收稿日期: 2014-12-04
修回日期: 2015-05-20
网络出版日期: 2015-11-15
基金资助
国家科技部国际科技合作专项(2013DFG21640)和中国科学院百人计划专项(09ZZ06101B)资助
Image classification for giant panda habitat using tasseled cap and matched filtering methods
Received date: 2014-12-04
Revised date: 2015-05-20
Online published: 2015-11-15
在卧龙大熊猫自然保护区,难以获取高质量的光学遥感影像,加之地形和植被类型复杂多样,地物分类精度低,对利用遥感技术研究大熊猫生境造成了困难.为此,本工作探究一种提高遥感分类精度的方法.首先分别利用缨帽变换和匹配滤波方法提取影像的亮度、绿度、湿度和丰度等特征,建立基于多特征数据的决策树分类规则进行分类,最后利用野外实测数据对分类结果进行验证.研究结果表明:绿度特征对提取林地非常有效,湿度分量可以区分草甸与灌丛,亮度特征则提高了雪地的分类精度.匹配滤波可以实现混合像元分解,去除部分噪声并快速探测目标地物的波谱特征.基于多特征数据决策树遥感分类的总体精度达到83.33%,比传统的最大似然法分类精度提高8.67%.本文方法在卧龙大熊猫自然保护区等地物分类中取得了较好的应用效果.
杨娅楠 , 习晓环 , 王成 , 王金亮 , 曾鸿程 . 基于缨帽变换与匹配滤波的大熊猫生境影像分类[J]. 中国科学院大学学报, 2015 , 32(6) : 797 -802 . DOI: 10.7523/j.issn.2095-6134.2015.06.011
It is difficult to acquire optical remote sensing images with good quality in Wolong nature reserve because of the weather conditions. Meanwhile, the terrain is very complex and the species are very rich, which leads to poor classification results when using Landsat TM data to study the panda's habitat. In this work, an effective classification method is proposed to improve classification accuracy. First, three features including greenness, brightness, and wetness are extracted from Landsat TM image by tasseled cap transformation. Second, the abundance index is deduced by matched filtering method. Then, the rules for decision tree are established by combining the results of the tasseled cap and matched filtering methods, and used to map the land use classification distribution in the study area. Finally, the classification results are validated by field measurements. The results show that the greenness is an effective measurement for extracting forest, wetness can distinguish between meadow and shrub, and brightness can improve the classification accuracy for snow. A matched filtering method for spectral unmixing removes image noise and effectively detects the spectra of targets. The overall accuracy of the decision tree classifier reaches 83.33%, which is 7.67% higher than that of the maximum likelihood classifier. This method improves the effectiveness and accuracy of image classification in Wolong nature reserve for giant pandas.
[1] 申文明, 王文杰, 罗海江, 等. 基于决策树分类技术的遥感影像分类方法研究[J]. 遥感技术与应用, 2007, 22(3):333-337.
[2] 曾珍, 罗怀斌, 范建容, 等. 四川宝兴森林分布及受损特征[J]. 山地学报, 2014, 32(3):284-292.
[3] 郭航, 张晓丽. 基于遥感技术的植被分类研究现状与发展趋势[J]. 世界林业研究, 2007, 20(3):14-19.
[4] 于菲菲, 曾永年, 徐艳艳, 等. 基于植被分区的多特征遥感智能分类[J]. 国土资源遥感, 2014, 26(1):63-70.
[5] 刘娟, 蔡演军, 王瑾. 青海湖流域土壤遥感分类[J]. 国土资源遥感, 2014, 26(1):57-62.
[6] Healey S P, Cohen W B, Yang Z Q, et al. Comparison of tasseled cap-based Landsat data structures for US in forest disturbance detection[J]. Remote Sensing of Environment, 2005, 97(3):301-310.
[7] 张景奇, 关威, 孙萍, 等. 基于K-T变换的地表水体信息遥感自动提取模型[J]. 中国水土保持科学, 2011, 9(3):88-92.
[8] 汪燕, 董张玉. 基于缨帽变换影像融合的遥感影像植被信息提取[J]. 地理空间信息, 2013, 11(4):85-86.
[9] 宋慧. 基于混合像元分解的土地利用分类. 济南:济南大学, 2013.
[10] 陶秋香. 植被高光谱遥感分类方法研究[J]. 山东科技大学学报, 2007, 26(5):61-65.
[11] 甘甫平, 王润生, 马蔼乃, 等. 基于光谱匹配滤波的蚀变信息提取[J]. 中国图象图形学报, 2003, 8(2):147-150.
[12] 刘衍宏, 刘少峰, 张川, 等. 基于Hyperion数据的粘土矿物权重信息提取研究:以江西省赣州地区为例[J]. 国土资源遥感, 2010, 22(3):26-29.
[13] Pour A B, Hashim M, Marghany M. Using spectral mapping techniques on short wave infrared bands of ASTER remote sensing data for alteration mineral mapping in Southeast Iran[J]. International Journal of the Physical Sciences, 2011, 6(4):917-929.
[14] 陈利顶, 刘雪华, 傅伯杰. 卧龙自然保护区大熊猫生境破碎化[J]. 生态学报, 1999, 19(3):291-297.
[15] 陈利, 林辉. 基于K-T变换和主成分变换的植被信息提取[J]. 中南林业科技大学学报, 2014, 34(6):81-84.
[16] 赵英时. 遥感应用分析原理与方法[M]. 北京:科学出版社, 2003:188-189.
[17] 梅安新, 彭望琭, 秦其明, 等. 遥感导论[M]. 北京:高等教育出版社, 2001:126.
[18] 戴昌达, 姜小光, 唐伶俐. 遥感图像应用处理与分析[M]. 北京:清华大学出版社, 2004:110-113.
[19] 邓书斌. ENVI遥感图像处理方法[M]. 北京:科学出版社, 2010:356-357.
[20] 王强. Hyperion高光谱数据进行混合像元分解研究[D]. 哈尔滨:东北林业大学, 2006.
/
| 〈 |
|
〉 |
