| 面向高光谱图像分类的超像素级Gabor特征融合方法研究 |
| |
| 引用本文： | 贾森,吴奎霖,朱家松,李清泉.面向高光谱图像分类的超像素级Gabor特征融合方法研究[J].南京气象学院学报,2018,10(1):72-80. |
| |
| 作者姓名： | 贾森 吴奎霖 朱家松 李清泉 |
| |
| 作者单位： | 深圳大学 计算机与软件学院, 深圳, 518060;深圳大学 空间信息智能感知与服务深圳市重点实验室, 深圳, 518060,深圳大学 计算机与软件学院, 深圳, 518060,深圳大学 空间信息智能感知与服务深圳市重点实验室, 深圳, 518060,深圳大学 空间信息智能感知与服务深圳市重点实验室, 深圳, 518060 |
| |
| 基金项目： | 国家自然科学基金（61671307）；广东特支计划科技青年拔尖人才（2015TQ01X238）；深圳市科技研发资金基础研究计划（JCYJ20160422093647889） |
| |
| 摘 要： | 由于高光谱图像中的地物空间分布具有规整性和局部连续性，同时超像素分割是一种将空间图像分割成多个同质区域的有效方法，因此从超像素的角度进行高光谱图像分类将具有重要意义.本文提出了一种超像素级Gabor特征融合的高光谱图像分类方法，简称为SPGF.首先，使用一组预定义的二维Gabor滤波器与原始高光谱图像进行卷积运算，提取有效特征.同时，利用简单线性迭代聚类（简称SLIC）超像素分割方法将原始高光谱图像划分成互不重叠的超像素.然后，对于每个Gabor特征模块，利用支持向量机分类器进行分类，并使用多数投票策略实现各模块分类结果的融合.最后，使用通过SLIC算法得到的超像素图对分类结果进行修正.在2个真实高光谱数据集上的实验结果表明，本文提出的SPGF方法能够比领域内的一些经典算法获得更高的分类效果.
|
| 关 键 词： | 高光谱图像 超像素分割 Gabor小波 |
| 收稿时间： | 2017/12/1 0:00:00 |
Superpixel-level Gabor feature fusion method for hyperspectral image classification |
| |
| JIA Sen,WU Kuilin,ZHU Jiasong and LI Qingquan.Superpixel-level Gabor feature fusion method for hyperspectral image classification[J].Journal of Nanjing Institute of Meteorology,2018,10(1):72-80. |
| |
| Authors: | JIA Sen WU Kuilin ZHU Jiasong and LI Qingquan |
| |
| Institution: | College of Computer Science & Software Engineering, Shenzhen University, Shenzhen 518060;Shenzhen Key Laboratory of Spatial Smart Sensing and Services, Shenzhen University, Shenzhen 518060,College of Computer Science & Software Engineering, Shenzhen University, Shenzhen 518060,Shenzhen Key Laboratory of Spatial Smart Sensing and Services, Shenzhen University, Shenzhen 518060 and Shenzhen Key Laboratory of Spatial Smart Sensing and Services, Shenzhen University, Shenzhen 518060 |
| |
| Abstract: | Since the spatial distribution of surface materials is usually regular and locally continuous,it is reasonable to classify the hyperspectral images (HSI) from superpixel viewpoint,which can be considered as a process of segmenting the spatial image into many regions.In this paper,a superpixel-level Gabor feature fusion approach (abbreviated as SPGF) has been proposed for hyperspectral image classification.Firstly,a set of predefined two-dimensional (2D) Gabor filters are applied to hyperspectral images to extract sufficient features.Meanwhile,a classic superpixel segmentation method,called simple linear iterative clustering (SLIC),is adopted to divide the original hyperspectral image into disjoint superpixels.Secondly,the Support Vector Machine classifier (SVM) is applied on each extracted 2D Gabor feature cube,and the majority voting strategy is adopted to combine the classification results.Finally,the superpixel map obtained by SLIC is used to regularize the classification map.Extensive experiments on two real hyperspectral data sets have demonstrated higher performance of the proposed SPGF approach over several state-of-the-art methods in the literature. |
| |
| Keywords: | hyperspectral image superpixel segmentation Gabor wavelet |
|
| 点击此处可从《南京气象学院学报》浏览原始摘要信息 |
| 点击此处可从《南京气象学院学报》下载免费的PDF全文 |
|
