摘要
空间数据的更新已成为目前世界各国的地理信息系统的数据库面临的突出问题。随着遥感技术的不断发展，特别是各种SAR传感器的相继上天，遥感作为空间数据获取的一种手段，其在空间数据更新中的作用显得越来越重要。当前，从遥感图像中，尤其是高分辨率SAR图像中提取道路网络已成为遥感技术应用研究中的热点之一，其目的就是利用自动或半自动提取技术为道路中心线的描述和GIS空间数据库的更新提供一种行之有效的方法。论文在总结分析国内外已有研究成果的基础上，对高分辨率SAR图像中道路网络提取方法及地理信息系统空间数据更新方法进行了深入研究。
高分辨率SAR图像中细节丰富，目标背景异常复杂，同时SAR图像受其固有的斑点噪声的影响，很难直接从原始图像中提取道路网络。针对这一特性，论文对高分辨率SAR图像进行聚类分析，将道路类象素从图像中分离出来，使问题得到简化。然后分别建立不同的数学模型，利用遗传算法和Snakes方法提取道路中心线。提出了两种从高分辨率SAR图像中提取道路网络的半自动提取方法。实验结果表明基于遗传算法的道路网络提取算法具有较高的计算精度，但计算时间稍长，而基于Snakes的提取方法计算速度较快，但计算精度有所下降。
对于合成孔径雷达这种侧视遥感器图像，SAR图像中道路与周围背景对比度强弱与雷达的侧视方向及道路的延伸方向密切相关，针对这一问题，提出了一种多阈值局部检测算子。局部检测的各方向的道路象素经过曲线拟合形成相应方向的道路线段。以提取的道路线段为图的顶点建立道路网络的数据结构，将这些线段有效地组织起来。针对局部检测的道路线段之间“相邻”等关系具有不确定性，提出了一种利用模糊推理系统进行道路线段全局连接的方法。利用该方法连接道路线段的具体步骤包括共线连接，线段整合，交叉点连接等，每一步包含一个Mamdani类型的模糊推理系统。该方法具有较好的适应性，只要合理选择模糊规则，就可以利用模糊系统将道路线段连接起来形成道路网络。
同一区域各种不同传感器数据之间存在一定的冗余和互补信息，
融合多种传感器数据可以减少系统总的不确定性，增加提取特征的精
确性。为充分利用各种传感器数据更准确地提取道路网络，论文提出
了一种融合多传感器数据提取道路网络的方法。在局部检测时，基于
DRO线性特征检测算子的基本思想，针对雷达图像和光学图像特性，
分别设计了一种改进的局部检测算子，该算子可以检测任意方向的道
路象素。利用D一S证据理论融合两算子分别在SAR图像和TM图像
中的检测结果，融合检测结果经细化和线性拟合后，利用模糊推理系
统融合先验知识对道路线段进行连接。试验结果表明融合检测的网络
较单独从SAR图像中提取的结果无论是完整性还是正确性都有明显
提高。同时，论文还对文中提出的各种道路网络提取算法的定量评价
方法进行了探讨。
最后，论文对利用遥感图像更新地理信息系统道路网络数据的方
法进行了研究，提出了一种线性特征变化检测的方法。该方法以地理
信息系统的道路网络图层中单个道路特征为变化检测单元，对道路特
征中两坐标点之间线段与遥感图像中融合检测的相应道路线段进行
匹配，判断是否应对原有数据进行校正或增加新的道路特征。该方法
克服了缓冲区检测算子对特征局部变化不敏感的局限性。
The update of spatial data has become a serious problem confronted by the database of geographical information system all over the world. With the development of the technique of remote sensing, especially the launch of the SAR remote sensors, remote sensing, as a tool to update the spatial data, is becoming more and more important. Currently, the road network extraction from the remote sensing images, especially from the high-resolution SAR images, has become a hotspot in remote sensing application research. And the goal is to offer viable and cost-effective approaches for road centerline delineation and for revision of spatial databases using automated or semi-automated extraction techniques. Based on the analysis and summarization of the research home and abroad, the dissertation makes deep research on the methods to extract road network from SAR images and to update the spatial data of GIS.
In high-resolution SAR images, rich details and the complicated background of objectives, along with the intrinsic speckle, make it difficult to extract road network directly from original SAR images. Aiming at this problem, fuzzy C means is first used to classify the SAR images to extract road pixels, and then GA or Snakes to extract road centerline according to different mathematical models. The dissertation presents two semi-automated methods to extract road network from high-resolution SAR images. The experimental results show that the method based on GA bears higher accuracy, but the computing time is a little longer, while the speed of the method based on Snakes is faster, but the accuracy falls.
