摘要
道路作为重要的人造地物，是构成现代交通体系的主要部分，具有重要的地理、政治、经济、军事意义。由于合成孔径雷达(Synthetic Aperture Radar, SAR)系统具有全天时、全天侯等优点，从SAR图像中提取道路日益受到重视。高分辨率使得对地观测中更多的地物细节得到呈现。在高分辨率SAR图像中，道路不再表现为线特征，而是呈现出由亮的双边缘包围的暗长区域。然而，高分辨率也使得各类干扰得到放大，道路旁的阴影遮挡、道路上的车辆等各类干扰的存在、道路类型的多样性以及环境背景的复杂性，使得高分辨率SAR图像道路提取变得复杂而艰巨。
针对当前SAR图像道路提取所存在的问题，本论文主要根据高分辨率SAR图像道路的辐射及几何特征，对高分辨率SAR图像道路交叉口的自动提取、道路自动以及半自动提取问题分别展开深入研究，提出了系列新的提取算法。
在第三章高分辨率SAR图像道路交叉口自动提取研究中，提出一种直接检测识别道路交叉口的新方法。该方法先根据交叉口的灰度特征，利用形态学变换，全局搜索交叉口候选区域中心点位置；然后以此为局部窗口中心，采用多阈值Otsu分割出各个局部窗口内道路目标；接着根据交叉口的几何特征，通过矩形旋转得到角度均值图，获取与交叉口相连的道路个数，最终识别出交叉口的类型。实验结果表明该方法可有效提取出各种干扰下的交叉口目标。
在第四章高分辨率SAR图像道路自动提取研究中，论文针对基于传统马尔科夫随机场(Markov random field, MRF)模型道路提取方法存在求解过程偏慢及参数设置偏多的问题，提出先根据道路空间几何特征关系对提取出的线基元进行预连接，以此减少虚假连接给MRF迭代求解带来的运算量；然后建立MRF道路网改进模型对道路网进行快速标记的方法。使用1m机载高分辨率SAR图像进行实验，结果表明该方法的有效性。
在第五章高分辨率SAR图像道路半自动提取研究中，提出一种局部检测和全局跟踪相结合的道路中心点提取方法。在局部检测时，设定内外双窗口，外窗口根据护栏、绿化带等干扰物与道路的边缘呈现一致的方向性，采用非线性结构张量获取该区域内的道路方向；内窗口根据方向结果调整转向，搜索道路区域，进而确定道路的宽度及中心点。在全局跟踪阶段，为克服路上阻塞及路旁建筑物遮挡造成跟踪频繁失败的影响，采用粒子滤波器变步长跟踪的策略。实验结果表明该方法能有效降低各种干扰及遮挡物的影响，有效实现道路中心点的跟踪提取。
综上所述，本论文的研究将为高分辨率SAR图像地物目标解译做有益探索，同时道路提取的应用技术研究也将为以后的工程实践提供研究思路。
As the typical man-made land object, roads are essential parts of moderntransportation system, which have important geographical, political, economic andmilitary values. As a kind of microwave remote sensing system, Synthetic ApertureRadar (SAR) data acquisition could operate during both day and night, and isindependent on the influence of sunlight and clouds. Becaese of these merits, roadextraction from SAR images has attracted attentions of researchers all over the world.More land object details can be described in high-resolution SAR images compariedwith which in low-resolution images. Ideally, roads may be modeled as dark elongatedareas surrounded by pairs of parallel bright edges in high resolution SAR images.However, the successive road areas are frequently broken by obstacles and shadows,such as vehicles on the road, trees along the road, building shadows covering the road,etc. Road extraction is still a difficult task in high resolution SAR.
Considering the difficulties of current road extraction methods and according to theradiate and geometric properties, the thesis lucubrates on the automatic andsemi-automatic road extraction problems respectively, and automatic road junctions’extraction problems, which can be suitable for different applications.
