高光谱影像光谱-空间多特征加权概率融合分类

doi:10.11947/j.AGCS.2015.20140544

测绘学报 ›› 2015, Vol. 44 ›› Issue (8): 909-918.doi: 10.11947/j.AGCS.2015.20140544

高光谱影像光谱-空间多特征加权概率融合分类

张春森¹, 郑艺惟¹, 黄小兵¹, 崔卫红²

1. 西安科技大学测绘科学与技术学院, 陕西西安 710054;
2. 武汉大学遥感信息工程学院, 湖北武汉 430079

收稿日期:2014-10-27 修回日期:2015-04-29 出版日期:2015-09-20 发布日期:2015-09-02
通讯作者: 崔卫红,E-mail:whcui@whu.edu.cn E-mail:whcui@whu.edu.cn
作者简介:张春森(1963-),男,博士,教授,研究方向为摄影测量与遥感。E-mail:zhchunsen@aliyun.com
基金资助:
国家自然科学基金(41101410);陕西省自然科学基金(2010JM5009)

Hyperspectral Image Classification Based on the Weighted Probabilistic Fusion of Multiple Spectral-spatial Features

ZHANG Chunsen¹, ZHENG Yiwei¹, HUANG Xiaobing¹, CUI Weihong²

1. College of Geomatics, Xi'an University of Science and Technology, Xi'an 710054, China;
2. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China

Received:2014-10-27 Revised:2015-04-29 Online:2015-09-20 Published:2015-09-02
Supported by:
The National Natural Science Foundation of China(No.41101410);The National Natural Science Foundation of Shaanxi Province of China(No.2010JM5009)

摘要/Abstract

摘要：

提出了一种基于光谱-空间多特征加权概率融合的高光谱影像分类方法。首先,利用最小噪声分离(minimum noise fraction,MNF)方法对高光谱影像进行降维和特征提取,并以得到的MNF特征影像作为光谱特征,联合灰度共生矩阵(gray level co-occurrence matrix,GLCM)提取的纹理特征、基于OFC算子建立的多尺度形态学特征以及采用连续最大角凸锥(sequential maximum angle convex cone,SMACC)提取的端元组分特征,组成3组光谱-空间特征;然后利用支持向量机(support vector machine,SVM)对每一组光谱-空间特征进行分类,得到每组特征的概率输出结果;最后,建立多特征加权概率融合模型,应用该模型将不同特征的概率输出结果进行加权融合,得到最终分类结果。为了验证该方法的有效性,利用ROSIS和 AVIRIS影像进行试验,总体分类精度分别达到97.65%和96.62%。结果表明本文的方法不但较好地克服了传统基于单一特征高光谱影像分类的局限性,而且其分类效果也优于常规矢量叠加(vector stacking,VS)和概率融合的多特征分类方法,有效地改善了高光谱影像的分类结果。

关键词: 光谱-空间特征, 概率融合, 支持向量机, 高光谱, 分类

Abstract:

A hyperspectral images classification method based on the weighted probabilistic fusion of multiple spectral-spatial features was proposed in this paper. First, the minimum noise fraction (MNF) approach was employed to reduce the dimension of hyperspectral image and extract the spectral feature from the image, then combined the spectral feature with the texture feature extracted based on gray level co-occurrence matrix (GLCM), the multi-scale morphological feature extracted based on OFC operator and the end member feature extracted based on sequential maximum angle convex cone (SMACC) method to form three spectral-spatial features. Afterwards, support vector machine (SVM) classifier was used for the classification of each spectral-spatial feature separately. Finally, we established the weighted probabilistic fusion model and applied the model to fuse the SVM outputs for the final classification result. In order to verify the proposed method, the ROSIS and AVIRIS image were used in our experiment and the overall accuracy reached 97.65% and 96.62% separately. The results indicate that the proposed method can not only overcome the limitations of traditional single-feature based hyperspectral image classification, but also be superior to conventional VS-SVM method and probabilistic fusion method. The classification accuracy of hyperspectral images was improved effectively.

Key words: spectral-spatial feature, probabilistic fusion, SVM, hyperspectral, classification

中图分类号:

P227

张春森, 郑艺惟, 黄小兵, 崔卫红. 高光谱影像光谱-空间多特征加权概率融合分类[J]. 测绘学报, 2015, 44(8): 909-918.

