Abstract：In order to overcome the disadvantages of the classification method based on spectral and texture features, the authors put forward a classification method based on the fusion of spatial relationship in this paper. Single object probability was built by G statistic after image object feature was extracted by histogram. The neighborhood object probability was described by land cover adjacency probability which was calculated by iterative statistics method. The joint probability of the object was built by the weighted combination of single object probability and neighborhood object probability. The classification result of the image was obtained according to the maximum a posteriori. The experimental results based on QuickBird image show that the proposed method can improve the classification accuracy compared with the traditional classifier using spectral and texture features. The overall classification accuracy and kappa coefficient are increased by 1.5% and 2.1%, respectively.
李亮, 张云, 李胜, 应国伟. 融合空间关系的遥感图像分类[J]. 国土资源遥感, 2017, 29(3): 10-16.
LI Liang, ZHANG Yun, LI Sheng, YING Guowei. Classification of remote sensing images based on the fusion of spatial relationship. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(3): 10-16.
[1] 白 穆,刘慧平,乔 瑜,等.高分辨率遥感图像分类方法在LUCC中的研究进展[J].国土资源遥感,2010(1):19-23.doi:10.6046/gtzyyg.2010.01.03"> doi:10.6046/gtzyyg.2010.01.03. Bai M,Liu H P,Qiao Y,et al.New progress in the classification of high spatial resolution satellite images for LUCC[J].Remote Sensing for Land and Resources,2010(1):19-23.doi:10.6046/gtzyyg.2010.01.03"> doi:10.6046/gtzyyg.2010.01.03. [2] 杨 耘,徐 丽,颜佩丽.条件随机场框架下基于随机森林的城市土地利用/覆盖遥感分类[J].国土资源遥感,2014,26(4):51-55.doi:10.6046/gtzyyg.2014.04.09"> doi:10.6046/gtzyyg.2014.04.09. Yang Y,Xu L,Yan P L.Urban land use /cover classification of remote sensing using random forests under the framework of conditional random fields[J].Remote Sensing for Land and Resources,2014,26(4):51-55.doi:10.6046/gtzyyg.2014.04.09"> doi:10.6046/gtzyyg.2014.04.09. [3] 张楼香,阮仁宗,夏 双.洪泽湖湿地纹理特征参数分析[J].国土资源遥感,2015,27(1):75-80.doi:10.6046/gtzyyg.2015.01.12"> doi:10.6046/gtzyyg.2015.01.12. Zhang L X,Ruan R Z,Xia S.Parameter analysis of image texture of wetland in the Hongze Lake[J].Remote Sensing for Land and Resources,2015,27(1):75-80.doi:10.6046/gtzyyg.2015.01.12"> doi:10.6046/gtzyyg.2015.01.12. [4] 杨 胜,李 敏,彭振国,等.一种新的多波段遥感影像变化检测方法[J].中国图象图形学报,2009,14(4):572-578. Yang S,Li M,Peng Z G,et al.A novel multi-band remote sensing image change detection algorithm[J].Journal of Image and Graphics,2009,14(4):572-578. [5] Ferro C J S,Warner T A.Scale and texture in digital image classification[J].Photogrammetric Engineering and Remote Sensing,2002,68(1):51-63. [6] 王增茂,杜 博,张良培,等.基于纹理特征和形态学特征融合的高光谱影像分类法[J].光子学报,2014,43(8):0810002-1-0810002-8. Wang Z M,Du B,Zhang L P,et al.Based on texture feature and extend morphological profile fusion for hyperspectral image classification[J].Acta Photonica Sinica,2014,43(8):0810002-1-0810002-8. [7] 刘昌振,舒 红,张 志,等.基于多尺度分割的高分遥感图像变异函数纹理提取和分类[J].国土资源遥感,2015,27(4):47-53.doi:10.6046/gtzyyg.2015.04.08"> doi:10.6046/gtzyyg.2015.04.08. Liu C Z,Shu H,Zhang Z,et al.Variogram texture extraction and classification of high resolution remote sensing images based on multi-resolution segmentation[J].Remote Sensing for Land and Resources,2015,27(4):47-53.doi:10.6046/gtzyyg.2015.04.08"> doi:10.6046/gtzyyg.2015.04.08. [8] 黄 昕,张良培,李平湘.