基于偏振光谱BRDF图像的物质分类

陈超; 赵永强; 程咏梅; 潘泉; 罗丽

光子学报, 2010, 39 (6): 1026, 网络出版: 2010-08-31

基于偏振光谱BRDF图像的物质分类

Materials Classification Based on Spectropolarimetric BRDF Imagery

论文大纲

陈超 ^*赵永强程咏梅潘泉罗丽

作者单位

西北工业大学自动化学院,西安 710072

偏振光谱二向反射分布函数物质分类特征选择支撑矢量机 Spectropolarimetric BRDF Material classification Feature selection SVM

摘要

提出一种基于偏振光谱二向反射分布函数图像的物质自动分类方法，该方法主要选择偏振光谱二向反射分布函数信息作为新的特征用于物质自动分类.采用支撑向量机的分类方法对不同的天气条件(晴天、多云、阴天)下处于杂乱的自然草地背景环境中的典型目标进行分类，最后比较三种不同特征选择对于分类准确度的影响.采取三种不同的特征选取方法，分别为采用单一的光谱特征、偏振光谱特征及偏振光谱二向反射分布函数特征.最后通过实验得出：将偏振光谱二向反射分布函数作为分类特征在三种不同的天气情况下，分类准确度都较高，特别是在阴天天气条件下，分类准确度明显高于其它两种特征选择.即使是在阴天低照度下的场景中，当不同目标和背景之间的灰度很接近时，采用本文方法也能准确的进行自动分类.

Abstract

A new classify method based on spectropolarimetric BRDF imagery is proposed.The performances of three different selected features in classifyication results under various weather conditions including sunny sky,cloudy,and dark sky are emphasized.The three selected features are material spectral information,spectropolarimetric information,and spectropolarimetric BRDF information respectively.Support Vector Machine method is used to classify targets in clutter grass environments,then the classify results based on spectropolarimetric BRDF features are compared with the other two features under the three different weather conditions respectively.The results show that the method based on spectropolarimetric BRDF features performs the best among the three,no matter what the weather conditions are,and its advantage shows most evidently especially in the dark sky.Selecting the spectropolarimetric BRDF information as features in the materials classification will enhance the precision at most time,even in the case when the gray values between backgrounds and targets are very near.

参考文献

[1] 王道荣，赵永强，潘泉.基于模糊聚类和证据理论的光谱偏振图像分类［J］.光子学报,2007,36(12):2365-2370.

WANG Dao-rong,ZHAO Yong-qiang,PAN Quan.Classification of spectropolarimetric imagery based on fuzzy clutter and evidence theory［J］.Acta Photonica Sinica,2007,36(12):2365-2370.

[2] 孙晓兵，洪津，乔延利.一种基于偏振角参量图像的特征提取方法研究［J］.遥感技术与应用,2005,20(2):256-260.

SUN Xiao-bing,Hong Jin,Qiao Hong-li.The study of method for feature extraction based on angle of polarization parameter image［J］.Remote Sensing Technology and Application,2005,20(2):256-260.

[3] 赵永强，潘泉，张洪才.自适应多波段偏振图像融合研究［J］.光子学报,2007,36(7):1356-1359.

ZHAO Yong-qiang,PAN Quan,ZHANG Hong-cai.Study of adaptive multi-band polarization image fusion［J］.Acta Photonica Sinica,2007,36(7):1356-1359.

[4] 赵永强，张洪才，潘泉.基于偏振特征的目标检测［J］.量子电子学报,2003,20(6):685-688.

ZHAO Yong-qiang,ZHANG Hong-cai,Pan Quan.Object detection through polarization characteristics［J］.Chinese Journal of Quantum Electronics,2003,20(6):685-688.

[5] . Review of passive imaging polarimetry for remote sensing applications[J]. Appl Opt, 2006, 45(22): 5453-5469.

[6] 宋芳妮,范闻捷,刘强,等.一种获取野外实测目标物BRDF的方法［J］.遥感学报,2007,11(3):296-302.

SONG Fang-ni,FAN Wen-jie,LIU Qiang,et al.A method of acquiring BRDF of objects in the field［J］.Journal of Remote Sensing,2007,11(3):296-302.

[7] 孙玮,刘政凯,单列.利用偏振技术识别人造目标［J］.光学技术,2004,30(3):267-269.

SUN Wei,LIU Zheng-kai,SHAN Lie.Manmade objects recognition with polarization information［J］.Optical Technique,2004,30(3):267-269.

[8] 王新,王学勤,孙金祚.基于偏振成像的目标识别技术研究［J］.烟台大学学报(自然科学与工程版),2007,20(2):95-98.

WANG Xin,WANG Xue-qin,SUN Jin-zuo.Study of target identification based on polarization imaging［J］.Journal of Yantai University(Natural Science and Engineering edirion,2007,20(2):95-98.

[9] 彭钦华,于国萍,唐若愚,等.自然光照下反射光的偏振特性研究［J］.光学与光电技术,2006,4(2):65-68.

PENG Qin-hua,Yu Guo-ping,TANG Ruo-yu,et al.Polarization characteristics of reflected light under natural lighting［J］.Optics & Optoelectronic Technology, 2006,4(2):65-68.

[10] NICODEMUS F E R,HSIA J C,GINSBERG J J,et al.Geometrical considerations and nomenclature for reflectance［R］.Final Report National Bureau of Standards,Washington,DC Inst for Basic Standards,1977.

[11] JAMES R S.A polarized clutter measurement technique based on the governing equation for polarimetric remote sensing in the visible to near infrared［C］.SPIE,2005,5811:34-45.

[12] . Classification of hyperspectral remote sensing images with support vector machines[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(8): 1778-1790.

[13] . A relative evaluation of multiclass image classification by support vector machines[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(6): 1335-1343.

陈超, 赵永强, 程咏梅, 潘泉, 罗丽. 基于偏振光谱BRDF图像的物质分类[J]. 光子学报, 2010, 39(6): 1026. CHEN Chao, ZHAO Yong-qiang, CHENG Yong-mei, PAN Quan, LUO Li. Materials Classification Based on Spectropolarimetric BRDF Imagery[J]. ACTA PHOTONICA SINICA, 2010, 39(6): 1026.

基于偏振光谱BRDF图像的物质分类

关于本站 Cookie 的使用提示

全站搜索

基于偏振光谱BRDF图像的物质分类

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索