帮助 关于我们

返回检索结果

基于超像素合并的高光谱图像分类
Superpixel Merging-Based Hyperspectral Image Classification

查看参考文献28篇

谢福鼎 1   李旭 1   黄丹 2   金翠 1 *  
文摘 超像素级的高光谱图像分类是一类有代表性的谱-空分类方法.与像素级分类方法相比,超像素级的分类方法在分类精度和分类效率方面都有明显的优势.然而,超像素级分类算法的主要缺点是分类结果严重依赖于超像素的分割尺度.已有的工作表明,最优超像素分割尺度的获得往往是一个实验结果,很难预先确定.为了削弱这种依赖性,文章提出了一种基于超像素合并的超像素级高光谱分类算法.该方法首先采用局部模块度函数对所构造的稀疏加权超像素图进行合并;然后通过新定义的映射将每一个超像素块表示为一个样本点,使用流行的KNN方法对合并后的超像素图像进行超像素级分类.超像素的合并增强了空间信息在分类中的作用,有效地削弱了分类结果对超像素分割尺度的依赖性,并提高了分类精度.为了评价该方法的有效性,在4个公开的实际高光谱数据集上,将所提出的方法与一些竞争性的高光谱图像分类方法进行了实验和对比.实验结果和比较结果表明,该方法不仅有效削弱了超像素分割尺度对分类结果的影响,且在分类精度和计算效率方面都有十分明显的优势.
其他语种文摘 Superpixel-level hyperspectral image classification is a representative spectral-spatial classification method. Compared with the pixel-wise classification method, it has obvious advantages in classification accuracy and efficiency. However, the main disadvantage of superpixel-level classification algorithms is that the classification results depend heavily on the segmentation scale of superpixels. Existing literature shows that the optimal segmentation scale of superpixels is usually an experimental result, and it is difficult to be specified in advance. To weaken this dependency, a superpixel-level hyperspectral image classification algorithm based on superpixel merging is proposed in this work. Local modularity function is first used to merge the sparse weighted superpixel graph constructed. By the newly defined mapping, each superpixel is represented as a sample. Then popular KNN method is adopted to classify the merged image at the superpixel level. The superpixel merging enhances the role of spatial information in classification, effectively weakens the dependence of classification results on the segmentation scale of superpixels, and improves the classification accuracy. To evaluate the effectiveness of the method, the proposed algorithm is compared with some competitive hyperspectral image classification methods on four publicly real hyperspectral datasets. The experimental and comparative results show that the proposed method not only effectively reduces the influence of superpixel segmentation scale on the classification results, but also has obvious advantages both in classification accuracy and computational efficiency.
来源 系统科学与数学 ,2021,41(12):3268-3279 【核心库】
关键词 高光谱图像 ; 超像素 ; 局部模块度 ; 分类
地址

1. 辽宁师范大学地理科学学院, 大连, 116029  

2. 辽宁师范大学计算机与信息技术学院, 大连, 116081

语种 中文
文献类型 研究性论文
ISSN 1000-0577
学科 自动化技术、计算机技术
基金 国家自然科学基金 ;  辽宁省教育厅自然科学研究项目
文献收藏号 CSCD:7160092

参考文献 共 28 共2页

1.  Landgrebe D A. Introduction to the special issue on analysis of hyperspectral image data. IEEE Trans. Geo. Remot. Sens,2001,39(7):1343-1345 CSCD被引 1 次    
2.  Yuen P. An introduction to hyperspectral imaging and its application for security, surveillance and target acquisition. Imag. Sci. J,2010,58(5):241-253 CSCD被引 12 次    
3.  Fauvel M. Advances in spectral-spatial classification of hyperspectral images. Proc. IEEE,2013,101(3):652-675 CSCD被引 81 次    
4.  Kang X. Spectral-spatial hyperspectral image classification with edge-preserving filtering. IEEE Trans. Geo. Remot. Sens,2014,52(5):2666-2677 CSCD被引 46 次    
5.  Kang X. Feature extraction of hyperspectral images with image fusion and recursive filtering. IEEE Trans. Geo. Remot. Sens,2014,52(6):3742-3752 CSCD被引 26 次    
6.  Fang L. Classification of hyperspectral images by exploiting spectral-spatial information of superpixel via multiple kernels. IEEE Trans. Geo. Remot. Sens,2015,53(12):6663-6674 CSCD被引 14 次    
7.  Jiang J. Super PCA: A superpixelwise PCA approach for unsupervised feature extraction of hyperspectral imagery. IEEE Trans. Geo. Remot. Sens,2018,56(8):4581-4593 CSCD被引 22 次    
8.  Xie F. An effective classification scheme for hyperspectral image based on superpixel and discontinuity preserving relaxation. Remot. Sens,2019,11(10):1149 CSCD被引 1 次    
9.  Xie F. A novel spectral-spatial classification method for hyperspectral image at superpixel level. Appl. Sci,2020,10(2):463 CSCD被引 2 次    
10.  Beaulieu J. Hierarchy in picture segmentation: A stepwise optimization approach. IEEE Trans. Patt. Anal. Mach. Intel,1989,11(2):150-163 CSCD被引 22 次    
11.  Tilton J. Image segmentation by region growing and spectral clustering with a natural convergence criterion. IEEE Inter. Geo. Remot. Sens. Symp,1998,4:1766-1768 CSCD被引 1 次    
12.  Haris K. Hybrid image segmentation using watersheds and fast region merging. IEEE Trans. Imag. Proc,1998,7(12):1684-1699 CSCD被引 108 次    
13.  Murtagh F. Algorithms for hierarchical clustering: An overview. Wiley. Interdiscip. Rev. Data. Min. Knowl. Discov,2012,2(1):86-97 CSCD被引 38 次    
14.  Kennedy S M. Cluster-based spectral-spatial segmentation of hyperspectral imagery. IEEE Access,2020,8:140361-140391 CSCD被引 2 次    
15.  Johnson B. Unsupervised image segmentation evaluation and refinement using a multiscale approach. ISPRS J. Photo. Remot. Sens,2011,66(4):473-483 CSCD被引 56 次    
16.  Lu T. Set-to-set distance-based spectral-spatial classification of hyperspectral images. IEEE Trans. Geo. Remot. Sens,2016,54(12):7122-7134 CSCD被引 3 次    
17.  Zhao Y. Novel semi-supervised hyperspectral image classification based on a superpixel graph and discrete potential method. Remot. Sens,2020,12(9):1528 CSCD被引 2 次    
18.  Tu B. KNN-based representation of superpixels for hyperspectral image classification. IEEE J. Sel. Top. Appl. Ear. Obs. Remot. Sens,2018,11(11):4032-4047 CSCD被引 1 次    
19.  Achant A R. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Patt. Ana. Mach. Intell,2012,34(11):2274-2282 CSCD被引 707 次    
20.  Liu M. Entropy rate superpixel segmentation. CVPR,2011:2097-2104 CSCD被引 1 次    
引证文献 1 篇

1 王蕊 基于孪生网络架构和图卷积的多尺度高光谱图像分类 系统科学与数学,2024,44(5):1272-1281
CSCD被引 0 次

显示所有1篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号