The contrast of road in SAR images with the background is tightly related with the side-looking direction of radar and the extension direction of roads. Aiming at this problem, a multi-threshold detector is presented. The road pixels detected by the local detectors form into road segments of the corresponding direction by using curve fitting. And a data structure of graph whose vertices are the extracted road segments is constructed for road network to organize the segments effectively.
Because of the uncertainty existing in the relations (such as proximity) between the road segments, a method to connect road segments using fuzzy inference system is presented. In this method, there are three steps ?Collinearity connection, segment mergence and junction connection. And each step includes a fuzzy inference system of Mamdani type. The method possesses very preferable adaptability. If only fuzzy rules selected rationally, the fuzzy inference system can connect segments into road network.
Because of the redundant and complementary information existing in different sensor data from the same areas, it can reduce the uncertainty and improve the accuracy of the extracted features by fusing multi-sensor data. In order to make full use of all kinds of sensor data to extract road network more exactly, the dissertation presents a method to extract road network by fusing multi-sensor data. During the local detection, aiming at the features of radar images and optical images, the respective line detectors are devised based on the thought of Dudo Road Operator (DRO), and they can detect road pixels at any direction. The Dempster-Shafer evidence theory is used to fuse the detected results of different sensor images such as SAR images and TM images. After the road pixels obtained by fusion being thinned and fitted linearly, the road segments are connected conditionally by using the fuzzy reasoning system that fuses some prior knowledge. The result shows that both the completeness and correctness of the road network obtained by the fusion method are sharply higher than that of the road network extracted only from SAR images. And the quality of the road network extraction algorithm presented in this dissertation is evaluated.
Finally, the dissertation makes research on the method to update road network data of GIS by using remote sensing images, and presents an algorithm for linear features to detect changes. Taking each road feature in the
引文
[1] 谢寿生，徐永进．微波遥感技术与应用．北京：电子工业出版社，1987
[2] 舒宁．微波遥感原理．武汉：武汉大学出版社，2000．
[3] Fritsch D. GIS data revision--visions and reality[R]. Keynote Speech in Joint ISPRS Commission Workshop on Dynamic and Multi-dimensional GIS. Beijing: NGCC, 1999.
[4] Uitermark H. Propagating updates: finding corresponding objects in a Multisource Environment [A]. Proceedings of 8th SDH [C]. Vancouver: International Geogra-phical Union, 1998, 580-591.
[5] Bajesy R, Tavakoli M. Computer recognition of roads fromsatellite pictures. IEEE Transactions on Systems, Man, and Cybernetics. 1976, 6(9): 623-637.
[6] 李德仁，关泽群．空间信息系统的集成与实现．武汉：武汉大学出版社，2000．
[7] Fishler M, Tenenbaum J, Wolf H. Detection of roads and linearstructures in low-resolution aerial imagery using a multisource knowledge integration technique. Computer Graphics and Image Processing, 1981, 15:201-223.
[8] Grün A, Li h. Road extractionfrom aerial and satellite images by dynamic programming. ISPRS Journal of Photogrammetry and Remote Sensing, 1995, 50(4): 11-20.
[9] Merlet N, Zerubia J. New prospects in line detection by dynamic programming. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(4): 570-585.
[10] Steger C. Extracting curvilinear structures: a differential geometric approach. Fourth European Conference on Computer Vision, 1996, 630-641.
[11] Quam, Lynn H. Road tracking and anomaly detection in aerial imagery. Image Understanding workshop, 1978, 51-55.
[12] McKeown D, Denlinger J. Coorpertive methods for road tracking in aerial imagery. Computer Vision and Pattern Recognition, 1988, 662-672.
[13] Kass M, Witkin A, Terzopoulos D. Snakes: active contour models. International Journal of Computer Vision, 1987, 1(4): 321-331.
[14] Trinder J, Li H. Extraction of man-made features by 3-D ative contour models. International Archives of Photogrammetry and Remote Sensing, 1996, 31: 874-879.
[15] Fua P, Leclerc Y. Model driven edge detection. Machine Vision and Applications, 1990, 3: 45-56.
