SAR图像中道路和桥梁识别方法研究
|
摘要
道路和桥梁是当今世界上主要的陆地交通设施,同时也是军事领域中的重要目标。合成孔径雷达(SAR)可以有效获得大面积的高分辨率的雷达图像,且具有全天候、全天时的成像特点,这些优点使得其在民用和军事的各个领域应用十分广泛。随着合成孔径雷达技术的发展以及交通、战争对SAR图像中的陆地目标信息需求的增多,人们对SAR图像中道路和桥梁的目标识别研究也日益增多。
本文以道路和桥梁目标的特征为基础,以对SAR图像的理解为背景,重点围绕SAR图像中道路和桥梁的特征选择与目标识别进行了较为深入的研究。
论文综合讨论了各种传统滤波和基于相干斑噪声滤波的方法,在此基础上,比较并选取了适合SAR图像滤波并能较好保留图像边缘信息的Lee滤波作为预处理的工具。同时讨论了多种可行的图像分割方法,为下面的目标识别提供充足的理论准备。
在对道路目标的几种特征进行分析的基础上,选择了较易提取和使用的形状特征和辐射特征,研究了一种基于动态规划的SAR图像道路目标识别的方法。实验证明该方法能够比较准确对道路目标进行识别与定位,同时能够较好的解决时间开销大、虚警率高的问题。但是由于道路阴影和噪声干扰的影响,识别结果仍然存在一定的断裂和虚警情况,需要进一步的研究解决。
在对桥梁目标的几种特征进行分析的基础上,选择了较易提取和使用的形状特征和辐射特征。首先利用桥梁的形态特征,提出了一种利用桥梁的长宽比、位置信息、平行边缘的信息进行识别的方法。实验证明该方法简单、快速、虚警率较低、识别率较高。但是由于SAR图像的噪声干扰,存在目标外形失真的情况,本文针对这个问题,提出了一种基于Pun熵的统计特征的识别方法。该方法在不明显提高算法复杂度和时间开销的前提下,提高了识别率,降低了虚警率,并具有一定的算法鲁棒性。
Road and Bridge are the main land traffic facilities in the world today, while they are also the important targets in the military field. Synthetic Aperture Radar (SAR) has been widely applied to gain large-area and high-resolution images, all-day and all-weather. These make SAR widely used in aerospace, ground reconnaissance, remote sensing or resource census etc. As the recognition of road and bridge is very useful for image registration, precision-guidance, map drawing and target detection and so on, the research on this field becomes more and more important.
Based on the features of road and bridge, this paper mainly researched on the choosing of features and target recognition of road and bridge with the background of SAR image understanding.
This paper firstly study on several traditional filters and some filters based on coherent speckle, and choose Lee filter to pre-process the original images, for Lee filter can de-noise well and reserve the edge information effectively. Also we talk about some image segmentation algorithms to get the theoretical basis of the recognition steps.
Based on analyzing kinds of features, we choose shape and radiate features to recognize road targets, as these features are easy to extract and use. We advised a road recognition algorithm based on dynamic programming, which is proved to be effective on recognition and orientation, with high rate of recognition and low rate of false target. However, the result still has some problems about rupture and false target because of the noise and shadow.
Based on analyzing kinds of features, we choose shape and radiate features to recognize bridge targets, as these features are easy to extract and use. First, we advised an algorithm based on the shape features, such as parallels, length-width ratio, position information and so on. Experiment results show the good qualities of the algorithm, such as fast speed, high rate of recognition, and low rate of false target. However, since the shape may be distorted in SAR images by the noise, we proposed a novel algorithm for bridge recognition using Histogram Entropy presented by Pun which is stable on shape distortion. This algorithm increased the recognition rate, decreased the rate of false target, and showed robustness in several conditions, while the time cost and algorithm complexity are not increased evidently.
