一种多特征融合的高分辨率遥感影像道路中心线提取算法
|
摘要
高分辨率遥感影像道路提取对于地理信息库建设等方面具有重要的研究意义。提出了多特征融合框架下的高分辨率遥感影像道路中心线提取算法。首先,从影像分割的角度出发,分别提取道路的光谱与空间特征;然后,通过引入多特征融合算法对该两种特征进行有效融合,得到初始道路网络,并结合构建的形状特征进行道路网络优化,得到精细化道路网络;最后,通过引入计算机视觉中的张量投票算法完成道路网络的中心线提取。实验表明,算法精度更高,效果更为理想。
High-resolution remote sensing image road extraction has important research significance for the construction of geographic information base. This paper proposed a new multi-feature fusion framework of high-resolution remote sensing image road centerline extraction method. Firstly, the spectral and spatial features of the road are extracted. Then, a new multi-feature fusion algorithm is used to fuse the two features effectively, and obtain the initial road network. We use a new shape feature to remove non-road areas and get the fine road network. Finally, the centerline extraction of the road network is completed by tensor voting algorithm. By contrast with the state of art algorithm, our method show a much better result.
High-resolution remote sensing image road extraction has important research significance for the construction of geographic information base. This paper proposed a new multi-feature fusion framework of high-resolution remote sensing image road centerline extraction method. Firstly, the spectral and spatial features of the road are extracted. Then, a new multi-feature fusion algorithm is used to fuse the two features effectively, and obtain the initial road network. We use a new shape feature to remove non-road areas and get the fine road network. Finally, the centerline extraction of the road network is completed by tensor voting algorithm. By contrast with the state of art algorithm, our method show a much better result.
引文
[1] 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
[2] Huang Xin,Zhang Liangpei.Road Centreline Extraction from High-Resolution Imagery Based on Multiscale Structural Features and Support Vector Machines[J].International Journal of Remote Sensing,2009,30(8):1 977-1 987
[3] Shi Wenzhong,Miao Zelang,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
[4] 傅罡,赵红蕊,李聪,等.曲折道路遥感影像圆投影匹配改进追踪法[J].测绘学报,2014,43(7):724-730
[5] Tuya H,Chen Zhongxin,Wang Limin,et al.Monitoring Plastic-Mulched Farmland by Landsat-8 OLI Imagery Using Spectral and Textural Features[J].Remote Sensing,8(4),doi:10.3390/rs8040353
[6] Huang Xin,Zhang Liangpei.A Multilevel Decision Fusion Approach for Urban Mapping Using very High-Resolution Multi/Hyperspectral Imagery[J].International Journal of Remote Sensing,2011,33(11):3 354-3 372
[7] 王俊淑,江南,张国明,等.融合光谱-空间信息的高光谱遥感影像增量分类算法[J].测绘学报,2015,44(9):1 003-1 013
[8] 张春森,郑艺惟,黄小兵,等.高光谱影像光谱-空间多特征加权概率融合分类[J].测绘学报,2015,44(8):909-918
[9] Fauvel M,Chanussot J,Benediktsson J A.A Spatial-Spectral Kernel-Based Approach for the Classification of Remote-Sensing Images[J].Pattern Recognition,2012,45(1):381-392
[10] 曹云刚,王志盼,慎利,等.像元与对象特征融合的高分辨率遥感影像道路中心线提取[J].测绘学报,2016,45(10):1 231-1 240
[11] Miao Zelang,Shi Wenzhong,Zhang Hua,et al.Road Centerline Extraction from High-Resolution Imagery Based on Shape Features and Multivariate Adaptive Regression Splines[J].IEEE Geoscience and Remote Sensing Letters,2013,10(3):583-587
[12] Chang C C,Lin C J.LIBSVM:A Library for Support Vector Machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3),doi:10.1145/1961189.1961199
[13] 顾海燕,闫利,李海涛,等.基于随机森林的地理要素面向对象自动解译方法[J].武汉大学学报·信息科学版,2016,41(2):228-234
[2] Huang Xin,Zhang Liangpei.Road Centreline Extraction from High-Resolution Imagery Based on Multiscale Structural Features and Support Vector Machines[J].International Journal of Remote Sensing,2009,30(8):1 977-1 987
[3] Shi Wenzhong,Miao Zelang,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
[4] 傅罡,赵红蕊,李聪,等.曲折道路遥感影像圆投影匹配改进追踪法[J].测绘学报,2014,43(7):724-730
[5] Tuya H,Chen Zhongxin,Wang Limin,et al.Monitoring Plastic-Mulched Farmland by Landsat-8 OLI Imagery Using Spectral and Textural Features[J].Remote Sensing,8(4),doi:10.3390/rs8040353
[6] Huang Xin,Zhang Liangpei.A Multilevel Decision Fusion Approach for Urban Mapping Using very High-Resolution Multi/Hyperspectral Imagery[J].International Journal of Remote Sensing,2011,33(11):3 354-3 372
[7] 王俊淑,江南,张国明,等.融合光谱-空间信息的高光谱遥感影像增量分类算法[J].测绘学报,2015,44(9):1 003-1 013
[8] 张春森,郑艺惟,黄小兵,等.高光谱影像光谱-空间多特征加权概率融合分类[J].测绘学报,2015,44(8):909-918
[9] Fauvel M,Chanussot J,Benediktsson J A.A Spatial-Spectral Kernel-Based Approach for the Classification of Remote-Sensing Images[J].Pattern Recognition,2012,45(1):381-392
[10] 曹云刚,王志盼,慎利,等.像元与对象特征融合的高分辨率遥感影像道路中心线提取[J].测绘学报,2016,45(10):1 231-1 240
[11] Miao Zelang,Shi Wenzhong,Zhang Hua,et al.Road Centerline Extraction from High-Resolution Imagery Based on Shape Features and Multivariate Adaptive Regression Splines[J].IEEE Geoscience and Remote Sensing Letters,2013,10(3):583-587
[12] Chang C C,Lin C J.LIBSVM:A Library for Support Vector Machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3),doi:10.1145/1961189.1961199
[13] 顾海燕,闫利,李海涛,等.基于随机森林的地理要素面向对象自动解译方法[J].武汉大学学报·信息科学版,2016,41(2):228-234