[16] Neuenschwander W. Elastic deformable contour and surface models for 2-D and 3-D image segmentation. 1996, Hartung-Gorre Verlag, konstanz.
[17] Grün A, Li h. Linear feature extraction with LSB-Snakes from multiple images. International Archives of Photogrammetry and Remote Sensing, 1996, 31: 266-272.
[18] Baumgartner A, Steger C, Mayer H, et al. Multi-resolution semantic objects and
context for road extraction. Akzeptiert für: Sematic Modelling and Topographic Information,1997.
[19] Donald G; Jedynak B. An active testing model for tracking roads in satellite images [J]. IEEE Transactions on Pattern Analysis and Machine Imtelligence, 1996, 18(1): 1-14
[20] Gruen A. Adaptive least squares coorelation: a powerful image matching technique [J]. South African Journal of Photogrammetry, Remote Sensing and Cartography, 1985, 14(3): 175-187.
[21] Gruen. A, Li H. Semi-automatic linear feature extraction by dynamic programming and LSB-Snakes [J]. Photogrammetric Engineering and Remote Sensing, 1997, 63(8): 985-995.
[22] Trinder J C, Li H. Semi-automatic linear feature extraction by snakes [A]. Automatic Extraction of Manmade Objects from Aerial and Space Images[C]. Bessel: Birkhaeuser Verlag, 1995, 95-104.
[23] Steger C, Mayer H, Radig B. The role of grouping for road extraction [A]. Automatic Extraction of Manmade Objects from Aerial and Space Images (2)[C]. Bessel: Birkhaeuser Verlag, 1997, 245-255.
[24] Steger C. Extracting curvilinear structures: a differential geometric approach [A]. Fourth European Conference on Computer Vision [C]. Bash: Springer Verlag, 1996, 630-641.
[25] 史文中，朱长青，王昱．从遥感影像提取道路特征的方法综述与展望．测绘学报，2001，30(3)：257-262．
[26] Trinder J C, Wang Y D, Sowmya A, et al. Artificial intelligence in 3D feature extracion. Automatic extraction of man-made objects from aerial and space images [C], Basel, Birkhaeuser Vedag, 1997, 257-265.
[37] Ton J, Jain A K, Enslin W R, et al. Automatic road identification and labeling in Landsat4 TM images [J]. Photogmmmetric (PRS), 1989, 43(2): 257-276.
[28] Wang F G; Newkirk R. A knowledge-based system for highway network extraction[J]. IEEE Transaction on Geoscience and Remote Sensing, 1988, 26(5): 525-531.
[29] Barzohar M, Cooper D B. Automatic finding of main roads in aerial images by using geometie-stochastic models and estimation[J]. IEEE Tansactions on Pattern Analysis and Machine Intelligence, 1996, 18(7): 707-727.
[30] Agouris P, Stefanidis A, Gyftakis S. Differential snakes for change detection in road segments. Photogrammetric Engineering and Remote Sensing. 2001, 67(12): 1391-1400.
[31] Bordes G, Giraudon G, Jamet O. Road modeling based on a cartographic database for aerial image interpretation. In: Semantic Modeling for the Acquisition of Topographic Information from Images and Maps. 1997, 123-139, Birkhauser Verlag Basel.
[32] Gunst M, Vosselman G. A semantic road model for aerial image interpretation. In: Semantic Modeling for the Acquisition of Topographic Information from Images and Maps, 1997, 107-122, Birkh(?)user Verlag.
[33] Zhang C, Baltsavias E. Knowledge-based image analysis for 3D edge extraction
and road reconstruction. In: International Archives of Photogrammetry and Remote Sensing, 2000, 1008-1015, ISPRS.
[34] Byoung-Ki Jeon, Jeong-Hun Jang, Ki-Sang Hong. Road detection in spaceborne SAR images using a genetic algorithm [J]. EEE Transactions on Geoscience and Remote Sensing, 2002,40(1): 22-29.
[35] Byoung-Ki Jeon, Jeong-Hun Jang, Ki-Sang Hong. Road detection in SAR images using genetic algorithm with region growing concept [C]. IEEE International Conference on Image Processing, 2000, 688-691.
[36] Byoung-Ki Jeon, Jeong-Hun Jang, Ki-Sang Hong. Road detection in space borne SAR images based on ridge extraction. IEEE International Conference on Image Processing, 1999, 2:735-739.
