Please wait a minute...
img

官方微信

遥感技术与应用  2011, Vol. 26 Issue (3): 322-327    DOI: 10.11873/j.issn.1004-0323.2011.3.322
图像与数据处理     
基于多元局部二值模式的遥感图像纹理提取与分类
宋翠玉1,李培军2,杨锋杰1
(1.山东科技大学山东省沉积成矿作用与沉积矿产重点实验室,山东 青岛266510;
2.北京大学遥感与地理信息系统研究所,北京100871)
Remote Sensing Image Classification based on Texture Features by Multivariate Local Binary Pattern
SONG Cui-yu1,LI Pei-jun2,YANG Feng-jie1
(1.Shandong University of Science and Technology,Shandong Provincial Key Laboratory of
Depositional Mineralization & Sedimentary Minerals,Qingdao 266510,China; 
2.Remote Sensing and GIS Institute,Peking University,Beijing 100871,China)
 全文: PDF(5315 KB)  
摘要:

纹理信息已经广泛应用于遥感图像分类以提高地物识别的精度。为了描述多光谱遥感图像多个波段之间的空间信息变化规律,将新型纹理提取算法局部二值模式(Local Binary Pattern,LBP)扩展到多维空间以计算多元纹理。单波段纹理信息、多元纹理信息分别与光谱信息结合后用于遥感图像分类,并根据分类精度评价其有效性。实验表明,加入单波段或多元纹理信息的分类精度均比光谱分类有明显提高;基于多元LBP纹理的分类不仅避免了传统单波段纹理参与分类前进行波段选择的繁琐,其精度还能与基于单波段纹理分类精度最高者相当或者更高。

关键词: 局部二值模式多元纹理纹理提取支持向量机(SVM)精度评价    
Abstract:

Texture has been widely used in remote sensing image classification to improve the classification result.In this paper,the recently developed texture measure Local Binary Pattern (LBP) was extended to a multivariate version to characterize the multivariate spatial correlation among multiple bands of multispectral image.The derived single\|band and multivariate texture features were then individually combined with the spectral data in image classification to evaluate the performance of the texture measure.Experiments demonstrate that compared with spectral classification,the classification accuracies can be significantly improved when the single\|band or the multivariate LBP texture features were included.The results also show that the classifications by incorporating multivariate texture show high overall accuracies,which are better than or at least comparable with the best classification result by adding the existing LBP texture;the use of multivariate LBP texture in image classification avoids the band selection procedure which is required in the incorporation of traditional LBP texture into image classification.

Key words: Local Binary Pattern    Multivariate texture    Texture extraction    Support Vector Machine(SVM)    Assessment of accuracy
收稿日期: 2010-12-13 出版日期: 2013-01-23
:  TP 75  
作者简介: 宋翠玉(1982-),女,山东泰安人,讲师,在读博士生,主要从事遥感信息处理应用研究。Email:songcuiyu_19@163.com。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
宋翠玉
李培军
杨锋杰

引用本文:

宋翠玉,李培军,杨锋杰. 基于多元局部二值模式的遥感图像纹理提取与分类[J]. 遥感技术与应用, 2011, 26(3): 322-327.

SONG Cui-yu,LI Pei-jun,YANG Feng-jie. Remote Sensing Image Classification based on Texture Features by Multivariate Local Binary Pattern. Remote Sensing Technology and Application, 2011, 26(3): 322-327.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2011.3.322        http://www.rsta.ac.cn/CN/Y2011/V26/I3/322

[1]Marceau D J,Howarth P J,Dubois J M,et al.Evaluation of the Grey\|level Co\|occurrence Matrix Method for Land\|Cover Classification Using SPOT Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,1990,28(4):513-519.

[2]Jensen J R.Detecting Residential Land\|Use Development at the Urban Fringe[J].Photogrammetric Engineering & Remote Sensing,1982,48(6):629-643.

[3]Gong P,Marceau D J,Howarth P J.A Comparison of Spatial Feature Extraction Algorithms for Land\|Use Classification with SPOT HRV Data[J].Remote Sensing of Environment,1992,40:137-151.

[4]Peng Guangxiong,Li Jing,He Yuhua.et al.Extracting Land Cover Information from CBERS\|2s CCD Image Using Texture Analysis[J].Remote Sensing Technology and Application,2007,22(1):8-13.[彭光雄,李京,何宇华,等.利用纹理分析方法提取CBERS02星CCD图像土地覆盖信息[J].遥感技术与应用,2007,22(1):8-13.]

[5]Coburn C A,Roberts A C B.A Multiscale Texture Analysis Procedure for Improved Forest Stand Classification[J].International Journal of Remote Sensing,2004,25(20):4287-4308.

[6]Song Cuiyu,Li Peijun,Yang Fengjie.The Application of Multiscale Image Texture to the Detection of Urban Expansion[J].Remote Sensing for Land & Resources,2006,69(3):37-42.[宋翠玉,李培军,杨锋杰.运用多尺度图像纹理进行城市扩展变化检测[J].国土资源遥感,2006,69(3):37-42.]

[7]Huang Yingduan,Li Peijun,Li Zhengxiao.The Application of Geostatistical Image Texture to Remote Sensing Lithological Classification[J].Remote Sensing for Land & Resources,2003,57(3):45-49.[黄颖端,李培军,李争晓.基于地统计学的图像纹理在岩性分类中的应用[J].国土资源遥感,2003,57(3):45-49.]

