一种面向对象的像元级遥感图像分类方法
收稿日期: 2013-03-07
修回日期: 2013-05-13
网络出版日期: 2013-09-29
基金资助
欧盟第七框架项目(FP7-PEOPLE-2009-IRSES-IGIT);广东省省院产学研合作资金项目(2012B091100219)、中国科学院对外重点合作项目(GJHZ1003)。
A Hybrid Model of Object-Oriented and Pixel Based Classification of Remotely Sensed Data
Received date: 2013-03-07
Revised date: 2013-05-13
Online published: 2013-09-29
本文提出一种面向对象的像元级分类方法(混合模型),并将其与单纯的以像元和面向对象的两种方法同时应用于分辨率分别为30m和0.5m的环境星CCD数据和航空影像进行对比分析。分类结果中不同地物类别之间光谱可分性的大小,很大程度上可反映分类结果的可靠性。若地物类型之间的光谱差异大,说明分类方法能将光谱差异大的地物很好地划分,显示出较可靠的分类结果;相反,如果分类结果中地物类型光谱差异小,则反映分类方法不够可靠。鉴此,本文通过计算分类结果中不同类别所对应的原始遥感影像像元之间的J-M(Jeffries-Matusita Distance)距离来度量分类结果中地物之间的光谱可分性,并用J-M距离比较分析了3种图像分类方法对2种不同分辨率影像的分类结果中各个类别之间的光谱可分性的变化。分析结果表明,混合模型不但能够得到较连续的分类结果,同时能够保持分类结果中类别之间的可分性。本文对分类结果进行了精度验证,结果发现混合模型的分类精度较其他2种方法要高。2种不同分辨率的遥感影像分析结果得到相同的结论,表明该模型适用于中分辨率和高分辨率影像。
关键词： 多种分辨率; 面向对象; 混合模型; J-M(Jeffries-Matusita)距离; 地物光谱可分性
李小江, 孟庆岩, 王春梅, 刘苗, 郑利娟, 王珂 . 一种面向对象的像元级遥感图像分类方法[J]. 地球信息科学学报, 2013 , 15(5) : 744 -751 . DOI: 10.3724/SP.J.1047.2013.00744
Three classification methods: maximum likelihood at pixel level, maximum likelihood at object level and a hybrid model of pixel based and object-based classification method were used to classify these two sorts of images, i.e., 30m resolution HJ-1-A CCD imagery and 0.5 m resolution aerial images. Spectral separability in training samples between different classes directly affect the classification accuracy; on the contrary, spectral separability between different classes in the classification result can be used to evaluate the accuracy of classification. Based on this assumption, classification results of these three methods were evaluated by spectral separability between different classes. Result reveals that compared with the maximum likelihood at object level, classification at pixel level can make full use of the spectral information in remotely sensed image. Analysis also shows that hybrid model can improve the classification accuracy. Multi-resolution image analysis proves that the hybrid model is suitable for applications at different scales.
[1] Ediriwickrema J, Khorram S. Hierarchical maximum-likelihood classification for improved accuracies[J]. IEEE Transactions on Geoscience and Remote Sensing, 1997 (35):810-816.
[2] Jensen R J, Lulla D K. Introductory digital image processing: A remote sensing perspective[C]. Upper Saddle River, NJ: Prentice-Hall, 2005.
[3] Bishop C M. Neural networks for pattern recognition[M]. Oxford: Clarendon Press, 1995.
[4] Benediktsson J A, Swain P H, Ersoy O K. Neural network approaches versus statistical methods in classification of multisource remote-sensing data[J]. IEEE Transactions on Geoscience and Remote Sensing, 1990(28):550-552.
[5] Vapnik V. The nature of statistical learning theory[M]. New York: Springer-Verlag, 1995.
[6] Huang C, Davis L S, Townshend J R G. An assessment of support vector machines for land cover classification[J]. International Journal of Remote Sensing, 2002(23):725-749.
[7] Zhu G, Blumberg, D G. Classification using ASTER data and SVM algorithms: The case study of Beer Sheva, Israel [J]. Remote Sensing of Environment, 2002(80):233-240.
[8] Pal M, Mather P M. Support vector machines for classification in remote sensing[J]. International Journal of Remote Sensing, 2005(26):1007-1011.
[9] Mountrakis G, Im J, Ogole C. Support vector machines in remote sensing: A review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011(66):247-259.
[10] Walter V. Object-based classification of remote sensing data for change detection[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2004(58):225-238.
[11] Wang, L., Sousa, W.P., et al. Integration of object-based and pixel-based classification for mapping mangroves with IKONOS imagery[J]. International Journal of Remote Sensing, 2004(25): 5655-5668.
[12] Malinverni E S, Tassetti A N, Mancini A,et al. Hybrid object- based approach for land use/land cover mapping using high spatial resolution imagery[J]. International Journal of Remote Sensing, 2011(25):1025-1043.
[13] Myint S W, Gober P, Brazel A, et al. Per-pixel vs object- based classification of urban land cover extraction using high spatial resolution imagery[J]. Remote Sensing of Environment, 2011,115(5):1145-1161.
[14] Lin H. Method of image segmentation on high-resolution image and classification for land covers fourth[C]. International Conference on Natural Computation, 2008, 563-566.
[15] Vincent L, Soille P. Watersheds in digital spaces: An efficient algorithm based on immersion simulations[J]. N IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991(13):583:597.
[16] Xiao P. Feng X, Li H. Multispectral remotely sensed imagery segmentation based on first fundamental form[C]. IEEE Urban Remote Sensing Joint Event, 2009.
[17] Hill P R, Canagarajah C N, Bull D R. Image segmentation using a texture gradient based watershed transform [J]. IEEE Transactions on Image Processing, 2003 (12): 1618-1633.
[18] Brandt T, Paul M M. Classification methods for remotely sensed data (2nd Ed.) [M]. New York: CRC Press, 2007, 58-62.
[19] Michelson D B, Liljeberg B M, Pilesjo P. Comparison of algorithms for classifying Swedish landcover using LANDSAT TM and ERS-1 SAR data[J]. Remote Sensing of Environment, 2000(71):1-15.
/
| 〈 |
|
〉 |