ZHANG Chunsen, ZHENG Yiwei, HUANG Xiaobing, CUI Weihong. Hyperspectral Image Classification Based on the Weighted Probabilistic Fusion of Multiple Spectral-spatial Features[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(8): 909-918.

参考文献

[1] BRUZZONEL, CARLIN L. A Multilevel Context-based System for Classification of Very High Spatial Resolution Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(9):2587-2600.
[2] SHI Beiqi, LIU Chun, SUN Weiwei, et al. Sparse Nonnegative Matrix Factorization for Hyperspectral Optimal Band Selection[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(3): 351-357. (施蓓琦, 刘春, 孙伟伟, 等. 应用稀疏非负矩阵分解聚类实现高光谱影像波段的优化选择[J]. 测绘学报, 2013, 42(3): 351-357.)
[3] PRASAD S, MANN BRUCE L. Decision Fusion with Confidence-based Weight Assignment for Hyperspectral Target Recognition[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(5): 1448-1456.
[4] HUANG Xin, ZHANG Liangpei, LI Pingxiang. An Adaptive Multiscale Information Fusion Approach for Feature Extraction and Classification of IKONOS Multispectral Imagery over Urban Areas[J]. IEEE Geoscience and Remote Sensing Letters,2007, 4(4): 654-658.
[5] FAUVEL M, TARABKA Y, BENEDIKTSSON J A, etal. Advances in Spectral-spatial Classification of Hyperspectral Images[J]. Proceedings of the IEEE, 2013, 101(3): 652-675.
[6] DELL'ACQUA F, GAMBA P, FERARI A, et al. Exploiting Spectral and Spatial Information in Hyperspectral Urban Data with High Resolution[J]. IEEE Geoscience and Remote Sensing Letters, 2004, 1(4): 322-326.
[7] AYTEKIN O, MURA M D, ULUSOY I, et al. Classification of Hyperspectral Images Based on Weighted DMPS[C]//IEEE International Geoscience and Remote Sensing Symposium.Munich: IEEE, 2012: 4154-4157.
[8] JI Rongrong, GAO Yue, HONG Richang, et al. Spectral-spatial Constraint Hyperspectral Image Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 55(3): 1811-1824.
[9] FAUVEL M, BENEDIKTSSON J A, CHANUSSOT J, et al. Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(11): 3804-3814.
[10] ZHANG Liangpei, HUANG Xin, HUANG Bo, et al. A Pixel Shape Index Coupled with Spectral Information for Classification of High Spatial Resolution Remotely Sensed Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(10): 2950-2961.
[11] HUANG Xin, ZHANG Liangpei, LI Pingxiang. Classification and Extraction of Spatial Features in Urban Areas Using High-resolution Multispectral Imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2007, 4(2): 260-264.
[12] HUANG X, ZHANG L, LI P. A Multiscale Feature Fusion Approach for Classification of Very High Resolution Satellite Imagery Based on Wavelet Transform[J]. International Journal of Remote Sensing, 2008, 29(20): 5923-5941.
[13] HARALICKRM,SHANMUGAMK,DINSTEINI.Textural Features for Image Classification[J]. IEEE Transactions on Systems, Man and Cybernetics,1973, SMC-3(6): 610-621.
[14] PALM, FOODY G M. Feature Selection for Classification of Hyperspectral Data by SVM[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(5):2297-2307.
[15] HUANG Xin, ZHANG Liangpei. An SVM Ensemble Approach Combining Spectral, Structural, and Semantic Features for the Classification of High-Resolution Remotely Sensed Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(1): 257-272.
[16] GREEN AA, BERMAN M, SWITZER P, et al. A Transformation for Ordering Multispectral Data in Terms of Image Quality with Implications for Noise Removal[J]. IEEE Transactionson Geoscience and Remote Sensing, 1988, 26(1): 65-74.
[17] ZHANG Liangpei,HUANG Xin. Object-oriented Subspace Analysis for Airborne Hyperspectral Remote Sensing Imagery[J]. Neurocomputing, 2010, 73(4-6): 927-936.
[18] HU Rongming, HUANG Xiaobing, HUANG Yuancheng. An Enhanced Morphological Building Index for Building Extraction from High-resolution Images[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(5): 514-520. (胡荣明, 黄小兵, 黄远程.增强形态学建筑物指数应用于高分辨率遥感影像中建筑物提取[J].测绘学报, 2014, 43(5): 514-520.)
[19] PESARESI M, BENEDIKTSSON J A. A New Approach for the Morphological Segmentation of High-resolution Satellite Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(2): 309-320.
[20] BENEDIKTSSON J A, PALMASON J A, SVEINSSON J R. Classification of Hyperspectral Data from Urban Areas Based on Extended Morphological Profiles[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3): 480-491.
[21] OUMA Y O, TETUKO J, TATEISHI R. Analysis of Co-occurrence and Discrete Wavelet Transform Textures for Differentiation of Forest and Non-forest Vegetation in Very-high-resolution Optical-sensor Imagery[J]. International Journal of Remote Sensing,2008, 29(12): 3471-3456.
[22] GRUNINGER J, RATKOWSKI A J, HOKEM L. The Sequential Maximum Angle Convex Cone (SMACC) Endmember Model[C]//Proceedings of SPIE5425.Orlando, FL: SPIE,2004: 1-14.
[23] FOODY U M. Thematic Map Comparison: Evaluating the Statistical Significance of Differences in Classification Accuracy[J]. Photogrammetric Engineering & Remote Sensing,2004, 70(5): 627-633.

