English

应用科学学报 >

2011 , Vol. 29 >Issue 6: 598 - 604

DOI: https://doi.org/10.3969/j.issn.0255-8297.2011.06.008

信号与信息处理

用随机决策树群算法进行高光谱遥感影像分类

展开
  • 1. 中南大学地球科学与信息物理学院，长沙410083
    2. 河南理工大学测绘与国土信息工程学院，河南焦作454000
    3. 中南大学冶金科学与工程学院，长沙410083
    4. 国家环境保护总局华南环境科学研究所，广州510655
作者简介：胥海威，博士生，研究方向：遥感分类与数字图像处理等，E-mail: haiweixu@126.com；杨敏华，教授，博导，研究方向：高光谱遥感、精细农业等，E-mail: yangmhua@163.com

收稿日期: 2011-01-11

  修回日期: 2011-05-04

  网络出版日期: 2011-11-30

基金资助

国家自然科学基金(No.50830301)；国家杰出青年科学基金(No.50925417)资助

收起

Hyperspectral Remote Sensing Image Classification with Extremely Randomized Clustering Forests

Expand
  • 1. School of Geosciences and Info-physics, Central South University, Changsha 410083, China
    2. School of Surveying & Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000,
    Henan Province, China
    3. School of Metallurgical Science and Engineering, Central South University, Changsha 410083, China
    4. South China Institute of Environmental Sciences, Ministry of Environmental Protection,
    Guangzhou 510655, China

Received date: 2011-01-11

  Revised date: 2011-05-04

  Online published: 2011-11-30

Fold

摘要

摘要： 高光谱影像具有丰富的光谱信息，与全色、多光谱影像相比能更好地进行地面目标的分类识别. 该文对决策树分类算法的优劣进行分析，引入随机决策树群算法，对青海省祁连县Hyperion高光谱影像和IRS-P6影像数据进行实验，使用子空间划分和光谱距离进行降维后，分别采用支持向量机、神经网络、最大似然法进行分类，并与随机决策树群算法分类结果进行比较. 结果表明，该算法表现最优且无需降维预处理，可广泛应用于高光谱遥感领域.

关键词： 高光谱遥感; 影像自动分类; 模式分类; 土地覆盖分类; 随机决策树群算法

本文引用格式

胥海威1， 杨敏华1， 韩瑞梅2， 王振兴3;4 . 用随机决策树群算法进行高光谱遥感影像分类[J]. 应用科学学报, 2011 , 29(6) : 598 -604 . DOI: 10.3969/j.issn.0255-8297.2011.06.008

Abstract

Hyperspectral images contain rich spectral information and have better performance in ground target recognition than panchromatic and multispectral images. An extremely randomized clustering forests (ERC-Forests) algorithm is introduced after analysis of the decision tree algorithm. Hyperion hyperspectral images and IRS-p6 image data of Qilian County, Qinghai Province, are used in the experiment. After dimension reduction with subspace methods and based on the spectral range, support vector machine (SVM), neural network (NN) and maximum likelihood (MLC) are used for classification. The results are compared with that of random decision trees algorithm, showing that the extremely randomized clustering forests algorithm is better, without dimension reduction. The method is widely applicable to hyperspectral remote sensing.

Key words： hyperspectral remote sensing; automatic image classification; pattern classification; land cover classification; extremely randomized clustering forests (ERC-forests)

Options
文章导航

/

〈 〉