[8]Haralick R M,Shanmugam K,Dinstein I.Texture Feature for Image Classification[J].IEEE Transactions on Systems,Man,and Cybermetics,1973,3:610-625.

[9]Wu Gaohong,Zhang Yujin,Lin Xinggang.Texture Segmentation with Wavelet Transform and Feature Weighting[J].Journal of Image and Graphics,2001,6(4):333-337.[吴高洪,章毓晋,林行刚.利用小波变换和特征加权进行纹理分割[J].中国图象图形学报,2001,6(4):333-337.]

[10]Ojala T,Pietikainen M,M enp T.Multiresolution Gray Sc\|ale and Rotation Invariant Texture Analysis with Local Binary Pattern[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.

[11]Kyll nen J,Pietikinen M.Visual Inspection of Parquet Slabs by Combining Color and Texture[J].Proceedings IAPR Workshop on Machine Vision Applications (MVA00),November 28-30,Tokyo,Japan,2000:187-192.

[12]Feng X,Pietikinen M,Hadid A.Facial Expression Recognition with Local Binary Patterns and Linear Programming[J].Pattern Recognition and Image Analysis,2005,15(2):550-552.

[13]Lucieer A,Stein A,Fisher P.Multivariate Texture\|based Segmentation of Remotely Sensed Imagery for Extraction of Objects and their Uncertainty[J].International Journal of Remote Sensing,2005,26(14):2917-2936.

[14]Li P,Cheng T,Guo J.Multivariate Image Texture by Multivariate Variogram for Multispectral Image Classification[J].Photogrammetric Engineering & Remote Sensing,2009,75(2):147-157.
[15]Tan Kun,Du Peijun.Hyperspectral Remote Sensing Image Classification based on Support Vector Machine[J].Journal of Infrared and Millimeter Waves,2008,27(2):123-128.[谭琨,杜培军.基于支持向量机的高光谱遥感图像分类[J].红外与毫米波学报,2008,27(2):123-128.]

[16]M enp T.The Local Binary Pattern Approach to Texture Analysis\|extension and Application[EB/OL].http://herkules.oulu.fi/isbn9514270762/,2006.

[1] 周胜男,车涛,戴礼云. 基于地面站点类型代表性的积雪遥感产品精度评价[J]. 遥感技术与应用, 2017, 32(2): 228-237.
[2] 葛莉,习晓环,王成,Khun\-Neay Khuon. ICESat-1/GLAS数据湖泊水位监测研究进展[J]. 遥感技术与应用, 2017, 32(1): 14-19.
[3] 于小淇,邱玉宝,阮永俭,石利娟,拉巴卓玛. 高亚洲地区无云积雪遥感二值产品对比和精度验证分析[J]. 遥感技术与应用, 2017, 32(1): 37-48.
[4] 林志垒,晏路明. 高光谱影像的BDT-SVM地物分类算法与应用[J]. 遥感技术与应用, 2016, 31(1): 177-185.
[5] 蒋璐媛,肖鹏峰,冯学智,李云,朱榴骏. 基于亚分数混淆矩阵的中国典型区大尺度土地覆盖数据集评价[J]. 遥感技术与应用, 2015, 30(2): 353-363.
[6] 郭钇宏,王博,刘勇,杨亦宁 . 综合优度法和不一致性法的最优分割参数选择方法[J]. 遥感技术与应用, 2014, 29(3): 489-497.
[7] 赵涌泉,单小军,唐娉. 低空间分辨率多源遥感数据的空间一致性分析和相对几何校正[J]. 遥感技术与应用, 2014, 29(1): 155-163.
[8] 陈超,秦其明,池长艳,蒋洪波,刘明超. 一种Curvelet变换和IHS变换相结合的遥感图像融合方法[J]. 遥感技术与应用, 2011, 26(4): 444-449.
[9] 范兴旺, 翁永玲, 胡伍生, 徐君民, 刘团荣. IRS-P5立体像对提取DEM及精度评价[J]. 遥感技术与应用, 2010, 25(4): 547-551.
[10] 别 强, 赵传燕, 彭守璋, 冯兆东. 基于多元数据和不同分类算法的遥感影像信息提取及精度评价
——以祁连山东段为例
[J]. 遥感技术与应用, 2009, 24(5): 576-581.
[11] 郭艳芬,刘志红,谢明元. 基于植被物候特征与监督分类的青南高原信息提取[J]. 遥感技术与应用, 2009, 24(2): 223-229.
[12] 张飞,塔西甫拉提?特依拜,丁建丽,依力亚斯江.努尔麦麦提,田源. 新疆干旱区绿洲土壤盐渍化信息提取对比研究[J]. 遥感技术与应用, 2008, 23(4): 398-404.
[13] 彭光雄,李 京,何宇华,胡德勇. 利用纹理分析方法提取CBERS02星CCD图像土地覆盖信息[J]. 遥感技术与应用, 2007, 22(1): 8-13.
[14] 车 涛,李 新. 利用被动微波遥感数据反演我国积雪深度及其精度评[J]. 遥感技术与应用, 2004, 19(5): 301-306.
[15] 梁 继,王 建,王建华. 基于光谱角分类器遥感影像的自动分类和精度分析研究[J]. 遥感技术与应用, 2002, 17(6): 299-303.