In the research on the automatic extraction of road junctions from high resolutionSAR images, a new method is proposed for directly detecting and identifying roadjunctions. Firstly, based on the junctions gray feature, global searching is done for thecenter positions of the road junctions’ candidate regions, by using morphologicaltransformation methods. Secondly, the center positions are set as the local windowscenters, road targets are segmented by using the multi-threshold Otsu method in thelocal windows. Thirdly, according to the geometric characteristics of junctions, weobtain the angle-mean figure in the rectangular template rotation process, and then getthe number of the roads connected to a junction. Finally, the style of the junction isrecognized. In1m high-resolution airborne SAR image experiment, the results indicatethat this method is effective to detect and identify the junctions with variousinterferences.
In the research on the automatic extraction of road networks from high resolutionSAR images, Markov random field (MRF) model can make full use of the imagerycontextual characters and priori knowledge, which have been widely used to extractroad networks. However, there exist some problems such as slow solution and manyparameters setting of these type methods. In order to reduce the computation ofsubsequent iterative solution of MRF, pre-linking is firstly introduced to removenumerous false line elements based on the spatial relationship among them. Then, theimproved road networks Markov function model is established to label road networks. SAR images with1meter resolution are tested in the experiment. And the results showthe effectivity of the method mentioned above in high resolution SAR imagery roadnetwork extraction.
In the research on the semi-automatic extraction of road junctions from highresolution SAR images, a new road center-point extraction method is proposed bycombined using local detection and global tracking. In local detection phase, twowindows are set. The outside window is used to obtain the local road direction by usingnon-linear structure tensor, based on the fact that fences, green belts and otherdisturbances point to a consistent direction with the edge of roads. The inside windowadjusts its direction by the result of non-linear structure tensor. Then it searches for theroad areas, and determines the width and center of roads. In global tracking phase,particle filter of variable-step is used for solving the problem of tracking brokenfrequently by occlusions on the road and shadowing alongside the road. In1mhigh-resolution airborne SAR image experiment, the results indicate that this method iseffective.
As mentioned above, this dissertation has explored the methods of road extractionin high-resolution SAR images. Also, these methods would be helpful to enginerringapplications posterior.
引文
[1]Colwell R N. History and place of photographic interpretation[M]. AmericaSociety for Photogrammetry&Remote Sensing: Bethesda,1997.
[2]皮亦鸣,杨建宇,付毓生等.合成孔径雷达成像原理[M].成都:电子科技大学出版社,2007.
[3]Carrara W G, Goodman R S, and Majewski R M, Spotlight Synthetic ApertureRadar: signal processing algorithms[M]. Norwood, MA: Artech House,1995.
[4]AIRSAR [EB/OL]. http://airsar.jpl.nasa.gov.
[5]Northrop Grumman: Protect “E-8C Joint-STRAS”[EB/OL]. http://www.northopgrumman.com/protectjointstars/.
[6]Northrop Grumman: Aerospace systems [EB/OL]. http://www.as. Northrop_grumman.com/index.html.
[7]Miceli W J. Test results from the AN/APY-6SAR/GMTI surveillance, trackingand targeting radar[C]∥In: Proc. of the IEEE Radar Conference, Atlanta, GA, USA:IEEE Press,2001:13~17.
[8]Suchandt S, Palubinskas G, Scheiber R, et al. Results from an airborneSARGMTI experiment supporting TerraSAR-X traffic processor development[C]∥In:Proc. of the IEEE International Geoscience and Remote Sensing Symposium(IGARSS’02), Toronto, Canada: IEEE Press,2005:2949~2952.
[9]Lombardini F, Ender J, R βing L, et al. Experiments of interferometric layoversolution with the three-antenna airborne AER-II SAR system[C]∥In: Proc. of the IEEEInternational Geoscience and Remote Sensing Symposium (IGARSS’04), Anchorag,Alaska, USA: IEEE Press,2004:3341~3344.
[10]Maori D C, Klare J, Brenner A R, et al. Wide-area traffic monitoring with theSAR/GMTI system PAMIR[J]. IEEE Transactions on Geoscience and Remote Sensing,2008,46(10):3019~3030.