高光谱影像光谱-空间多特征加权概率融合分类

Hyperspectral Image Classification Based on the Weighted Probabilistic Fusion of Multiple Spectral-spatial Features

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	白坤, 慕晓冬, 陈雪冰, 朱永清, 尤轩昂. 融合半监督学习的无监督遥感影像场景分类[J]. 测绘学报, 2022, 51(5): 691-702.
[2]	王丹菂, 邢帅, 徐青, 林雨准, 李鹏程. 单频机载激光测深海陆回波自动分类方法[J]. 测绘学报, 2022, 51(5): 750-761.
[3]	李凡, 金绍华, 边刚, 崔杨, 汤寓麟, 张永厚. 多波束测深误差改进模型构建与验证[J]. 测绘学报, 2022, 51(5): 762-771.
[4]	孙伟伟, 常明会, 孟祥超, 杨刚, 任凯. 空谱协同多尺度顶点成分分析的高光谱影像端元提取[J]. 测绘学报, 2022, 51(4): 587-598.
[5]	王蓝星, 王群明, 童小华. 融合多光谱影像的高光谱影像厚云去除方法[J]. 测绘学报, 2022, 51(4): 612-621.
[6]	方莉娜, 王爽, 赵志远, 付化胜, 陈崇成. 车载激光点云中交通标线自动分类与矢量化[J]. 测绘学报, 2021, 50(9): 1251-1265.
[7]	杨秋莲, 刘艳飞, 丁乐乐, 孟凡效. 高分影像场景分类的半监督深度卷积神经网络学习方法[J]. 测绘学报, 2021, 50(7): 930-938.
[8]	纪雪, 唐秋华, 陈义兰, 李杰, 丁德秋. 联合支持向量机和增强学习算法的多波束声学底质分类[J]. 测绘学报, 2021, 50(7): 972-981.
[9]	董卫华, 王圣凯, 王雪元, 杨天宇. 地图线状要素眼动识别的朴素贝叶斯方法[J]. 测绘学报, 2021, 50(6): 749-756.
[10]	王思, 王光霞, 田江鹏. 面向位置聚合的泛在地图信息分类模型[J]. 测绘学报, 2021, 50(6): 789-799.
[11]	施慧慧, 徐雁南, 滕文秀, 王妮. 高分辨率遥感影像深度迁移可变形卷积的场景分类法[J]. 测绘学报, 2021, 50(5): 652-663.
[12]	张红, 吴智伟, 王继成, 高培超. 高光谱图像分类的Wasserstein配置熵非监督波段选择方法[J]. 测绘学报, 2021, 50(3): 405-415.
[13]	黄远程, 薛园园, 李朋飞. 高光谱影像子空间分析孤立森林异常目标探测方法[J]. 测绘学报, 2021, 50(3): 416-425.
[14]	方莉娜, 沈贵熙, 游志龙, 郭迎亚, 付化胜, 赵志远, 陈崇成. 融合点云和多视图的车载激光点云路侧多目标识别[J]. 测绘学报, 2021, 50(11): 1558-1573.
[15]	傅琛, 黄升钶, 汤焱, 吴杭彬, 刘春, 姚连璧, 黄炜. 结合行驶场景语义的轨迹-路网实时匹配方法[J]. 测绘学报, 2021, 50(11): 1617-1627.