[37] Lee J. A simple speckle smoothing algorithm for synthetic aperture radar images. IEEE Transactions on Systems, Man, and Cybernet, 1983, 13: 85-89.
[38] Jocelyn Chanussot, Giles Maufis, Patrick Lambert. Fuzzy fusion techniques for linear features detection in multitemporal SAR images. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(3): 1292-1304.
[39] Touzi R, Lopes A, Bousquet P. A statistical and geometrical edge detector for SAR images. IEEE Transactions on Geoscience and Remote Sensing, 1988, 26(6): 764-773.
[40] Bovik A C. On detecting edges in speckle imagery. IEEE Transactions on Acoustic Speech and Signal Processing, 1988, 36(10): 1618-1627.
[41] Tupin F, Mangin J F, Nicolas J M, et al. Detection of linear features in SAR images: application to road network extraction. IEEE Transactions on Geoscience and Remote Sensing. 1998, 36(2):434-453.
[42] 郦苏丹，张翠，王正志．SAR图像中道路检测方法研究[J]．宇航学报，2002，23(1)：17-24．
[43] Reinhold Huber, Konmd Lang. Road extraction from high-resolution airborne SAR using operator fusion. Intemational Geoscience and Remote Sensing Symposium (IGARSS), 6:2813-2815, 2001.
[44] Jocelyn Chanussot, Patrick Lambert. An application of mathematical morpholohy to road network extraction on SAR images. In Proceeding of 4th Intemational Symposius, Mathematical Morpholohy and Its Applications, Amsterdam, The Netherlands, 1998, 399-406.
[45] Jocelyn Chanussot, Gilles Mauris, Patrick Lambert. Fuzzy fusion technique for linear features detection in multitemporal SAR images. IEEE Transactions on Geoscience and Remote Sensing, 37(3): 1292-1304, 1999.
[46] Katartzis A, Sahli H, Pizurica V, et al. A model-based approach to the automatic extraction of linear features from airborne images. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(9): 2073-2079.
[47] Fabio Dell' Acqua, Paolo Gamba. Detection of urban structures in SAR images by robust fuzzy clustering algorithms: the example of street tracing. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(10): 2287～2296.
[48] Tupin E Radar cross-views for road detection in dense urban areas. EUSAR2000, Munich, Germany, 2000, 617-622.
[49] Tupin F, Houshmand B, Datcu M. Road detection in denseurban areas using SAR imagery and the usefulness of multiple views. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(11): 405-2413.
[50] Fabio Dell'Acqua, Paolo Gamba, Gianni Lisini. Road map extraction by multiple detectors in fine spatial resolution SAR data. Can. J. Remote Sensing, 29(4): 481-490, 2003.
[51] Toenjes R, Growe S. Knowledge based road extraction from multisensor imagery. International Archives of Photogrammetry and Remote Sensing. 32(3): 387-393, 1998.
[52] Hellwich O. Detection of linear objects in ERS-1 SAR images using neural networ technology. In: Proceeding of IEEE International Geoscience and Remote Sensing Sympsium, Pasadena, CA, 1994.
[53] Bonnefon R, Dhérété P, Desachy J. Geographic information system updating using remote sensing images. Pattern Recognition Letters, 23:1073-1083,2002.
[54] Haigang SUI, Deren LI, Jianya GONG. Automatic change detection for road networks from imagery based on GIS. IAPRS, Xi'an, 2002.
[55] Steger C, Eckstein W, Wiedemann C. Updating of roads in GIS by automatic extraction from aerial imagery. International Airborne Remote Sensing Conference and Exhibition, San Francisco, California, 1996.
[56] Dan Klang. Automatic detection of changes in road databases using satellite imagery. In Proceedings of International Archives of Photogrammetry and Remote Sensing, 32:293-298,1998.
[57] Marie-Flavie Auclair Fortier, Djemel Ziou, Costas Armenakis, et al. Automatic updating of road information from aerial images. American Society Photogrammetry and Remote sensing Conference, Washington, 2002.
[58] Wenzhong Shi, Changqing Zhu. The line segment match for extracting road from high resolution satellite images. IEEE Trans. Geosci. Remote Sensing, 2002, 40(2):511～514.
[59] Peter Doucette, Peggy Agouris, Anthony Stefanidis, et al. Self-organised clustering for road extraction in classified imagery. Photogammetry and Remote Sensing, 2001, 55: 347-358.