[11]CCRS C/X band SAR, CCRS Convair580aircraft [EB/OL]. http://www.ccrs.nrcan.gc.ca/radar/airborne/cxsar/sbc580_e.php.
[12]Uratsuka S, Moriyama T, Umehara T, et al. Disastrous environment afterearthquake observed by airborne SAR (Pi-SAR)[C]∥In: Proc. of the IEEE InternationalGeoscience and Remote Sensing Symposium (IGARSS’05), Seoul, Korea: IEEE Press,2005:4081~4083.
[13][法]Maitre H著,孙洪译.合成孔径雷达图像处理[M].北京:电子工业出版社,2005.
[14]Raytheon: ASTOR SAR Imagery [EB/OL]. http://www.raytheon.com/capabilities/products/astor/sar_imagery/index.html.
[15]EADS: SOSTAR-X [EB/OL]. http://www.eads.com/1024/en/businet/defence/mas/projects/sostar/SOSTAR.html.
[16]Jordan R L, Huneycutt R L, and Werner M. The SIR-C/X-SAR syntheticaperture radar system[J]. IEEE Transactions on Geoscience and Remote Sensing,1995,33(4):829~839.
[17]Chien S, Sherwood R, Zetocha P, et al. The Techsat-21autonomous spacescience agent[C]∥In: Proc. of the First International Joint Conference on AutonomousAgents and Multiagent Systems (AAMAS’02), Bologna, Italy,2002:570~557.
[18]Whelan D A. Discoverer П program summary[C]∥In: Proc. of the IEEERadar Conference, Virginia, USA: IEEE Press,2000:7~8.
[19]Mir-Priroda[EB/OL]. http://old.spaceonline.tv/priroda.htm.
[20]Vant M, Livingstone C, and Rey M. Canadian experience on Radarsat-1andRadarsat-2GMTI for surveillance[C]∥In: Proc. AIAA/ICAS International Air andSpace Symposium and Exposition: The Next100Year, Dayton, OH, USA,2003:1~10.
[21]TerraSAR-X[EB/OL]. http://www.dlr.de/tsx/start_en.htm.
[22]TanDEM-X [EB/OL]. http://ilrs.gsfc.nasa.gov/satellite_missions/list_of_satellites/tand_general.html。
[23] ALOS PALSAR[EB/OL]. http://www.alos-restec.jp/index_e.html
[24]Massonnet D. Capabilities and limitations of the interferometric Cartwheel[J].IEEE Transactions on Geoscience and Remote Sensing,2001,39(3):506~520.
[25]COSMO-SkyMed[EB/OL]. http://cosmos-skymed-ao.asi.it/asi/asi.
[26]ESA: Missions[EB/OL]. http://earth.esa.int/missions/.
[27]贾承丽,匡纲要. SAR图像自动道路提取[J].中国图象图形学报,2005,10(10):1218~1223.
[28]宫鹏,黎夏,徐冰.高分辨率影像解译理论与应用方法中的一些研究问题[J].遥感学报,2006,10(1):1~5.
[29]Negri M, Gamba P, Lisini G, et al. Junction-aware extraction andregularization of urban road networks in high-resolution SAR images[J]. IEEETransactions on Geoscience and Remote Sensing,2006,44(10):217~221.
[30]Bajcsy R, and Tavakoli M. Computer recognition of roads from satellitepictures [J]. IEEE Transactions on Systems, Man and Cybernetics,1976, SMC-6(9):623~637.
[31]Frost V S, Shanmugan K S, and Holtzman J C. Edge detection for syntheticaperture radar and other noisy images[C]//International Geoscience and Remote SensingSymposium, Munich, Germany: IEEE,1982:4.1~4.9.
[32]Touzi R, Lopes A, and Bousquet P. A statistical and geometrical edge detectorfor SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing,1988,26(6):764~773.
[33]Samadani R, and Vesecky J F. Finding curvilinear features in speckled images[J]. IEEE Transactions on Geoscience and Remote Sensing,1990,28(4):669~673.
