Multi-view hyperspectral image classification via weighted sparse representation

被引：0
作者：
Zhao Y. [1 ]
Qin Y. [2 ]
Li Z. [3 ]
Huang W. [3 ]
Hou R. [1 ]
机构：
[1] Shandong Police College, Ji’nan
[2] Northwest Institute of Nuclear Technology, Xi’an
[3] Hubei University, Wuhan
来源：
Multimedia Tools and Applications | 2024年 / 83卷 / 42期
基金：
中国国家自然科学基金;
关键词：
Hyperspectral image classification; Multi-view data; Renyi entropy; Sparse representation;
D O I：
10.1007/s11042-024-18917-2
中图分类号：
学科分类号：
摘要：
Hyperspectral image classification aims to classify pixels in hyperspectral image into different land-cover classes. Considering multi-view data can improve the classification performance as it contains more abundant information than single view, a multi-view based method is proposed for hyperspectral image classification in this paper. In the proposed method, spatial neighboring pixels are adaptively determined by the mean and deviation of samples in the fixed-size spatial window. Then, the sparse representation algorithm is realized to obtain the sparse coefficients for the multi-view matrix set of the spatial neighboring pixels. Moreover, the renyi-entropy is calculated to determine the weight of each view in the classification task since the performance of different views is different. Finally, the obtained sparse coefficients and weights are jointly used to determine the class label of each test pixel. Experimental results on the Indian Pines dataset and University of Pavia dataset demonstrate the superior performance of the proposed method compared to several state-of-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
引用
收藏
页码：90207 / 90226
页数：19
相关论文
共 61 条
[41]  
Yuan Q., Shen H., Zhang L., Xia L., Hypspectral image denoising with a multi-view fusion strategy, (2014)
[42]  
Jiang J., Huang L., Li H., Liang X., Hyperspectral image supervised classification via multi-view nuclear norm based 2D PCA feature extraction and kernel ELM, Geosci Remote Sens Symp, (2016)
[43]  
Li Y., Lu T., Li S., Subpixel-pixel-superpixel-based multiview active learning for hyperspectral images classification, IEEE Trans Geosci Remote Sensing, 99, pp. 1-13, (2020)
[44]  
Xu X., Li J., Li S., Multiview intensity-based active learning for hyperspectral image classification, IEEE Trans Geosci Remote Sensing, 2, pp. 1-12, (2018)
[45]  
Di W., Crawford M.M., View generation for multiview maximum disagreement based active learning for hyperspectral image classification, IEEE Trans Geosci Remote Sensing, 50, 5, pp. 1942-1954, (2012)
[46]  
Yao Q., Xiang X., Zou K., Hyperspectral image classification based on heterogeneous multi-view active learning, Comput Appl Softw, (2018)
[47]  
Zhao Y., Cheung Y.M., You X., Peng Q., Shi Y., Hyperspectral image classification via spatial window-based multiview intact feature learning, IEEE Trans Geosci Remote Sensing, 99, pp. 1-13, (2020)
[48]  
Zhao Y., Peng J., Wei Y., Peng Q., Mou Y., Multiple-feature latent space learning-based hyperspectral image classification, IEEE Geosci Remote Sensing Lett, 99, pp. 1-5, (2020)
[49]  
Zhang E., Zhang X., Liu H., Jiao L., Fast multifeature joint sparse representation for hyperspectral image classification, IEEE Geosci Remote Sensing Lett, 12, 7, pp. 1397-1401, (2015)
[50]  
Yu S., Giraldo L., Jenssen R., Principe J.C., Multivariate extension of matrix-based renyi’s α -order entropy functional, IEEE Trans Pattern Anal Mach Intell, (2019)
1234567