[60] Uri Kroszynski, Jianjun Zhou. Fuzzy clustering principles, methods and examples. IKS, December 1998
[61] Bezdek J C, Pattern recognition with fuzzy objective ftmction algorithms, Plenum Press, New York 1981.
[62] 郭桂蓉．模糊模式识别．长沙：国防科技大学出版社，1993．
[63] 陈国良，王煦法，庄镇泉，等．遗传算法及其应用．北京：人民邮电出版社，1996．
[64] 周明，孙树栋．遗传算法原理及应用．北京：国防工业出版社，1999．
[65] 陈建安，郭大伟，徐乃平，等．遗传算法理论研究综述．西安电子科技大学学报，25(3)：363-368，1998．
[66] 刘键庄，谢维信，高新波，等．基于Hausdorff距离和遗传算法的物体匹配方法．电子学报，24(4)：1-6，1996．
[67] 吴成柯，刘靖，侯格贤．图像分割的多参量遗传算法．自动化学报，24(3)：
410-413，1998．
[68] 李宏贵，李兴国，李国桢，等．一种基于遗传算法的红外图像增强方法．系统工程与电子技术，21(7)：44-46，1999．
[69] Amini J, Saradjian M R, Blais J A R, et al. Automatic road-side extraction from large scale imagemaps. International Journal of Applied Earth Observation and Geoinformation, 2002, 4: 95-107.
[70] Gruen A, Li H. Semi-automatic linear feature extraction by dynamic programming and LSB-Snakes. PE&RS, 1997, 63(8): 985-995.
[71] Kass M, Witkin A, Terzopoulos D, Snakes: active contour models. Proceedings of First International Conference on Computer Vision, London, 1987, 259-269.
[72] Amini A A, Tehrani S, Weymouth T E. Using dynamic programming for minimizing the energy of active contours in the presence of hard constraints. In: Proceedings of Second International Conference on Computer Vision, 1988, 95-99.
[73] Amini A A, Weymouth T E, Jain R C. Using dynamic programming for solving variational problems in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(9): 855-866
[74] Williams D J, Mubarak Shah. A fast algoithm for acive contours and curvature estimation. CVGIP: Image Understanding, 1992, 55(1): 14-26
[75] Touzi R, Lopes A, Bousquet P. A statistical and geometrical edge detector for SAR images. IEEE Trans. Geosci. Remote Sensing. 1988, 26(6):764-773.
[76] Oliver C J. Edge detection for SAR segmentation. SPIE Proc. 1994, 216: 80-91.
[77] Hellwich O, Meyer H. Extracting line feature from synthetic aperture radar using a Markov random field mode, in proc. 3rd IEEE Int. Conf. Image processing, 1996.
[78] Tupin F, Mangin J F, Nicolas J M, et al. Detection of linear features in SAR images: application to road network xxtraction. IEEE Trans. Geosci. Remote Sensing. 1998, 36(2):434-453.
[79] Jinfei Wang, Howarth P J. Use of the Hough transform in automatic linearment detection. IEEE Transactions on Geoscience and Remote Sensing, 1990, 28(7): 561-566.
[80] Burns J B. Extracting straight lines. IEEE Trans.on PAMI. 1986. 8(4): 425-455.
[81] 王润生．图像理解．长沙：国防科技大学出版社，1995．
[82] Ruskoné R, Airault S, Jamet O. Road network interpretation: A topological hypothesis driven system. International Archives of Photogrammetry and Remote Sensing, 1994, 711-717.
[83] Moissinac H, Maitre H, Bloch I. Graph based urban scene analysis using symbolic data. Integrating Photogrammetric Technique with Scene Analysis and Machine vision Ⅱ, 1995, Proc. SPIE 2486, 93-104.
[84] Steger C, Mayer H, R.ading B. The role of grouping for road extraction. Automatic extraction of Man-Made Objects from Areal and Space Images(Ⅱ). 1997, 245-256.
[85] 刘同明，夏祖勋，解洪成．数据融合技术及其应用．北京：国防工业出版社，1998．
[86] Solberg S, Jain A K, Taxt T. Multi-source classification of remotely sensed data: fusion of Landsat TM and SAR images. IEEE Transactions on Geoscience and Remote Sensing, 1994, 32(4): 768-777.
[87] Solberg S, Jain A K, Taxt T. A markov random field model for classification of multi-source satellite imagery. IEEE Transactions on Geoscience and Remote Sensing, 1996, 34(1): 100-113.