本文以道路和桥梁目标的特征为基础,以对SAR图像的理解为背景,重点围绕SAR图像中道路和桥梁的特征选择与目标识别进行了较为深入的研究。
论文综合讨论了各种传统滤波和基于相干斑噪声滤波的方法,在此基础上,比较并选取了适合SAR图像滤波并能较好保留图像边缘信息的Lee滤波作为预处理的工具。同时讨论了多种可行的图像分割方法,为下面的目标识别提供充足的理论准备。
在对道路目标的几种特征进行分析的基础上,选择了较易提取和使用的形状特征和辐射特征,研究了一种基于动态规划的SAR图像道路目标识别的方法。实验证明该方法能够比较准确对道路目标进行识别与定位,同时能够较好的解决时间开销大、虚警率高的问题。但是由于道路阴影和噪声干扰的影响,识别结果仍然存在一定的断裂和虚警情况,需要进一步的研究解决。
在对桥梁目标的几种特征进行分析的基础上,选择了较易提取和使用的形状特征和辐射特征。首先利用桥梁的形态特征,提出了一种利用桥梁的长宽比、位置信息、平行边缘的信息进行识别的方法。实验证明该方法简单、快速、虚警率较低、识别率较高。但是由于SAR图像的噪声干扰,存在目标外形失真的情况,本文针对这个问题,提出了一种基于Pun熵的统计特征的识别方法。该方法在不明显提高算法复杂度和时间开销的前提下,提高了识别率,降低了虚警率,并具有一定的算法鲁棒性。
Road and Bridge are the main land traffic facilities in the world today, while they are also the important targets in the military field. Synthetic Aperture Radar (SAR) has been widely applied to gain large-area and high-resolution images, all-day and all-weather. These make SAR widely used in aerospace, ground reconnaissance, remote sensing or resource census etc. As the recognition of road and bridge is very useful for image registration, precision-guidance, map drawing and target detection and so on, the research on this field becomes more and more important.
Based on the features of road and bridge, this paper mainly researched on the choosing of features and target recognition of road and bridge with the background of SAR image understanding.
This paper firstly study on several traditional filters and some filters based on coherent speckle, and choose Lee filter to pre-process the original images, for Lee filter can de-noise well and reserve the edge information effectively. Also we talk about some image segmentation algorithms to get the theoretical basis of the recognition steps.
Based on analyzing kinds of features, we choose shape and radiate features to recognize road targets, as these features are easy to extract and use. We advised a road recognition algorithm based on dynamic programming, which is proved to be effective on recognition and orientation, with high rate of recognition and low rate of false target. However, the result still has some problems about rupture and false target because of the noise and shadow.
Based on analyzing kinds of features, we choose shape and radiate features to recognize bridge targets, as these features are easy to extract and use. First, we advised an algorithm based on the shape features, such as parallels, length-width ratio, position information and so on. Experiment results show the good qualities of the algorithm, such as fast speed, high rate of recognition, and low rate of false target. However, since the shape may be distorted in SAR images by the noise, we proposed a novel algorithm for bridge recognition using Histogram Entropy presented by Pun which is stable on shape distortion. This algorithm increased the recognition rate, decreased the rate of false target, and showed robustness in several conditions, while the time cost and algorithm complexity are not increased evidently.
引文
[1]匡纲要,计科峰,粟毅,郁文闲. SAR图象自动目标识别研究[J].中国图像图形学报, Vol.8(A), NO.10, 2003年10月, 1115-1120.
[2]刘永坦.雷达成像技术[M].哈尔滨工业大学出版社,1999.
[3]Verbout S M, Irving W W, Hanes A S. Improving a Templatedbased Classifier in a SAR Automatic Target Recognition System by Using 3-D Target Information[J]. Lincoln Laboratory Journal, 1993, 6(1), 53-76.
[4]Diemunsch Joseph, Wissinger John. Moving and Stationary Target Acquisition and Recognition (MSTAR) Model-based Automatic Target Recognition[J]: Searching Technology for a Robust ATR. SPIE, 1998, 3370, 481-492.
[5]刘迎春,宋建社,郑永安. SAR图像识别提取与选择特征[J].航空计算技术, Vol.33, No.4, 2003年12月, 55-58.
[6]Jian L, Zelnio E G. Target Detection with Synthetic Aperture Radar[J]. IEEE Transaction on Aerospace Electroni Systems, 1996, 32(2), 613-627.