融合形状和光谱的高空间分辨率遥感影像分类[J].遥感学报,2007,11(2):193-200. Huang X,Zhang L P,Li P X.Classification of high spatial resolution remotely sensed imagery based on the fusion of spectral and shape features[J].Journal of Remote Sensing,2007,11(2):193-200. [9] Segl K,Roessner S,Heiden U,et al.Fusion of spectral and shape features for identification of urban surface cover types using reflective and thermal hyperspectral data[J].ISPRS Journal of Photogrammetry and Remote Sensing,2003,58(1/2):99-112. [10] 蔡晓斌,陈晓玲,王 涛,等.基于图斑空间关系的遥感专家分类方法研究[J].武汉大学学报(信息科学版),2006,31(4):321-324. Cai X B,Chen X L,Wang T,et al.Remote sensing expert classification method based on patch spatial relationship[J].Geomatics and Information Science of Wuhan University,2006,31(4):321-324. [11] 乔 程,沈占锋,吴 宁,等.空间邻接支持下的遥感影像分类[J].遥感学报,2011,15(1):88-99. Qiao C,Shen Z F,Wu N,et al.Remote sensing image classification method supported by spatial adjacency[J].Journal of Remote Sensing,2011,15(1):88-99. [12] 陈秋晓,骆剑承,周成虎,等.基于多特征的遥感影像分类方法[J].遥感学报,2004,8(3):239-245. Chen Q X,Luo J C,Zhou C H,et al.Classification of remotely sensed imagery using multi-features based approach[J].Journal of Remote Sensing,2004,8(3):239-245. [13] 赵红蕊,阎广建,邓小炼,等.一种简单加入空间关系的实用图像分类方法[J].遥感学报,2003,7(5):358-363. Zhao H R,Yan G J,Deng X L,et al.A classification method based on spatial information[J].Journal of Remote Sensing,2003,7(5):358-363. [14] 王 凯,舒 宁,孔祥兵,等.一种多特征转换的高光谱影像自适应分类方法[J].武汉大学学报(信息科学版),2015,40(5):612-616. Wang K,Shu N,Kong X B,et al.A multi-feature conversion adaptive classification of hyperspectral image[J].Geomatics and Information Science of Wuhan University,2015,40(5):612-616. [15] 张 倩,黄 昕,张良培.多尺度同质区域提取的高分辨率遥感影像分类研究[J].武汉大学学报(信息科学版),2011,36(1):117-121. Zhang Q,Huang X,Zhang L P.Multiscale image segmentation and classification with supervised ECHO of high spatial resolution remotely sensed imagery[J].Geomatics and Information Science of Wuhan University,2011,36(1):117-121. [16] Zhao Y D,Zhang L P,Li P X,et al.Classification of high spatial resolution imagery using improved Gaussian Markov random-field-based texture features[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(5):1458-1468. [17] 龚 龑,舒 宁,王 琰,等.遥感影像像斑空间关系分析的非规则无参数马尔可夫随机场模型[J].测绘学报,2013,42(1):101-107. Gong Y,Shu N,Wang Y,et al.Segments spatial relationship feature analysis of remote sensing imagery based on non-parameter irregular-MRF model[J].Acta Geodaetica et Cartographica Sinica,2013,42(1):101-107. [18] 谭 熊,余旭初,张鹏强,等.基于MKSVM和MRF的高光谱影像分类方法[J].国土资源遥感,2015,27(3):42-46.doi:10.6046/gtzyyg.2015.03.08"> doi:10.6046/gtzyyg.2015.03.08. Tan X,Yu X C,Zhang P Q,et al.Hyperspectral images classification based on MKSVM and MRF[J].Remote Sensing for Land and Resources,2015,27(3):42-46.doi:10.6046/gtzyyg.2015.03.08"> doi:10.6046/gtzyyg.2015.03.08. [19] Ojala T,Pietikäinen M.Unsupervised texture segmentation using feature distributions[J].Pattern Recognition,1999,32(3):477-486. [20] Ojala T,Pietikainen M,Maenpaa T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987. [21] 巫兆聪,胡忠文,张 谦,等.结合光谱、纹理与形状结构信息的遥感影像分割方法[J].测绘学报,2013,42(1):44-50. Wu Z C,Hu Z W,Zhang Q,et al.On combining spectral, textural and shape features for remote sensing image segmentation[J].Acta Geodaetica et Cartographica Sinica,2013,42(1):44-50.
2017, Vol. 29 
