Random Forest Ensembles and Extended Multiextinction Profiles for Hyperspectral Image Classification
Random Forest Ensembles and Extended Multiextinction Profiles for Hyperspectral Image Classification
复制标题
DOI：
10.1109/tgrs.2017.2744662
复制
发表时间：
2018
影响因子：
8.2
通讯作者：
J. Xia;Pedram Ghamisi;N. Yokoya;A. Iwasaki
中科院分区：
文献类型：
--
作者：
J. Xia;Pedram Ghamisi;N. Yokoya;A. Iwasaki
提出了基于随机森林（RF）集成和扩展多消光剖面（EMEPs）的高光谱图像分类技术，作为提高性能的一种手段。为此，五种策略-装袋，升压，随机子空间，旋转为基础的，和升压旋转为基础的-被用来构建RF合奏。EP，这是基于一个面向极值的连接过滤技术，被施加到与独立成分分析提取的第一信息成分相关联的图像，导致一组EMEP。所提出的方法的有效性进行了研究的两个基准高光谱图像：帕维亚大学和印度松树。比较实验评估揭示了所提出的方法，特别是那些采用基于旋转和增强旋转的方法的上级性能。另一个优点是CPU处理时间是可以接受的。
Classification techniques for hyperspectral images based on random forest (RF) ensembles and extended multiextinction profiles (EMEPs) are proposed as a means of improving performance. To this end, five strategies—bagging, boosting, random subspace, rotation-based, and boosted rotation-based—are used to construct the RF ensembles. EPs, which are based on an extrema-oriented connected filtering technique, are applied to the images associated with the first informative components extracted by independent component analysis, leading to a set of EMEPs. The effectiveness of the proposed method is investigated on two benchmark hyperspectral images: the University of Pavia and Indian Pines. Comparative experimental evaluations reveal the superior performance of the proposed methods, especially those employing rotation-based and boosted rotation-based approaches. An additional advantage is that the CPU processing time is acceptable.