[88] Costantiti M, Farina A, Zirili F. The fusion of different resolution SAR images. In: Proceedings of the IEEE, 1997, 85(1): 139-146.
[89] 贾永红．遥感多光谱影像空间分辨力增强的融合方法．遥感技术与应用，1997，(1)：9-23．
[90] 何国金，李克鲁．星载合成孔径雷达遥感及多卫星数据融合方法．地质科技情报，1997，16：29-33．
[91] Hall D L. Mathematical techniques in multi-sensor data fusion[M]. Boston: Artech House, 1992.
[92] Kim H, Swain H P. Multi-source data analysis in remote sensing and geographic information systems based on Shafer's theory of evidence, In: International Geoscience and remote sensing Symposium.Vancouver B.C.Canada,1989: 829-832.
[93] Jimenez Luis O. Classification of hyper-dimensional data based on feature and decision fusion approach using projection pursuit, majority voting, and neural networks. IEEE Transactions on Geoscience and Remote Sensing, 1999,37(3):1360-1366.
[94] Lorenzo Bruzzone, et al. Neural-statistical approach to multitemporal and multisource remote-sensing image classification. IEEE Transactions on Geoscience and Remote Sensing, 1999,37(31): 1350-1359.
[95] Jocelyn chanussot, Gilles Mauris, Patrick Lambert. Fuzzy fusion techniques for linear features detection in multi-temporal SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(3): 1292 1305.
[96] Solaiman Bassel. Multisensor data fusion using fuzzy concepts: Application to land-cover classification using ERS-1/JERS-1 SAR composites. IEEE Transactions on Geoscience and Remote Sensing, 1999,37(3): 1316-1326.
[97] Byeungwoo Jeon. Decision fusion approach for multitemporal classification. IEEE Transactions on Geoscience and Remote Sensing, 1999,37(3): 1227-1233.
[98] Jon Atli Benediktsson. Classification of multisource and hyperspectral data based on decision fusion. IEEE Transactions on Geoscience and Remote Sensing, 1999,37(3): 1367-1377.
[99] Jmenez Luis O. Classification of hyperd-mensional data based on feature and decision fusion approaches using projection pursuit, majority voting, and neural networks [J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(3): 1360-1366.
[100] Fischler M A, Tenenbaum J M, Wolf H C. Detection of roads and linear structures in low-resolution aerial imagery using a multisouree knowledge integration technique. Computer Graphics and Image Processing, 14: 201-223, 1981.
[101] Roux M. Reealage d'images multi-sources. Application au recalage d'une image SPOT et d'une carte. Ph.D. thesis, ENST - Paris - France, 1992.
[102] Dh(?)r(?)t(?) P, Desachy J, V. B. Data fusion for linear geographic features matching on SPOT images. ISPRS WG Ⅱ/6- international society of photogrammetry and remote sensing Integration of image understanding into cartographic systems, Paris, April, 99, (1998).
[103] Reinhold Huber, Konrad Lang. Road extraction from high-resolution airborne SAR using operator fusion. International Geoscienee and Remote Sensing Symposium (IGARSS), 6:2813-2815, 2001.
[104] Heipke C, Mayer H, Wiedemann C, et al. Evaluation of automatic road extraction. International Archives of Photogrammetry and Remote Sensing, 1997, 32:47-56.
[105] Couloigner I, Ranchin T. Extraction of urban network from high spatial resolution satellite imagery: assessment of the quality of an automated method. Proceedings of the EARSel Symposium "Operational Remote Sensing for Sustainable Development", Enschede, The Netherlands, 1998, 309-314.
[106] Harvey W A. Performance evaluation for road extraction. ISPRS Proceedings of the International Workshop on 3D Geospatial Data Production, Paris.
[107] Airault S, Jamet O, Leymarie F. From manual to automatic Stereoplotting: evaluation of different road network capture processes. International Archives of Photogrammetry and Remote Sensing, 1996, 31(3): 14-18.
[108] Ruskon(?) R, Airault S. Toward an automatic extraction of the road network by local interpretation of the scene. Pbotogrammetric week'97, 1997, 147-157.
[109] CMU. Performance evaluation for feature extraction, http://www.cs.cmu.edu/afs/cs/usr/maps/www/rcvw/terrainweek97/roads/tw97-roadeval.root.html.
[110] Christmas W J, Kittler J, Petrou M. Structural matching in computer vision using probabili stic relaxation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 749-764.