[7]Rignot E, Kwok R. Characterization of Spatial Statistics of Distributed Targets in SAR[J]. International Journal of Remote Sensing, 1993, 14(2), 345-363.
[8]董江曼,李应岐,邓飚. SAR图像舰船目标的特征识别[J].陕西师范大学学报(自然科学版), Vol. 32, Sup, 2004年6月, 203-205.
[9]解凯. SAR图像特征提取与降噪方法的研究[D].西安交通大学硕士论文, 2002.5.
[10]黄波.星载SAR图像处理[D].东南大学硕士论文, 2002.3.
[11]Wang X. Lee Filter for Multiscale Image Denoising [J]. Signal Processing, The 8th International Conference on, Volume 1, 2006, 16-20.
[12]Jone-Sen Lee. A simple speckle smoothing algorithm for synthetic aperture radar images. IEEE Trans. on System, Man, and Cybernatics, 1983, Vol.13, No.1.
[13]Jone-Sen Lee. Digital image enhancement and noise filtering by use of local statistics. IEEE Trans. on PAMI., 1980,Vol.2,No.2.
[14]Mallat S G. A Theory of Multiresolution Signal Decomposition : the Wavelet Representation[J]. IEEE Trans. on PAMI , 1989, 11, 674-693.
[15]容观澳编著.计算机图像处理.清华大学出版社, 2000年.
[16]潘湘岳,宋建社,吴建新.基于数据融合的SAR图像斑点噪声抑制.雷达科学与技术, Vol.5, No.6, 2007年12月, 443-446.
[17]王丽辉,袁保宗.鲁棒的模糊C均值和点云双边滤波去噪.北京交通大学学报, Vol.32, No.2, 2008年4月, 18-21.
[18]章毓晋编著.图像处理和分析.清华大学出版社, 2000年.
[19]刘秀兰,马丹等.一种新的快速动态阈值图像分割算法.北京工业大学学报, Vol.25, No.2, 1999年, 92-96.
[20]蔡志刚.一种改进的SAR影像斑点噪声抑制方法.地理信息世界, No.1, 2008年2月, 73-89.
[21]吴建华,李迟生,周卫星.中值滤波与均值滤波的去噪性能比较.南昌大学学报(工科版), No.1, 1998年, 32-35.
[22]S.Horowitz, T.Pavlidis. Picture segmentation by a tree traversal algorithm, JACM, Vol 23, 1976, 368-388.
[23]Tupin F, Matre H, Mangin J F, et al. Detection of linear features in SAR images: Application to road network extraction [J]. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(2), 434-453.
[24]Kartartzis A, Sahli H, Pizurica V, et al. A model-based approach to the automatic extraction of linear features form airborne images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(9), 2073-2079.
[25]Jeon B, Jang J, Hong K. Road detection in spaceborne SAR images using a genetic algorithm [J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(1): 22-29.
[26] LI Su-dan, WANG Zheng-zhi, ZHANG Cui. Road network detection in SAR images [J]. Journal of National University of Defense Technology, 2001, 23(1), 59-65. [郦苏丹,王正志,张翠. SAR图像中道路的检测[J].国防科技大学学报, 2001, 23(1),59-65.]
[27]LI Su-dan, ZHANG Cui, WANG Zheng-zhi. A study of road network detection method for SAR images [J]. Journal of Astronautics, 2002, 23(1): 17-24. [郦苏丹,王正志,张翠. SAR图像中道路检测方法研究[J].宇航学报, 2002, 23 (1): 17-24.]
[28] RJ Brown, B Guindon, PM Teillet, DG Goodenough. Crop type determination from multitemporal SAR imagery. Proc. 9th Can. Symp. on Remote Sens, 1984.
[29] G Franceschetti, V Pascazio, G Schirinzi. Iterative homomorphic technique for speckle reduction in synthetic-aperture radar imaging. Journal of the Optical Society of America A, 1995, Vol.12, No.4, 16-20.
[30]H Xie, FT Ulaby, LE Pierce, MC Dobson. Performance metrics for SARspeckle-suppression filters. Geoscience and Remote Sensing Symposium, 1999, Vol.3, 1540-1542.
