基于高光谱图像的协同分层波谱识别--以兰州、榆林地区为例
投稿时间:2018-07-10  修订日期:2020-01-17  点此下载全文
引用本文:刘炜,孙海霞,杨晓波.基于高光谱图像的协同分层波谱识别--以兰州、榆林地区为例[J].红外与毫米波学报,2020,39(1):99~110].LIU Wei,SUN Hai-Xia,YANG Xiao-Bo.Hierarchical spectrum recognition based on hyper-spectral images[J].J.Infrared Millim.Waves,2020,39(1):99~110.]
摘要点击次数: 14
全文下载次数: 8
作者单位邮编
刘炜 西藏民族大学 西藏光信息处理与可视化技术重点实验室陕西 咸阳 712082 712082
孙海霞 西藏民族大学 西藏光信息处理与可视化技术重点实验室陕西 咸阳 712082 
杨晓波 西藏民族大学 西藏光信息处理与可视化技术重点实验室陕西 咸阳 712082 
基金项目:国家自然科学基金资助项目 41361044;西藏自治区自然科学基金项目 XZ2019ZRG-43国家自然科学基金资助项目(41361044 );西藏自治区自然科学基金项目(XZ2019ZRG-43)
中文摘要:提出协同分层波谱识别法,分别从兰州、榆林市Hyperion高光谱图像上识别9种目标地类,并与SVM监督分类对比。针对Hyperion图像波谱识别的4个难点:光谱信息高保真融合、敏感谱段提取、“椒盐效应”去除、 消除“同物异谱” 现象导致的误判,协同应用WP-GS融合、导数变换、4尺度面向对象分割和多谱段SAM解决上述难点,并基于Hyperion导数变换图像分析波谱变化特征、提取敏感谱段、从4个尺度层依次识别9种目标地类,然后根据目视评判和定量评价,与综合使用Gram-Schmidt光谱锐化融合/Savitzky-Golay卷积滤波/PCA变换的SVM监督分类结果比较识别精度。实验结果表明WP-GS融合的光谱保真效果优于Gram-Schmidt光谱锐化;4尺度面向对象分割抑制“椒盐效应”的效果优于Savitzky-Golay卷积滤波、移动均值滤波;多谱段SAM利用导数波谱特征能够消除因照度不同对同一类别地物的误判。采用协同分层波谱识别法,兰州市Hyperion图像波谱识别的总体精度、Kappa系数分别为89.52%、0.852,较SVM分类分别提高18.68%和17.52%;榆林市Hyperion图像识别地物的总体精度、Kappa系数分别为91.12%、0.873,较SVM分类分别提高17.80%和16.89%。协同分层波谱识别法应用多种技术一体化解决Hyperion图像应用难点,有效利用导数波谱变化特征提取目标敏感谱段,在复杂环境下识别目标地类的能力优于SVM监督分类。
中文关键词:星载高光谱图像  导数波谱特征  敏感谱段  同物异谱  多尺度  多谱段SAM
 
Hierarchical spectrum recognition based on hyper-spectral images
Abstract:Hierarchical spectrum recognition is pointed out in the aspect of hyper-spectralimage classification using Hyperion imagesof Lanzhou and Yulin in China, by the comparison study of SVM supervised classification.There are 4 problems for hyper-spectralimage classification: spectral information fidelity image fusion, extraction of sensitive band, removal of "salt and pepper effect" which avoids misclassification for "same body with different spectrum" phenomenon. Hierarchical spectrum recognitionputs forward 4 methods for solving these problems,which are WP-GS image fusion, derivative transformation, object oriented segmentation with 4 scales and multispectral SAM. Hierarchical spectrum recognitioncan identify 9 kinds land type exactly, based on sensitive bands extracted from derivative transformationimage. Visual examination and quantifiable evaluation have been executed to verify authenticity. By contrast, SVM supervised classification is tested, with Gram-Schmidt Spectral sharpening/ Savitzky-Golay convolution filtering/PCA transformation.Using the method of hierarchical spectrum recognition proposed in this paper, the above 4 problems for hyper-spectralimage classification are solved, and good classification results is achieved, with overall classification accuracy and kappa coefficient as 89.52%, 0.852 in Lanzhou, 91.12%、0.873 in Yulin. Growth of 18.68% in Lanzhou and 17.80% in Yulin for overall classification accuracy, as well as17.52% in Lanzhou and 16.89% in Yulin for kappa coefficient are achieved compared with SVM supervised classification.Hierarchical spectrum recognition can provide more accurate recognition results are provided for Hyperion images classification in comparison with SVM supervised classification .
keywords:satellite-borne hyper-spectral image  derivative spectrum feature  sensitive bands  same body with different spectrum  multi-scale  multispectral SAM
查看全文  HTML  查看/发表评论  下载PDF阅读器

版权所有:《红外与毫米波学报》编辑部