[34]Tupin F, Ma tre H, Mangin J F, et al. Detection of linear features in SARimages: Application to road network extraction[J]. IEEE Transactions on Geoscienceand Remote Sensing,1998,36(2):434~453.
[35]Tupin F, Houshmand B, and Datcu M. Road detection in dense urban areasusing SAR imagery and the usefulness of multiple views[J]. IEEE Transactions onGeoscience and Remote Sensing,2002,40(11):2405~2414.
[36]Lisini G, Tison C, Tupin F, et al. Feature fusion to improve road networkextraction in high-resolution SAR images[J]. IEEE Geoscience and Remote SensingLetters,2006,3(2):217~221.
[37]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):1908~1917.
[38]Dell'Acqua F, and Gamba P. Detection of urban structures in SAR images byrobust fuzzy clustering algorithms the example of street tracking[J]. IEEE Transactionson Geoscience and Remote Sensing,2001,39(10):2287~2297.
[39]Cheng J H, Guan Y F, Ku X S, et al. Semi-automatic road centerline extractionin high-resolution SAR images based on circular template matching [C]//InternationalConference on Electric Information and Control Engineering, Wuhan, China: IEEE,2011:1688~1691.
[40]Gamba P, and Savazzi P. Classification of urban environments in SAR images:a fuzzy clustering perspective[C]//International Geoscience and Remote SensingSymposium, Seattle, WA, USA: IEEE,1998:351~353.
[41]Gamba P, Dell'Acqua F, and Lisini G. Improving urban road extraction inhigh-resolution images exploiting directional filtering, perceptual grouping, and simpletopological concepts[J]. IEEE Geoscience and Remote Sensing Letters,2006,3(3):387~391.
[42]Gamba P, and Houshmand B. Three-dimensional road network by fusion ofpolarimetric and interferometric SAR data[C]//International Geoscience and RemoteSensing Symposium, Hamburg, Germany: IEEE,1999:302~304.
[43]Lisini G, Gamba P, and Luebeck D. Road extraction in urban and ruralenvironments exploiting a dual-band SAR system[C]//International Geoscience andRemote Sensing Symposium, Vancouver, BC, Canada: IEEE,2011:3610~3613.
[44]Negri M, and Gamba P. Feature fusion for road extraction in SAR scenes[C]//International Geoscience and Remote Sensing Symposium, Denver, CO, USA: IEEE,2006:2514~2517.
[45]Dell'Acqua F, Gamba P, and Lisini G. Extraction and fusion of street networksfrom fine resolution SAR data[C]//International Geoscience and Remote SensingSymposium, Toronto, Ont, Canada: IEEE,2002:89~91.
[46]Dell'Acqua F, Gamba P, and Lisini G. Improvements to urban areacharacterization using multitemporal and multiangle SAR images[J]. IEEE Transactionson Geoscience and Remote Sensing,2003,41(9):1996~2004.
[47] Dell'Acqua F, Gamba P, Odasso L, et al. Segment-based urban block outliningin high-resolution SAR images [C]//2009Joint Urban Remote Sensing Event, Shanghai,China: IEEE,2009:1~6.
[48] Bentabet L, Jodouin S, Ziou D, et al. Road vectors update using SAR imagery:a snake-based method[J]. IEEE Transactions on Geoscience and Remote Sensing,2003,41(8):1785~1803.
[49] Hedman K, Stilla U, Lisini G, et al. Road network extraction in VHR SARImages of urban and suburban areas by means of class-aided feature-level fusion[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(3):1294~1296.
[50]蒋斌. SAR图像道路提取方法研究[D].长沙:国防科学技术大学,2004.
[51]贾承丽. SAR图像道路和机场提取方法研究[D].长沙:国防科学技术大学,2006.
[52]Jeon B K, Jang J H, Hong K S. Road detection in spaceborne SAR imagesusing a genetic algorithm[J]. IEEE Transactions on Geoscience and Remote Sensing,2002,40(1):22~29.