[31]A Baraldi, F Parmiggiani, M IMGA-CNR. A modified version of the SAR speckle filter based on structuredetection. Geoscience and Remote Sensing Symposium, 1994, Vol.4, 2168-2172.
[32]王建国,杨晋浩.一种新的SRA图像Speckle滤波算法.电子科技大学学报, Vol.24, No.5, 461-466, 1995.
[33]李凌杰,王建国,一种基于区域分集的SAR相干斑抑制算法.电子科技大学学报, Vol.25, No.2, 113-115, 1996.
[34]M Cheriet, JN Said, CY Suen. A recursive thresholding technique for image segmentation. Image Processing, IEEE Transactions on, Vol.7, 918-921, Jun 1998.
[35]刘健庄.基于二维直方图的图象模糊聚类分割方法.电子学报, Vol.20, No.9, Sep. 1992.
[36]王鹏伟,李滔,吴秀清.一种基于SVM后验概率的MRF分割方法.遥感学报, 12(2), 2008.
[37]吴成柯,刘靖.图像分割的遗传算法方法.西安电子科技大学学报, 23(1), 1996.
[38]Su F L, Wu ZM, Lin X L. An Algorithm of Bridge Detection in Remote Sensing Images Based on Fractal[A]. Proceedings.2003 6th International Symposium [C]. 28 Oct.-1 Nov. 2003: 600-602.
[39]侯彪,刘芳,焦李成.高分辨率SAR图象中桥梁目标的自动分割.激光与红外, 2004, 34(1): 46-49.
[40]杜宗岗,卢凌等.基于知识的航空图象水上桥梁目标识别.武汉理工大学学报, 2005, 29(2): 230-233.
[41]Wu F, Wang C, Zhang H. Recognition of Bridge by Integrating Satellite SAR and Optical Imagery[A]. Geoscience and Remote Sensing Symposium 2005. IGARSS’05. Proceedings. 2005 IEEE International[C]. Volume 6, 25-29 July 2005:3939-3941.
[42]于大洋,周露,杨健等.基于极化合成孔径雷达数据的桥梁检测.清华大学学报(自然科学版), 2005, 45(7): 888—891.
[43]Hou Biao, Li Ying and Jiao Licheng. Segmentation and Recognition of Bridges in High Resolution SAR Images. Radar, 2001 CIE International Conference on, Proceedings,479-482.
[44]吴皓,刘政凯,张荣. TM图象中桥梁目标识别方法的研究.遥感学报, 2003,7(6):478-484.
[45]吴樊,王超等.基于知识的中高分辨率光学卫星遥感影像桥梁目标识别研究.电子与信息学报, 2006, 28(4): 587-591.
[46]杨浩,尹东,洪日昌.高分辨率遥感图象中桥梁自动识别方法研究.计算机仿真, 2006, 23(9): 119-122.
[47]戴光照,张荣.高分辨率SAR图象中的桥梁识别方法研究.遥感学报, 2007, 11(2): 177-184.
[48]Pun T. A New Method for Gray Level Picture Thresholding Using the Entropy of the Histogram [J]. Signal Processing, 1980, 2(3): 223-237.
[49]Bovik A C. On detecting edges in speckle imagery [J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 1988, 36(10): 1618～1627.
[50]Touzi R, Lopes A, Bousquet P. A statistical and geometrical edge detection for SAR images [J]. IEEE Transactions on Geoscience and Remote Sensing, 1988, 26(6): 764～773.
[51]Gray Geling, Dan Jonescu. An edge detection operator for SAR images[A]. In: Canadian Conference on Electrical and Computer Engineering [C], Canada, 1993, 2: 707～709.
[2]刘永坦.雷达成像技术[M].哈尔滨工业大学出版社,1999.
[3]Verbout S M, Irving W W, Hanes A S. Improving a Templatedbased Classifier in a SAR Automatic Target Recognition System by Using 3-D Target Information[J]. Lincoln Laboratory Journal, 1993, 6(1), 53-76.
[4]Diemunsch Joseph, Wissinger John. Moving and Stationary Target Acquisition and Recognition (MSTAR) Model-based Automatic Target Recognition[J]: Searching Technology for a Robust ATR. SPIE, 1998, 3370, 481-492.
