基于SLIC超像素的高分辨率遥感影像城镇道路提取
|
摘要
针对高分辨率遥感影像道路提取方法易受影像噪声影响,且对道路特征利用不充分,难以准确提取城镇道路的问题,提出了一种基于SLIC(simple linear iterative clustering)超像素的高分辨遥感影像城镇道路提取方法。该方法首先用SLIC算法对影像进行过分割生成SLIC超像素,用k-means算法对SLIC超像素进行分类,然后根据绿色波段归一化植被指数(green normalized difference vegetation index,GNDVI)对分类影像进行过滤,再用改进Canny算子消除过滤影像中其他地物与道路间的连接,最后根据对象形状指数、对象最小外接矩形的长宽比、对象面积特征提取道路对象,用数学形态学对提取道路对象进行处理形成道路网。实验结果表明,本方法具有较好的城镇道路提取效果。
As the current method of high-resolution remote sensing image road extraction is easy to be affected by the noise of the image and road features are not fully used,this paper proposes an urban road extraction method of high-resolution remote sensing image based on object multi-feature.Firstly,the image is over-segmented by SLIC algorithm to achieve SLIC superpixels,then the image is classified by k-means algorithm based on SLIC superpixels.Secondly,image is filtered according to GNDVI index,then the improved Canny operator is used to eliminate the connection between the other objects and the road.Finally,road is extracted according to the object shape index,the length and width ratio of the object minimum bounding rectangle and the object area.Road network is formed by mathematical morphology.The experimental results show that the proposed method can well extract urban road from high resolution remote sensing image.
As the current method of high-resolution remote sensing image road extraction is easy to be affected by the noise of the image and road features are not fully used,this paper proposes an urban road extraction method of high-resolution remote sensing image based on object multi-feature.Firstly,the image is over-segmented by SLIC algorithm to achieve SLIC superpixels,then the image is classified by k-means algorithm based on SLIC superpixels.Secondly,image is filtered according to GNDVI index,then the improved Canny operator is used to eliminate the connection between the other objects and the road.Finally,road is extracted according to the object shape index,the length and width ratio of the object minimum bounding rectangle and the object area.Road network is formed by mathematical morphology.The experimental results show that the proposed method can well extract urban road from high resolution remote sensing image.
引文
[1]文贡坚,王润生.从航空遥感图像中自动提取主要道路[J].软件学报,2000,11(7):957-964
[2]余长慧,孟令奎,秦昆.基于标点随机过程的遥感影像道路提取[J].武汉大学学报·信息科学版,2006,31(1):59-62
[3]吴小波,杨辽,沈金祥,等.利用空间连续性进行高分辨率遥感影像道路提取[J].武汉大学学报·信息科学版,2011,36(11):1 298-1 301
[4]Song M,Civco D.Road Extraction Using SVM and Image Segmentation[J].Photogrammetric Engineering&Remote Sensing,2004,70(12):1 365-1 371
[5]Shi W,Miao Z,Debayle J.An Integrated Method for Urban Main-Road Centerline Extraction from Optical Remotely Sensed Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(6):3 359-3 372
[6]胡海旭,王文,何厚军.基于纹理特征与数学形态学的高分辨率影像城市道路提取[J].地理与地理信息科学,2008,24(6):46-49
[7]Laptev I,Mayer H,Lindeberg T,et al.Automatic Extraction of Roads from Aerial Images Based on Scale Space and Snakes[J].Machine Vision and Applications,2000,12(1):23-31
[8]余洁,余峰,张晶,等.结合区域生长与道路基元的高分辨率遥感影像道路提取[J].武汉大学学报·信息科学版),2013,38(7):761-764
