面向变化检测的遥感影像弹性配准方法
|
摘要
对于遥感载荷技术指标差异、观测角度、时相、地形起伏等内外部因素造成的几何畸变,采用全局配准方法制约着影像配准和变化检测精度的提高。提出一种基于加速抗差特征(speed up robust feature,SURF)算法的全局匹配和像元局部配准模型相结合的弹性配准方法,以不同时相遥感影像的差值特征影像各像元正态分布密度函数构建像元局部参数解算权重,缓减不同时相影像中辐射亮度差异较大的像元对局部配准模型参数解算的影响,采用城市典型区域遥感影像进行实验,结果表明该方法影像配准精度(包括地形起伏区域)优于1个像元,弹性配准算法的适用性和运算速度有一定的提高。
Algorithms based on global rigid model can not resolve local geometric distortion problems caused by internal and external factors such as different remote sensing payloads,observation angles,times,and topography.Gobal algorithms restrict accuracy improvemenst in automatic registration and change detection in remote sensing images.In this paper,we present an elastic registration method based on a preliminary global speed up robust feature(SURF)affine registration method,local translation,and smoothing models.We constructed the weight function with normal density function of each pixel in the difference image to weaken errors of local translation paramters,caused by different radiation intensities of pixels.Experiments using urban area data show that this method of image registration(including topography area)is more accuracate than a pixel,and is applicable and effective for change detection.
Algorithms based on global rigid model can not resolve local geometric distortion problems caused by internal and external factors such as different remote sensing payloads,observation angles,times,and topography.Gobal algorithms restrict accuracy improvemenst in automatic registration and change detection in remote sensing images.In this paper,we present an elastic registration method based on a preliminary global speed up robust feature(SURF)affine registration method,local translation,and smoothing models.We constructed the weight function with normal density function of each pixel in the difference image to weaken errors of local translation paramters,caused by different radiation intensities of pixels.Experiments using urban area data show that this method of image registration(including topography area)is more accuracate than a pixel,and is applicable and effective for change detection.
引文
[1]Dai X,Khorram S.The Effects of Image Misregistration on the Accuracy of Remotely Sensed Change Detection[J].IEEE Transactions on Geoscience and Remote Sensing,1998,36:1 566-1 577
[2]Shi Wenzhong,Hao Ming.Analysis of Spatial Distribution Pattern of Change-detection Error Caused by Misregistration[J].International Journal of Remote Sensing,2013,34(19):6 883-6 897
[3]Wu Jianwei,Qin Yanping.Analysis on Accuracy Factors of Multi-source Remote Sensing Image Registration by Polynomial model[J].Computer Engineering and Applications,2009,45(32):153-155(邬建伟,秦艳平.多源遥感影像多项式配准精度影响因素分析[J].计算机工程与应用.2009,45(32):153-155)
[4]Goshtasby,Ardeshir A.Image Registration by Local Approximation Methods[J].Image Vision Computing,1988,6(4):255-261
[5]Ehlers M,Fogel D N,High-precision Geometric Correction of Airborne Remote Sensing Revisited:the Multiquadric Interpolation[J].Proceedings of SPIE:Image and Signal Processing for Remote Sensing,1994,2 315:814-824
[6]Wiemker R,Rohr K,Binder L,et al.Application of Elastic Registration to Imaginery from Airborne Scanners[J].International Archives for Photogrammetry and Remote Sensing,1996,XXXI-B4:949-954
[7]Xing Shuai,Tan Bing,Li Jiansheng,et al.Approach of High Accurate Multisensor Remote Sensing Images Registration Based on Tiny Facet Primitive[J].Journal of Geomatics Science and Technology,2003,20(2):124-128(邢帅,谭兵,李建胜,等.基于小面元的多源遥感影像高精度配准方法[J].测绘科学技术学报,2003,20(2):124-128)
