Kernel Supervised Ensemble Classifier for the Classification of Hyperspectral Data Using Few Labeled Samples

Remote Sensing

Zhaohui Xue¹  Jocelyn Chanussot²  Junshi Xia³  Peijun Du⁴  Xiangjian Xie⁴  Jike Chen⁴ 

[1] Department of Geomatics, Hohai University, 8 West of Focheng Road, 211100 Nanjing, China;Grenoble-Image-sPeech-Signal-Automatics Lab (GIPSA)-lab, Grenoble Institute of Technology, 38400 Grenoble, France;Intégration, du Matériau au Système (IMS), Univsité de Bordeaux, UMR 5218, F-33405 Talence, France;Key Laboratory for Satellite Mapping Technology and Applications of State Administration of Surveying, Mapping and Geoinformation of China, Nanjing University, 210093 Nanjing, China;

关键词: Rotation Forest;    Kernel-based methods;    Kernel Orthonormalized Partial Least Square;    classification;    hyperspectral data;   

DOI  :  10.3390/rs8070601

来源: DOAJ

【 摘 要 】

Kernel-based methods and ensemble learning are two important paradigms for the classification of hyperspectral remote sensing images. However, they were developed in parallel with different principles. In this paper, we aim to combine the advantages of kernel and ensemble methods by proposing a kernel supervised ensemble classification method. In particular, the proposed method, namely RoF-KOPLS, combines the merits of ensemble feature learning (i.e., Rotation Forest (RoF)) and kernel supervised learning (i.e., Kernel Orthonormalized Partial Least Square (KOPLS)). In particular, the feature space is randomly split into K disjoint subspace and KOPLS is applied to each subspace to produce the new features set for the training of decision tree classifier. The final classification result is assigned to the corresponding class by the majority voting rule. Experimental results on two hyperspectral airborne images demonstrated that RoF-KOPLS with radial basis function (RBF) kernel yields the best classification accuracies due to the ability of improving the accuracies of base classifiers and the diversity within the ensemble, especially for the very limited training set. Furthermore, our proposed method is insensitive to the number of subsets.

【 授权许可】

Unknown