结合Steger方法和影像分类的道路中心线提取
|
摘要
针对直接利用监督分类结果提取道路中心线过程过于复杂的问题,研究一种综合利用Steger方法和影像分类结果的道路中心线提取新策略。以影像分类结果从Steger方法获取的条带中心线中初步筛选出候选道路中心线段,根据道路的连续性和方向的一致性进行合理延伸、连接,即可实现道路中心线提取。实验证明,提取的道路中心线在完整率、准确率和提取质量方面精度较高,并在一定程度上解决了道路断裂问题。
Extracting road centerline through image classification directly was complicated. To solve this problem, a new strategy which combined the Steger method strip centerline result with classification result was studied to get the road centerline in this paper. Firstly, the strip centerlines acquired by Steger method were preliminarily selected by the classification result directly. Then the road centerline result was extracted by extending and connecting the selected result reasonably based on the continuity and consistence in direction of the road. The experimental result indicates that the accuracies of completeness, correctness and quality are efficient, and this method partly solves the road fracture problem.
Extracting road centerline through image classification directly was complicated. To solve this problem, a new strategy which combined the Steger method strip centerline result with classification result was studied to get the road centerline in this paper. Firstly, the strip centerlines acquired by Steger method were preliminarily selected by the classification result directly. Then the road centerline result was extracted by extending and connecting the selected result reasonably based on the continuity and consistence in direction of the road. The experimental result indicates that the accuracies of completeness, correctness and quality are efficient, and this method partly solves the road fracture problem.
引文
[1]Shi W,Miao Z,Wang Q,et al.Spectral–Spatial Classification and Shape Features for Urban Road Centerline Extraction[J].IEEE Geoscience&Remote Sensing Letters,2013,11(4):788-792
[2]Saati M,Amini J,Maboudi M.A Method for Automatic Road Extraction of High Resolution SAR Imagery[J].Journal of the Indian Society of Remote Sensing,2015,43(4):697-707
[3]Song M,Civco D.Road Extraction Using SVM and Image Segmentation[J].Photogrammetric Engineering&Remote Sensing,2004,70(12):1 365-1 371
[4]Wegner J D,Montoya-Zegarra J A,Schindler K.Road Networks as Collections of Minimum Cost Paths[J].ISPRS Journal of Photogrammetry&Remote Sensing,2015(108):128-137
[5]明冬萍,骆剑承,沈占锋,等.高分辨率遥感影像信息提取与目标识别技术研究[J].测绘科学,2005,30(3):18-20
[6]朱长青,王耀革,马秋禾,等.基于形态分割的高分辨率遥感影像道路提取[J].测绘学报,2004,33(4):347-351
[7]苗则朗,史文中,张华.一种高分辨率影像道路中心线提取算法[J].中国矿业大学学报,2013(5):887-892
[8]朱昌盛,周伟,关键.基于平行线对检测的SAR图像主干道提取算法[J].中国图象图形学报,2011,16(10):1 908-1 917
[9]Steger C.An Unbiased Detector of Curvilinear Structures[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(2):113-125
[10]Steger C.Unbiased Extraction of lines with Parabolic and Gaussian Profiles[J].Computer Vision and Image Understanding,2013,117(2):97-112
[11]张远,张广军,江洁.Steger算法的FPGA递归逻辑结构设计与实现[J].传感器与微系统,2008(9):78-81
[12]胡坤,周富强,张广军.一种快速结构光条纹中心亚像素精度提取方法[J].仪器仪表学报,2006(10):1 326-1 329
[13]杜培军,夏俊士,薛朝辉,等.高光谱遥感影像分类研究进展[J].遥感学报,2016(2):236-256
[14]刘志刚,李德仁,秦前清,等.支持向量机在多类分类问题中的推广[J].计算机工程与应用,2004,40(7):10-13
[15]Sch?lkopf B.A Comparison on Methods for Multi-class Support Vector Machines[J].IEEE Transactions on Neural Networks,2008,13(2):415-425
[16]Chang Chih-Chung,Lin Chih-Jen.Libsvm:A Library for Support Vector Machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3):1-27
[17]Wiedemann C,Heipke C,Mayer H,et al.Empirical Evaluation Of Automatically Extracted Road Axes[J].Empirical Evaluation Techniques in Computer Vision,1998:172-187
[2]Saati M,Amini J,Maboudi M.A Method for Automatic Road Extraction of High Resolution SAR Imagery[J].Journal of the Indian Society of Remote Sensing,2015,43(4):697-707
[3]Song M,Civco D.Road Extraction Using SVM and Image Segmentation[J].Photogrammetric Engineering&Remote Sensing,2004,70(12):1 365-1 371
[4]Wegner J D,Montoya-Zegarra J A,Schindler K.Road Networks as Collections of Minimum Cost Paths[J].ISPRS Journal of Photogrammetry&Remote Sensing,2015(108):128-137
[5]明冬萍,骆剑承,沈占锋,等.高分辨率遥感影像信息提取与目标识别技术研究[J].测绘科学,2005,30(3):18-20
[6]朱长青,王耀革,马秋禾,等.基于形态分割的高分辨率遥感影像道路提取[J].测绘学报,2004,33(4):347-351
[7]苗则朗,史文中,张华.一种高分辨率影像道路中心线提取算法[J].中国矿业大学学报,2013(5):887-892
[8]朱昌盛,周伟,关键.基于平行线对检测的SAR图像主干道提取算法[J].中国图象图形学报,2011,16(10):1 908-1 917
[9]Steger C.An Unbiased Detector of Curvilinear Structures[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(2):113-125
[10]Steger C.Unbiased Extraction of lines with Parabolic and Gaussian Profiles[J].Computer Vision and Image Understanding,2013,117(2):97-112
[11]张远,张广军,江洁.Steger算法的FPGA递归逻辑结构设计与实现[J].传感器与微系统,2008(9):78-81
[12]胡坤,周富强,张广军.一种快速结构光条纹中心亚像素精度提取方法[J].仪器仪表学报,2006(10):1 326-1 329
[13]杜培军,夏俊士,薛朝辉,等.高光谱遥感影像分类研究进展[J].遥感学报,2016(2):236-256
[14]刘志刚,李德仁,秦前清,等.支持向量机在多类分类问题中的推广[J].计算机工程与应用,2004,40(7):10-13
[15]Sch?lkopf B.A Comparison on Methods for Multi-class Support Vector Machines[J].IEEE Transactions on Neural Networks,2008,13(2):415-425
[16]Chang Chih-Chung,Lin Chih-Jen.Libsvm:A Library for Support Vector Machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3):1-27
[17]Wiedemann C,Heipke C,Mayer H,et al.Empirical Evaluation Of Automatically Extracted Road Axes[J].Empirical Evaluation Techniques in Computer Vision,1998:172-187