Study on island land use classification method based on multi-scale texture and spectral information

LI Li-hong; ZHANG Hua-guo; LI Dong-lin; SHI Ai-qin; WANG Xiao-zhen

PDF(6579 KB)

Journal of Marine Sciences ›› 2013, Vol. 31 ›› Issue (2) : 35-44.

Study on island land use classification method based on multi-scale texture and spectral information

LI Li-hong, ZHANG Hua-guo^*, LI Dong-lin, SHI Ai-qin, WANG Xiao-zhen

Author information +

History +

Abstract

Based on gray level co-occurrence matrix(GLCM), different multi-scale texture images were extracted, and then the texture bands were combined with original bands to get new composited multispectral bands. The maximum likelihood supervised classification method was applied to new different composited images to test the differences of classification accuracy. Taking Ximen Island as a case study, through analyzing the differences of classification accuracy of different composited images, the following preliminary conclusions were got: (1)the total classification accuracy can be improved from 75.41% to 89.41% by using multi-scale texture images; (2)among different texture indices, correlation and homogeneity texture image calculated from the first band and second band of SPOT-5 image, mean texture image calculated from the third band, homogeneity texture image calculated from the fourth band can both improve classification accuracy than other texture indices images calculated from other bands.

Key words

remote sensing / multi-scale / GLCM / texture

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LI Li-hong, ZHANG Hua-guo, LI Dong-lin, SHI Ai-qin, WANG Xiao-zhen. Study on island land use classification method based on multi-scale texture and spectral information[J]. Journal of Marine Sciences. 2013, 31(2): 35-44

References

[1] SONG Cui-yu, LI Pei-jun, YANG Feng-jie. Application of multiscale image texture to the detection of urban expansion[J]. Remote Sensing for Land & Resources,2006,69(3):27-42.
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):27-42.
[2] MA De-feng, LI Pei-jun. The use of multiscale texture in image classification for lithologic mapping[J]. Acta Petrologica Sinica,2008,24(6):1 425-1 430.
马德锋,李培军.加入多尺度图像纹理的岩性分类[J].岩石学报,2008,24(6):1 425-1 430.
[3] CHEN Cheng, ZHANG You-jing. The classification of SVM based on the multi-scale texture information and spectral information[J]. Science of Surveying and Mapping,2009,34(1):29-31.
陈晨,张友静.基于多尺度纹理和光谱信息的SVM分类研究[J].测绘科学,2009,34(1):29-31.
[4] HU Wen-yuan, NIE Qian, HUANG Xiao-chuan. A method for classification of high spatial resolution remotely sensed images based on texture and spectral information[J]. Journal of Geomatics,2009,34(1):16-17.
胡文元,聂倩,黄小川.基于纹理和光谱信息的高分辨率遥感影像分类[J].测绘信息与工程,2009,34(1):16-17.
[5] LI Jin, WANG Xin, ZHANG Yuan. On relationship between texture features based on GLCM and tree measuring factors of pinus massoniana forest[J]. Journal of Zhejiang for SCI & TECH,2010,30(3):68-71.
李进,王鑫,张园.灰度共生矩阵纹理特征与马尾松林测树因子关系初探[J].浙江林业科技,2010,30(3):68-71.
[6] HARLICK R M, SHANMUGAM K, DINSTEIN I H. Textual features for image classification[J]. IEEE Transactions on Systems, Man, and Cybernetics,1973,3(6):610-621.
[7] CAO Bao, QIN Qi-ming, MA Hai-jian, et al.Application of object-oriented approach to SPOT-5 image classification: A case study in Haidian District,Beijing City[J]. Geography Geo-information Science,2006,22(2):46-49.
曹宝,秦其明,马海建,等.面向对象方法在SPOT5遥感图像分类中的应用——以北京市海淀区为例[J].地理与地理信息科学,2006,22(2):46-49.
[8] ZHANG Jun, WANG Bao-shan, ZHANG Zhi-qiang. High spatial resolution remote sensing image classification based on object-oriented multi-features[J]. Journal of Geomatics,2010,35(3):3-5.
张俊,王宝山,张志强.面向对象的高空间分辨率影像分类研究[J].测绘信息与工程,2010,35(3):3-5.
[9] FAN Lei, CHENG Yong-zheng, WANG Lai-gang, et al. Estimation of winter wheat planting area using object-oriented method based on multi-scale segmentation[J]. Chinese Journal of Agricultural Resources and Regional Planning,2010,31(6):44-51.
范磊,程永政,王来刚,等.基于多尺度分割的面向对象分类方法提取冬小麦种植面积[J].中国农业资源与区划,2010,31(6):44-51.