CAJ | 학술논문

根据高光谱遥感图像的特点及二维Gabor滤波器纹理分割的原理，提出了一种基于三维Gabor 滤波器的高光谱遥感图像分类方法。三维Gabor滤波器能够对高光谱遥感图像所有波段同时进行滤波，将大量的图像信息抽取为少量的不同尺寸、方向和波谱的响应，极大减少了高光谱遥感图像纹理信息提取的计算量。利用不同方向和尺寸的三维Gabor滤波器对祁连山黑河流域上游地区的 Hyperion影像全波段进行滤波处理，获取26个纹理响应特征，并分析不同纹理对不同地物的区分度。利用自动子空间划分的波段指数（BI）进行波段选择，选取不同的波段组合进行试验，寻找最佳降维幅度。按照纹理对不同地物响应的区分度逐一加入三维Gabor纹理特征，利用三维Gabor纹理辅助光谱信息，运用支持向量机（SVM）的方法进行监督分类。结果表明，基于三维Gabor纹理和自动子空间BI 波段选择的SVM分类方法能够在有效降低光谱维数的同时，提高高光谱遥感图像分类的精度和效率。
근거고광보요감도상적특점급이유Gabor려파기문리분할적원리，제출료일충기우삼유Gabor 려파기적고광보요감도상분류방법。삼유Gabor려파기능구대고광보요감도상소유파단동시진행려파，장대량적도상신식추취위소량적불동척촌、방향화파보적향응，겁대감소료고광보요감도상문리신식제취적계산량。이용불동방향화척촌적삼유Gabor려파기대기련산흑하류역상유지구적 Hyperion영상전파단진행려파처리，획취26개문리향응특정，병분석불동문리대불동지물적구분도。이용자동자공간화분적파단지수（BI）진행파단선택，선취불동적파단조합진행시험，심조최가강유폭도。안조문리대불동지물향응적구분도축일가입삼유Gabor문리특정，이용삼유Gabor문리보조광보신식，운용지지향량궤（SVM）적방법진행감독분류。결과표명，기우삼유Gabor문리화자동자공간BI 파단선택적SVM분류방법능구재유효강저광보유수적동시，제고고광보요감도상분류적정도화효솔。
A three-dimensional Gabor filter was developed for classification of hyperspectral remote sensing image.This method is based on the characteristics of hyperspectral image and the principle of texture extraction with 2-D Gabor filters.Three-dimen-sional Gabor filter is able to filter all the bands of hyperspectral image simultaneously,capturing the specific responses in differ-ent scales,orientations,and spectral-dependent properties from enormous image information,which greatly reduces the time consumption in hyperspectral image texture extraction,and solve the overlay difficulties of filtered spectrums.Using the de-signed three-dimensional Gabor filters in different scales and orientations,Hyperion image which covers the typical area of Qi Lian Mountain was processed with full bands to get 26 Gabor texture features and the spatial differences of Gabor feature tex-tures corresponding to each land types were analyzed.On the basis of automatic subspace separation,the dimensions of the hy-perspectral image were reduced by band index (BI)method which provides different band combinations for classification in order to search for the optimal magnitude of dimension reduction.Adding three-dimensional Gabor texture features successively ac-cording to its discrimination to the given land types,supervised classification was carried out with the classifier support vector machines (SVM).It is shown that the method using three-dimensional Gabor texture features and BI band selection based on au-tomatic subspace separation for hyperspectral image classification can not only reduce dimensions,but also improve the classifica-tion accuracy and efficiency of hyperspectral image.