[53]Bolon P, Chanussot J, Issa I, et al. Comparison of prefiltering operators forroad network extraction in SAR images [C]//International Conference on ImageProcessing, Chambery, France: IEEE,1999:924~928.
[54]胡平广,张名成.滤波器组实现SAR图像中主要道路提取[J].计算机仿真,2007,24(3):187~190.
[55]胡平广,薛东升. SAR图像道路目标提取研究[J].计算机仿真,2007,24(4):206~210.
[56]赵青,孔繁兴.基于MAP-MRF模型的SAR图像道路提取[J].系统工程与电子技术,2008,30(10):2028~2030.
[57]张广伟,张永红.基于链码优化的SAR影像城市道路网络提取[J].遥感学报,2008,12(4):620~625.
[58]安成锦,杜琳琳,王卫华等.基于融合边缘检测的SAR图像线性特征提取算法[J].电子与信息学报,2009,31(6):1279~1282.
[59]Geling G, and Ionescu D. An edge detection operator for SAR images[C]//Conference on Electrical and Computer Engineering, Vancouver, BC, Canada: IEEE,1993:14~17.
[60]匡纲要,高贵,蒋咏梅等.合成孔径雷达-目标检测理论、算法及应用[M].长沙:国防科技大学出版社,2007.
[61]Fj rtoft R, Lopes A, and Marthon P. An optimal multiedge detector for SARimage segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing,1998,36(3):793~802.
[62]赵凌君,贾承丽,匡纲要. SAR图像边缘检测方法综述[J].中国图象图形学报,2007,12(12):2042~2049.
[63]Skingley J, and Rye A. The hough transform applied to SAR images for thinline detection[J]. Pattern Recognition Letters,1987,6(3):61~67.
[64]Kang C W, Park R H, and Lee K H. Extraction of straight line segments usingrotation transformation: generalized hough transformation[J]. Pattern Recognition,1991,24(7):633~641.
[65]巫兆聪,万茜婷,梁静等.粒度Hough变换及其在遥感影像直线检测中的应用[J].武汉大学学报-信息科学版,2007,32(10):860~863.
[66]Copeland A C, Ravichandran G, and Trivedi M M. Localized Radontransform-based detection of ship wakes in SAR images[J]. IEEE Transactions onGeoscience and Remote Sensing,1995,33(1):35~45.
[67]Zhang Q P, Couloigner I. Accurate centerline detection and line widthestimation of thick lines using the radon transform[J]. IEEE Transactions on Geoscienceand Remote Sensing,2007,16(2):310~316.
[68]贾承丽,赵凌君,吴其昌等.基于遗传算法的SAR图像道路网检测方法[J].计算机学报,2007,30(7):1186~1194.
[69]Cardoso L A. Computer aided recognition of man-made structures in aerialphotographs[D]. Monterey: Naval Postgraduate School,1999.
[70]Burns J B, Hanson A R, Riseman E. Extracting Straight Lines [J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1986,8(4):426~466.
[71]王程,王润生. SAR图像直线提取[J].电子学报,2003,31(6):816~820.
[72]Lindi J Q. A review of techniques for extracting linear features from imagery[J]. Photogrammetric Engineering&Remote Sensing,2004,70(12):1383~1392.
[73]杨明,尹勇,彭玉华等. Beamlet变换与多尺度线特征提取[J].电子学报,2007,35(1):100~103.
[74]肖志强,鲍光淑.基于GA的SAR图像中主干道路提取[J].中国图象图形学报,2004,9(1):93~98.
[75]洪日昌,吴秀清,刘媛等.低分辨率遥感影像中道路的全自动提取方法研究[J].遥感学报,2008,12(1):36~45.
[76]Deng Q M, Chen Y L, Yang J. Joint detection of roads in multifrequency SARimages based on a particle filter[J]. International Journal of Remote Sensing,2010,31(4):1069~1077.
[77]Chen Y L, Gu Y T, Gu J, et al. Particle filter based road detection in SARimage [C]//IEEE International Symposium on Microwave, Antenna, Propagation andEMC Technologies for Wireless Communications, Beijing, China: IEEE,2005:301~305.