[111] Walter V. Zuordnung von raumbezogenen Daten-am Beispiel der Datenmodelle ATKIS und GDF. PhD thesis, 1996, University Stuttgart.
[112] Wiedemann C, Heipke C, Mayer H, et al. Empirical evaluation of automatically extracted road axes. In: K. J. Bowyer and P. J. Philips (eds), Empirical Evaluation Methods in Computer Vision, IEEE Computer Society Press, Los Alamitos, California, 1998, 172-187.
[113] McKeon D M, Bowling J M, Bulwinkle G E, et al. Research in the automated analysis of remotely sensed imagery: 1995-1996. Proceedings of the DARPA Image Understanding Workshop, 1997, 779-812.
[114] http://www.luoxunjie.8u8.com/news/gm-market.htm.
[115] Patynen V. Digital orthophotos and map revision in national land survey of Finland [A]. International Archives of Photogrammetry and Remote Sensing on GIS between Visions and Applications: 32-B4[C], Stuttgart: Ifp, 1998, 463-466.
[116] Asperen. Digital updates at the Dutch Topographic service [A]. International Archives of Photogrammetry and Remote Sensing: XXXI[C], Vienna: [s.n.], 1996, 891-900.
[117] Effenberg W W. Data flows, standards and incremental cadastral update [A]. The 8th Colloquium of the Spatial Information Research Center[C], New Zealand: [s. n.], 1996, 53-59.
[118] Hojholt P, Grum J. Revision of maps registrating only true changes [A]. Proceedings of 19th International Cartographic Conference and 11th General Assembly of ICA[C], Ottawa: [s. n.], 1999, 173-179.
[119] Ramirez J R. Spatial data revision: current research and its influence in GIS. Proceedings of Position, Location, and Navigation Symposium, 1996, Atlanta, Georgia, 137-144.
[120] Peggy Agouris, Anthony Stefanidis, Sotirios Gyftakis. Differential snakes for change detection in doad segments. Photogrammetric Engineering and Remote Sensing, 67(12):1391-1399, 2001.
[121] Peter J D. Digital change detection techniques: civilian and military application [Z]. Published in the UK in 1999 by Tavlar & Francis Ltd.
[122] 李德仁．利用遥感影像进行变化检测．武汉大学学报(信息科学版)，2003，28(5)：7-12．
[123] Ralf Tnjes, Stefa Growe. Knowledge based road extraction from multisensor imagery. ISPRS Symposium: Object Recognition and Scene Classification from Multispectral and Multisensor Pixels, 1998, Columbus, Ohio, USA.
[124] Merlet N, Zerubia J. New propects in line detection by dynamic programming. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(4): 426-431.
[125] Fischler M A. The perception of linear structure: a generic linker. Image Understanding Workshop, Morgan Kaufmann Publishers, San Francisco, CA, USA, 1994, 1565-1579.
[126] Vasudevan S, Cannon R L, Bezdek J C. Heuristics for intermediate level road finding algorithms. Computer Vision, Graphics, and Image Processing, 1988, 44: 175-190.
[127] Zhu M L, Yeh P S. Automatic road network detection on aerial photographs. Computer Vision and Pattern Recognition. 1986, 34-40.
[128] Ruskon(?) R, Airault S, Jamet O. Road network interpretation: a topological hypothesis driven system. International Archives of Photogrammetry and Remote Sensing, 1994, 711-717.
[129] 张文修，梁怡．不确定性推理原理．西安：西安交通大学出版社，1996．
[130] 张智星，孙春在，小谷英二[日]．神经．模糊和软计算．西安：西安交通大学出版社，2000．
[131] 赵振宇，徐用懋．模糊理论和神经网路的基础与应用．清华大学出版社，广西科学技术出版社，1997．
[132] 郭桂蓉．模糊模式识别．长沙：国防科技大学出版社，1992．
[133] 刘普演，吴孟达．模糊理论及其应用．长沙：国防科技大学出版社，1998．
[134] 瞿继双，王超，王正志．基于数据融合的遥感图像处理技术．2002，7(10)：985-993．
[135] 将捷，陈军．基础地理信息数据库更新的若干思考．测绘通报，2000，5：1-3．
[136] 陈述彭，鲁学军，周成虎．地理信息系统导论．北京：科学出版社，1999．
[137] 朱光，季晓燕，戎只．地理信息系统基本原理及应用．北京：测绘出版社，1997．