[5]刘迎春,宋建社,郑永安. SAR图像识别提取与选择特征[J].航空计算技术, Vol.33, No.4, 2003年12月, 55-58.
[6]Jian L, Zelnio E G. Target Detection with Synthetic Aperture Radar[J]. IEEE Transaction on Aerospace Electroni Systems, 1996, 32(2), 613-627.
[7]Rignot E, Kwok R. Characterization of Spatial Statistics of Distributed Targets in SAR[J]. International Journal of Remote Sensing, 1993, 14(2), 345-363.
[8]董江曼,李应岐,邓飚. SAR图像舰船目标的特征识别[J].陕西师范大学学报(自然科学版), Vol. 32, Sup, 2004年6月, 203-205.
[9]解凯. SAR图像特征提取与降噪方法的研究[D].西安交通大学硕士论文, 2002.5.
[10]黄波.星载SAR图像处理[D].东南大学硕士论文, 2002.3.
[11]Wang X. Lee Filter for Multiscale Image Denoising [J]. Signal Processing, The 8th International Conference on, Volume 1, 2006, 16-20.
[12]Jone-Sen Lee. A simple speckle smoothing algorithm for synthetic aperture radar images. IEEE Trans. on System, Man, and Cybernatics, 1983, Vol.13, No.1.
[13]Jone-Sen Lee. Digital image enhancement and noise filtering by use of local statistics. IEEE Trans. on PAMI., 1980,Vol.2,No.2.
[14]Mallat S G. A Theory of Multiresolution Signal Decomposition : the Wavelet Representation[J]. IEEE Trans. on PAMI , 1989, 11, 674-693.
[15]容观澳编著.计算机图像处理.清华大学出版社, 2000年.
[16]潘湘岳,宋建社,吴建新.基于数据融合的SAR图像斑点噪声抑制.雷达科学与技术, Vol.5, No.6, 2007年12月, 443-446.
[17]王丽辉,袁保宗.鲁棒的模糊C均值和点云双边滤波去噪.北京交通大学学报, Vol.32, No.2, 2008年4月, 18-21.
[18]章毓晋编著.图像处理和分析.清华大学出版社, 2000年.
[19]刘秀兰,马丹等.一种新的快速动态阈值图像分割算法.北京工业大学学报, Vol.25, No.2, 1999年, 92-96.
[20]蔡志刚.一种改进的SAR影像斑点噪声抑制方法.地理信息世界, No.1, 2008年2月, 73-89.
[21]吴建华,李迟生,周卫星.中值滤波与均值滤波的去噪性能比较.南昌大学学报(工科版), No.1, 1998年, 32-35.
[22]S.Horowitz, T.Pavlidis. Picture segmentation by a tree traversal algorithm, JACM, Vol 23, 1976, 368-388.
[23]Tupin F, Matre H, Mangin J F, et al. Detection of linear features in SAR images: Application to road network extraction [J]. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(2), 434-453.
[24]Kartartzis A, Sahli H, Pizurica V, et al. A model-based approach to the automatic extraction of linear features form airborne images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(9), 2073-2079.
[25]Jeon B, Jang J, Hong K. Road detection in spaceborne SAR images using a genetic algorithm [J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(1): 22-29.
[26] LI Su-dan, WANG Zheng-zhi, ZHANG Cui. Road network detection in SAR images [J]. Journal of National University of Defense Technology, 2001, 23(1), 59-65. [郦苏丹,王正志,张翠. SAR图像中道路的检测[J].国防科技大学学报, 2001, 23(1),59-65.]
[27]LI Su-dan, ZHANG Cui, WANG Zheng-zhi. A study of road network detection method for SAR images [J]. Journal of Astronautics, 2002, 23(1): 17-24. [郦苏丹,王正志,张翠. SAR图像中道路检测方法研究[J].宇航学报, 2002, 23 (1): 17-24.]
[28] RJ Brown, B Guindon, PM Teillet, DG Goodenough. Crop type determination from multitemporal SAR imagery. Proc. 9th Can. Symp. on Remote Sens, 1984.