[78]Matthias B. Geometric refinement of road networks using network snakes andSAR images [C]//IEEE International Geoscience and Remote Sensing Symposium,Honolulu, HI, USA: IEEE,2010:49~452.
[79]Sun X F, Li Y C, Lin X G. Semi-automatic extraction of ribbon roads fromVHR remotely sensed SAR imagery [C]//Chinese Conference on Pattern Recognition,Chongqing, China: IEEE,2010:1~4.
[80]Zhou G Y, Cui Y, Chen Y L, et al. Linear feature detection in polarimetricSAR images[J]. EEE Transactions on Geoscience and Remote Sensing,2011,49(4):1453~1463.
[81]肖志强,鲍光淑,黄继先.融合SAR和TM图像更新GIS道路网络数据[J].测绘学报,2006,35(1):46~51.
[82]Zhou J, Cheng L, Bischof W F. Online Learning with novelty detection inhuman-guided road tracking[J]. IEEE Transactions on Geoscience and RemoteSensing,2007,45(12):3967~3977.
[83]Chen T L, Wang J F, and Zhang K Z. A wavelet transform based method forroad centerline extraction[J]. Photogrammetric Engineering&Remote Sensing,2004,70(12):1423~1431.
[84]Amberg V, Coulon M, Marthon P, et al. Improvement of road extraction inhigh resolution SAR data by a context-based approach[C]//IEEE InternationalGeoscience and Remote Sensing Symposium, Seoul, Korea: IEEE,2005:490~493.
[85]Steger C, Glock C, Eckstein W, et. al. Model-based road extraction fromimages[C]//Proceedings Automatic extraction of Man-made Objects from Aerial andSpace Images, Basel, Schweiz, Birkhauser Verlag,1995:275~284.
[86]Hinz S, and Baumgartner A. Automatic extraction of urban road network frommulti-viewaerial imagery[J]. ISPRS Journal of Photogrammetry&Remote Sensing,2003,58:83~98.
[87]CJJ37-90,城市道路设计规范[S].
[88]JTJ001-97,公路工程技术标准[S].
[89]单春芝.基于形态学策略的高分辨率遥感影像道路提取方法研究[D].山东:山东科技大学,2011.
[90]赵凌君.高分辨率SAR图像建筑物提取方法研究[D].长沙:国防科技大学,2009.
[91]Hoheisel S. Automated road extraction from radar and optical imagery[D].Germany: University of Hannover,2003.
[92]舒宁.微波遥感原理[M].武汉:武汉大学出版社,2000.
[93]高贵. SAR图像统计建模研究综述[J].信号处理,2009,25(8):1270-1278.
[94]Bruzzone J, Marconcini M, Wegmuller U, and Wiesmann A. An advancedsystem for the automatic classification of multitemporal SAR images[J]. IEEETransactions on Geoscience and Remote Sensing,2004,42(3):1321-1334.
[95]Mantero P. Partially supervised classification of remote sensing images usingSVM-based probability density estimation[J]. IEEE Transactions on Geoscience andRemote Sensing,2005,43(7):559-570.
[96]Gao G. A parzen-window-kernel-based CFAR algorithm for ship detection inSAR images[J]. IEEE Geoscience and Remote Sensing Letters,2011,8(3):557-561.
[97]Frery A C, Muller H J, Costa C D, Yanasse C D C F, and Sant’ Anna S J S. Amodel for extremely heterogeneous clutter[J]. IEEE Transactions on Geoscience andRemote Sensing,1997,35(3):648-659.
[98]Joughin I R. Maximum likelihood estimation of K distribution parameters forSAR data[J]. IEEE Transactions on Geoscience and Remote Sensing,1993,31(5):989-999.
[99]Freitas C C, Frery A C, and Correia A H. The polarimetric G distribution forSAR data[J]. Environmetries,2005,16(1):13-31.
[100]Allende H, Frery A C, Galbiati J, and Pizarro L. M-estimators withasymmetric influence functions: the G0distribution case[J]. Journal of StatisticalComputation and Simulation,2006,76(11):941-956.