[9]傅嘉政,杨少敏,刘浩.基于小波变换和霍夫变换的高分辨率遥感影像道路提取[J].测绘地理信息,2015,40(4):48-50
[10]Ren X,Malik J.Learning a Classification Model for Segmentation[C].Ninth IEEE International Conference on Computer Vision,Vancouver,Canada,2003
[11]Achanta R,Shaji A,Smith K,et al.SLIC Superpixels Compared to State-of-the-art Superpixel Methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2 274-2 282
[12]王春瑶,陈俊周,李炜.超像素分割算法研究综述[J].计算机应用研究,2014,31(1):6-12
[13]Yi L,Zhang G,Wu Z.AScale-Synthesis Method for High Spatial Resolution Remote Sensing Image Segmentation[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(10):4 062-4 070
[14]Gitelson A A,Kaufman Y J,Merzlyak M N.Use of a Green Channel in Remote Sensing of Global Vegetation from EOS-MODIS[J].Remote Sensing of Environment,1996,58(3):289-298
[15]刘金榜,李建松,柯晓龙,等.ArcGIS支持下高分辨率遥感影像解译效率提高方法[J].测绘地理信息,2014,39(6):54-58
[16]Heipke C,Mayer H,Wiedemann C,et al.Evaluation of Automatic Road Extraction[J].International Archives of Photogrammetry and Remote Sensing,1997,32(3SECT 4W2):151-160
[17]Wiedemann C,Heipke C,Mayer H,et al.Empirical Evaluation of Automatically Extracted Road Axes[C].Empirical Evaluation Techniques in Computer Vision,Piscataway,N J,1998
[2]余长慧,孟令奎,秦昆.基于标点随机过程的遥感影像道路提取[J].武汉大学学报·信息科学版,2006,31(1):59-62
[3]吴小波,杨辽,沈金祥,等.利用空间连续性进行高分辨率遥感影像道路提取[J].武汉大学学报·信息科学版,2011,36(11):1 298-1 301
[4]Song M,Civco D.Road Extraction Using SVM and Image Segmentation[J].Photogrammetric Engineering&Remote Sensing,2004,70(12):1 365-1 371
[5]Shi W,Miao Z,Debayle J.An Integrated Method for Urban Main-Road Centerline Extraction from Optical Remotely Sensed Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(6):3 359-3 372
[6]胡海旭,王文,何厚军.基于纹理特征与数学形态学的高分辨率影像城市道路提取[J].地理与地理信息科学,2008,24(6):46-49
[7]Laptev I,Mayer H,Lindeberg T,et al.Automatic Extraction of Roads from Aerial Images Based on Scale Space and Snakes[J].Machine Vision and Applications,2000,12(1):23-31
[8]余洁,余峰,张晶,等.结合区域生长与道路基元的高分辨率遥感影像道路提取[J].武汉大学学报·信息科学版),2013,38(7):761-764
[9]傅嘉政,杨少敏,刘浩.基于小波变换和霍夫变换的高分辨率遥感影像道路提取[J].测绘地理信息,2015,40(4):48-50
[10]Ren X,Malik J.Learning a Classification Model for Segmentation[C].Ninth IEEE International Conference on Computer Vision,Vancouver,Canada,2003
[11]Achanta R,Shaji A,Smith K,et al.SLIC Superpixels Compared to State-of-the-art Superpixel Methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2 274-2 282
[12]王春瑶,陈俊周,李炜.超像素分割算法研究综述[J].计算机应用研究,2014,31(1):6-12
[13]Yi L,Zhang G,Wu Z.AScale-Synthesis Method for High Spatial Resolution Remote Sensing Image Segmentation[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(10):4 062-4 070
[14]Gitelson A A,Kaufman Y J,Merzlyak M N.Use of a Green Channel in Remote Sensing of Global Vegetation from EOS-MODIS[J].Remote Sensing of Environment,1996,58(3):289-298
[15]刘金榜,李建松,柯晓龙,等.ArcGIS支持下高分辨率遥感影像解译效率提高方法[J].测绘地理信息,2014,39(6):54-58
[16]Heipke C,Mayer H,Wiedemann C,et al.Evaluation of Automatic Road Extraction[J].International Archives of Photogrammetry and Remote Sensing,1997,32(3SECT 4W2):151-160
[17]Wiedemann C,Heipke C,Mayer H,et al.Empirical Evaluation of Automatically Extracted Road Axes[C].Empirical Evaluation Techniques in Computer Vision,Piscataway,N J,1998