[29] G Franceschetti, V Pascazio, G Schirinzi. Iterative homomorphic technique for speckle reduction in synthetic-aperture radar imaging. Journal of the Optical Society of America A, 1995, Vol.12, No.4, 16-20.
[30]H Xie, FT Ulaby, LE Pierce, MC Dobson. Performance metrics for SARspeckle-suppression filters. Geoscience and Remote Sensing Symposium, 1999, Vol.3, 1540-1542.
[31]A Baraldi, F Parmiggiani, M IMGA-CNR. A modified version of the SAR speckle filter based on structuredetection. Geoscience and Remote Sensing Symposium, 1994, Vol.4, 2168-2172.
[32]王建国,杨晋浩.一种新的SRA图像Speckle滤波算法.电子科技大学学报, Vol.24, No.5, 461-466, 1995.
[33]李凌杰,王建国,一种基于区域分集的SAR相干斑抑制算法.电子科技大学学报, Vol.25, No.2, 113-115, 1996.
[34]M Cheriet, JN Said, CY Suen. A recursive thresholding technique for image segmentation. Image Processing, IEEE Transactions on, Vol.7, 918-921, Jun 1998.
[35]刘健庄.基于二维直方图的图象模糊聚类分割方法.电子学报, Vol.20, No.9, Sep. 1992.
[36]王鹏伟,李滔,吴秀清.一种基于SVM后验概率的MRF分割方法.遥感学报, 12(2), 2008.
[37]吴成柯,刘靖.图像分割的遗传算法方法.西安电子科技大学学报, 23(1), 1996.
[38]Su F L, Wu ZM, Lin X L. An Algorithm of Bridge Detection in Remote Sensing Images Based on Fractal[A]. Proceedings.2003 6th International Symposium [C]. 28 Oct.-1 Nov. 2003: 600-602.
[39]侯彪,刘芳,焦李成.高分辨率SAR图象中桥梁目标的自动分割.激光与红外, 2004, 34(1): 46-49.
[40]杜宗岗,卢凌等.基于知识的航空图象水上桥梁目标识别.武汉理工大学学报, 2005, 29(2): 230-233.
[41]Wu F, Wang C, Zhang H. Recognition of Bridge by Integrating Satellite SAR and Optical Imagery[A]. Geoscience and Remote Sensing Symposium 2005. IGARSS’05. Proceedings. 2005 IEEE International[C]. Volume 6, 25-29 July 2005:3939-3941.
[42]于大洋,周露,杨健等.基于极化合成孔径雷达数据的桥梁检测.清华大学学报(自然科学版), 2005, 45(7): 888—891.
[43]Hou Biao, Li Ying and Jiao Licheng. Segmentation and Recognition of Bridges in High Resolution SAR Images. Radar, 2001 CIE International Conference on, Proceedings,479-482.
[44]吴皓,刘政凯,张荣. TM图象中桥梁目标识别方法的研究.遥感学报, 2003,7(6):478-484.
[45]吴樊,王超等.基于知识的中高分辨率光学卫星遥感影像桥梁目标识别研究.电子与信息学报, 2006, 28(4): 587-591.
[46]杨浩,尹东,洪日昌.高分辨率遥感图象中桥梁自动识别方法研究.计算机仿真, 2006, 23(9): 119-122.
[47]戴光照,张荣.高分辨率SAR图象中的桥梁识别方法研究.遥感学报, 2007, 11(2): 177-184.
[48]Pun T. A New Method for Gray Level Picture Thresholding Using the Entropy of the Histogram [J]. Signal Processing, 1980, 2(3): 223-237.
[49]Bovik A C. On detecting edges in speckle imagery [J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 1988, 36(10): 1618～1627.
[50]Touzi R, Lopes A, Bousquet P. A statistical and geometrical edge detection for SAR images [J]. IEEE Transactions on Geoscience and Remote Sensing, 1988, 26(6): 764～773.
[51]Gray Geling, Dan Jonescu. An edge detection operator for SAR images[A]. In: Canadian Conference on Electrical and Computer Engineering [C], Canada, 1993, 2: 707～709.