[101]时公涛,高贵,周晓光等.基于Mellin变换的G0分布参数估计方法[J].自然科学进展,2009,19(6):677-690.
[102]Tison C, Nicolas J M, Tupin F, and Ma tre H. A new statistical model forMarkovian classification of urban areas in high-resolution SAR images[J]. IEEETransactions on Geoscience and Remote Sensing,2004,42(10):2046-2057.
[103]吴亮,胡云安.参考道路交叉点的飞行器视觉辅助导航[J].北京航空航天大学学报,2010,36(8):892~895.
[104]赵东保,盛业华.全局寻优的矢量道路网自动匹配方法研究[J].测绘学报,2010,39(4):416~421.
[105]Gautama S, Goeman W, and D'Haeyer J. Robust detection of road junctionsin VHR images using an improved ridge detector[C]//The International Archives of thePhotogrammetry, Remote Sensing and Spatial Information Sciences, Istanbul, Turkey,2004:815~819.
[106]Ravanbakhsh M, Heipke C, and Pakzad K. Knowledge-based road junctionextraction from high-resolution aerial images [C]//2007Urban Remote Sensing JointEvent, Paris, France,2007:1~8.
[107]Iisaka J, Sakurai-Amano T, and Lukowski T I. Automated detection of roadintersections from ERS-1SAR imagery[C]//International Geoscience and RemoteSensing Symposium, Florence, Italy,1995:676~678.
[108]Chiang Y Y, Knoblock C A, Shahabi C, et al. Automatic and accurateextraction of road intersections from raster maps[J]. Geoinformatica,2009,13(2):121~157.
[109]Barsi A, and Heipke C. Detecting road junctions by artificial neural networks
[C]//Remote Sensing and Data Fusion over Urban Areas,2nd GRSS/ISPRS JointWorkshop on, Berlin, Germany,2003:129~132.
[110]陈晓飞,薛峰,王润生.航空照片中道路交叉口的自动检测[J].模式识别与人工智能,2000,13(1):83~86.
[111]Hu J X, Anshuman R, John C, et al. Road network extraction and intersectiondetection from aerial images by tracking road footprints[J]. IEEE Transactions onGeoscience and Remote Sensing,2007,45(12):4144~4157.
[112]黄石生,朱炬波,谢美华.基于变分的SAR图像目标特征增强方法[J].红外与毫米波学报,2010,29(5):392~396.
[113]Li P J, Li Z X. Comparison of three geostatistical texture measures forremotely sensed data classification[J]. Geography and Geo-Information Science,2003,19(4):89-92.
[114]赵凌君,高贵,匡纲要.基于变差函数纹理特征的高分辨率SAR图像建筑区提取[J].信号处理,2009,25(9):1433-1442.
[115]Lin X G, Liu Z J, Zhang J X, and Shen J. Combining multiple algorithms forroad network tracking from multiple source remotely sensed imagery: a practical systemand performance evaluation[J]. Sensors,2009,9:1237~1258.
[116]Ranjani J J, Gokila M, and Thiruvengadam S J. Edge detection in speckledSAR images with improved ROEWA[C].//Sixth Indian Conference on Computer Vision,Graphics&Image Processing, New Jersey: IEEE Press,2008:644~649.
[117]安成锦,辛玉林,陈曾平.基于改进ROEWA算子的SAR图像边缘检测方法[J].中国图象图形学报,2011,16(8):1483~1488.
[118]吴禹昊,陈天泽,粟毅.基于方向ROEWA算子的高分辨率SAR图像道路提取[J].计算机工程与科学,2010,32(8):71~74.
[119]Otsu N. A threshold selection method from gray level histograms[J]. IEEETransactions on System Man and Cybernetic,1979,9(1):62~66.
[120]Xu G, Sun H,Yang W, et al. An improved road extraction method based onMRFs in rural areas for SAR images[C]//1st Asian and Pacific Conference onSynthetic Aperture Radar Proceedings, Washington: IEEE Press,2007,1:489~492.
