IEEE geoscience and remote sensing magazine, 2018, 6(3): 10-43.
[9] 李子轩, 官云兰, 王楠, 等. 基于卷积神经网络的高光谱图像分类[J]. 江西科学, 2025, 43(01): 26-35.
https://doi.org/10.13990/j.issn1001-3679.2025.01.004.
[10] Lv Z, Dong X M, Peng J, et al. ESSINet: Efficient spatial- spectral interaction network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-15.
DOI:10.1109/TGRS.2022.3162721
[11] Yao J, Cao X, Hong D, et al. Semi-active convolutional neural networks for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-15.
DOI:10.1109/TGRS.2022.3206208
[12] Feng J, Zhao N, Shang R, et al. Self-supervised divideand- conquer generative adversarial network for classification of hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-17.
[13] Yang Y, Tang X, Zhang X, et al. Semi-supervised multiscale dynamic graph convolution network for hyperspectral image classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 35(5): 6806-6820.
[14] Wang L, Wang L, Wang Q, et al. RSCNet: A residual self-calibrated network for hyperspectral image change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-17.
[15] Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv: 1704. 04861, 2017.
https://doi.org/10.48550/arXiv.1704.04861
[16] Zhang X, Zhou X, Lin M, et al. Shufflenet: An extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6848-6856.
[17] Han K, Wang Y, Tian Q, et al. Ghostnet: More features from cheap operations[C]//Proceedings of the IEEE/ CVF conference on computer vision and pattern recognition. 2020: 1580-1589.
[18] Kavitha K, Arivazhagan S, Suriya B. Classification of Pavia University hyperspectral image using Gabor and SVM classifier[J]. Int. J. New Trends Electron. Commun, 2014, 2(3): 9-14.
[19] Vishwanath V, Sreekanth K, Prakash J, et al. Hyperspectral Patterns With Deep Learning For Classification For Indian Pines[C]//2024 15th International Conference on Computing Communication and Networking Technologies(ICCCNT). IEEE, 2024: 1-7.
[20] 刘柏森, 刘志衡, 孔伟力. 一种自动编码机与K-means相结合的高光谱图像聚类方法[J]. 黑龙江工程学院学报, 2020, 34(06): 23-27+33.
https://doi.org/10.19352/j.cnki.issn1671-4679.2020.06.004.

引用本文

常佩佩. 基于G-GhostNets轻量化网络的高光谱图像分类[J]. 交叉科学学报, 2025, 2(1): 48-57.

Citation

CHANG Peipei. Hyperspectral image classification based on the lightweight G-GhostNets network[J]. Acta Interdisciplinary Science, 2025, 2(1): 48-57.