基于LTP编码的分数阶Gabor高光谱遥感图像分类  

Classification of Hyperspectral Remote Sensing Images Based on LTP Encoded Fractional Order Gabor

作　　者：王亚丽 李丙春 刘晨 要秀红 代明军 贾森[2] WANG Yali;LI Bingchun;LIU Chen;YAO Xiuhong;DAI Mingjun;JIA Sen(College of Computer Science and technology Kashi University,Kashi 844000 China;College of Computer Science and Software Engineering Shenzhen University,Shenzhen 518000 China)

机构地区：[1]喀什大学计算机科学与技术学院,新疆喀什844000 [2]深圳大学计算机与软件工程学院,广东深圳518000

出　　处：《电光与控制》2024年第11期96-101,共6页Electronics Optics & Control

基　　金：高校科研计划项目青年项目(XJEDU2022P080)。

摘　　要：为有效提取高光谱遥感图像的空谱结构特征、增强特征鉴别性及提高分类精度,提出基于局部三元模式编码的分数阶Gabor高光谱遥感图像分类方法。首先,用分数阶三维Gabor滤波器进行局部特征的有效提取;其次,对Gabor相位特征进行局部三元模式编码,以提高特征的可鉴别性;然后,通过随机森林算法对Gabor相位特征进行分类以获得置信度立方体;最后,融合多组基于Gabor的置信立方体,提取具有互补性、强表达性的纹理特征。选择3个训练样本分别在Indian Pines、Salinas、Trento数据集上验证,总体分类精度分别达到63.50%、81.78%、86.89%。实验结果表明,所提的方法具有更好的分类性能。To effectively extract the spatial spectral structural features of hyperspectral remote sensing images enhance feature discrimination and improve classification accuracy a classification method for hyperspectral remote sensing images is proposed based on local ternary pattern encoded fractional order Gabor.Firstly effective extraction of local features is achieved using fractional order 3D Gabor filters.Secondly local ternary mode encoding is applied to Gabor phase features to improve their discriminability.Then Gabor phase features are classified using a random forest algorithm to obtain confidence cubes.Finally by fusing multiple sets of Gabor based confidence cubes the textural features with complementarity and strong expressivity are extracted.Three training samples are selected for validation on the Indian Pines Salinas and Trento datasets and the overall classification accuracy reaches 63.50%81.78%and 86.89%respectively.The experimental results verifies that the proposed method has better classification performance.

关 键 词：高光谱图像分类 GABOR滤波器 分数阶滤波器 局部三元模式 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]