[121]Li S Y, Yang W, Yang H, et al. Road extraction from high resolutiondual-polarization SAR images over urban areas[C]//Proc. of SPIE, InternationalConference on Earth Observation Data Processing and Analysis, Washington: SPIEPress,2008,7285:1~10.
[122]余长慧,易尧华.利用MRF方法的高分辨率影像道路提取[J].武汉大学学报-信息科学版,2011,36(5):544~547.
[123]Metropolis N, Rosenbluth A, Rosenbluth M, et. al. Equation of statecalculations by fast computing machines[J]. J.Chem. Phy s.,1953,21:1087-1092.
[124]Kirkpatrick S, Celatt C D, Vecchi M P. Optimization by simulated annealing[J]. Sciences,1983,220:671~680.
[125]Besag J. On the statistical analysis of dirty pictures [J]．Journal of RoyalStatistical Society,1986, B48:259~302.
[126]Wiedemann C, Heipke C, Mayer H, et al. Empirical evaluation ofautomatically extracted road axes[R]. In Workshop on Empirial Evaluation on Methodsin Computer Vision,1998:172-187.
[127]Kim T J, Park S R, Soo J. Tracking road centerlines from high resolutionremote sensing images by least squares correlation matching[J]. PhotogrammetricEngineering&Remote Sensing,2004,70(12):1417~1422.
[128]Zhou J, Bischof W F, Caelli T. Road tracking in aerial images based onhuman-computer interaction and Bayesian filtering[J]. Photogrammetry&RemoteSensing,2006,61(2):108~124.
[129]Lin X G, Zhang J X, Liu Z J, Shen J, and Duan M Y. Semi-automaticextraction of road networks by least squares interlaced template matching in urban areas[J]. International Journal of Remote Sensing,2011,32(17):4943~4959.
[130]Sahar M, Alireza M, Ahad T. Road extraction from satellite images usingparticle filtering and extended kalman filtering[J]. IEEE Transactions on Geoscienceand Remote Sensing,2010,48(7):2807~2817.
[131]Kjain A, Vailaya A. Image retrieval using color and shape[J]. PatternRecognition,1996,29(8):1233~1244.
[132]Cheng J H, Guan Y F, Ku X S, and Sun J X. Semi-automatic road centerlineextraction in high-resolution SAR images based on circular template matching[C]//International Conference on Electric Information and Control Engineering, Wuhan,China,2011:1688~1691.
[133]Frost V S, Stiles J A, Shanmugan K S, and Holtzman J C. A model for radarimages and its application to adaptive digital filtering of multiplicative noise[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1982,4(2):157~166.
[134]唐亮,谢维信,黄建军等.一种新的道路描述子:对称边缘方向直方图[J].电子学报,2005,33(1):7~11.
[135]张道兵,张慧,张正等.一种稳健的道路主方向提取算法[J].光子学报,2007,36(S1):326~330.
[136]Brox T, Weickert J, Burgeth B, et al. Nonlinear structure tensors[J]. Imageand Vision Computing,2006,24(1):41~55.
[137]鉴福升,徐跃民,阴泽杰.多模型粒子滤波跟踪算法研究[J].电子与信息学报,2010,32(6):1271~1276.
[138]Baumgartner A, Hinz S, and Wiedemann C. Efficient methods and interfacesfor road tracking[J]. International Archives of Photogrammetry and Remote Sensing,2002,34(3):309~312.
[139]唐晓芬.基于水平集的遥感图像道路提取方法研究[D].杭州:浙江大学,2010.
[140]吴学文,徐涵秋.一种基于水平集方法提取高分辨率遥感影像中主要道路信息的算法[J].宇航学报,2010,31(5):1495-1502.
[141]曹广真,金亚秋.基于水平集方法的多源遥感数据融合及城区道路提取[J].电子与信息学报,2007,29(6):1464-1470.
[142]孙即祥.图像处理[M].北京:科学出版社,2009.
[143]孙即祥.现代模式识别(第二版)[M].北京:高等教育出版社,2008.