[8]Zhang Jixian,Li Guosheng,Zeng Yu.The Study on Automatic and High-Precision Rectification and Registration of Multi-source Remote Sensing Imagery[J].Journal of Remote Sensing,2005,9(1):73-77(张继贤,李国胜,曾钰.多源遥感影像高精度自动配准的方法研究[J].遥感学报,2005,9(1):73-77)
[9]You Hongjian,Hu Yanfeng.Investigation on Fine Registration for SAR and Optical Image[J].Journal of Radars,2014,3(1):78-84(尤红建,胡岩峰.SAR和光学图像精配准技术的研究[J].雷达学报,2014,3(1):78-84)
[10]Li Ming,Li Deren,Fan Dengke,et al.An Automatic PC-SIFT-Based Registration of Multi-source Images from Optical Satellites[J].Geomatics and Information Science of Wuhan University,2015,40(1):64-70(李明,李德仁,范登科,等.利用PC-SIFT的多源光学卫星影像自动配准方法[J].武汉大学学报·信息科学版,2015,40(1):64-70)
[11]Zhang Zexu,Li Jinzong,Li Dongdong.Research of Automated Image Registration Technique for Infrared Images Based on Optical Flow Field Analysis[J].Journal of Infrared and Millimeter Waves,2003,22(4):307-312(张泽旭,李金宗,李冬冬.基于光流场分析的红外图像自动配准方法研究[J].红外与微波毫米学报,2003,22(4):307-312)
[12]Feng Li.Development of Super Resolution Techniques for Finer Scale Remote Sensing Image Mapping[D].Sydney:University of New South Wales,2009
[13]Feng Li,ChuanRong Li,LingLi Tang,Yi Guo.Elastic Registration for Airborne Multispectral Line Scanners[J].Journal of Applied Remote Sensing,2016,8(1):4 480-4 494
[14]Bay H,Tuytelaars T,Gool L V.SURF:Speeded Up Robust Features[J].Computer Vision and Image Understanding,2008,110(3):346-359
[15]Fishler M A,Bolles R C.Random Sample Consensus:A Paradigm for Model Fitting with Application to Image Analysis and Automated Cartography[J].Communication of Association for Computing Machinery,1981,24(6):381-395
[16]Zhang Qian,Jia Yonghong,Hu Zhongwen.An Improved SIFT Algorithm for Multi-source Remote Sensing Image Registration[J].Geomatics and Information Science of Wuhan University,2013,38(4):455-459(张谦,贾永红,胡忠文.多源遥感影像配准中的SIFT特征匹配改进[J].武汉大学学报·信息科学版,2013,38(4):455-459)
[17]Bruzzone L,Bovolo F,Marchesi S.A Multiscale Change Detection Technique Robust to Registration Noise[J].Pattern Recognition and Machine Intelligence,2007,LNCS 4815:77-86
[18]Celik T.Multiscale Change Detection in Multitemporal Satellite Images[J].IEEE Geoscience and Remote Sensing Letters,2009,6(4):820-824
[2]Shi Wenzhong,Hao Ming.Analysis of Spatial Distribution Pattern of Change-detection Error Caused by Misregistration[J].International Journal of Remote Sensing,2013,34(19):6 883-6 897
[3]Wu Jianwei,Qin Yanping.Analysis on Accuracy Factors of Multi-source Remote Sensing Image Registration by Polynomial model[J].Computer Engineering and Applications,2009,45(32):153-155(邬建伟,秦艳平.多源遥感影像多项式配准精度影响因素分析[J].计算机工程与应用.2009,45(32):153-155)
[4]Goshtasby,Ardeshir A.Image Registration by Local Approximation Methods[J].Image Vision Computing,1988,6(4):255-261
[5]Ehlers M,Fogel D N,High-precision Geometric Correction of Airborne Remote Sensing Revisited:the Multiquadric Interpolation[J].Proceedings of SPIE:Image and Signal Processing for Remote Sensing,1994,2 315:814-824
[6]Wiemker R,Rohr K,Binder L,et al.Application of Elastic Registration to Imaginery from Airborne Scanners[J].International Archives for Photogrammetry and Remote Sensing,1996,XXXI-B4:949-954
[7]Xing Shuai,Tan Bing,Li Jiansheng,et al.Approach of High Accurate Multisensor Remote Sensing Images Registration Based on Tiny Facet Primitive[J].Journal of Geomatics Science and Technology,2003,20(2):124-128(邢帅,谭兵,李建胜,等.基于小面元的多源遥感影像高精度配准方法[J].测绘科学技术学报,2003,20(2):124-128)
[8]Zhang Jixian,Li Guosheng,Zeng Yu.The Study on Automatic and High-Precision Rectification and Registration of Multi-source Remote Sensing Imagery[J].Journal of Remote Sensing,2005,9(1):73-77(张继贤,李国胜,曾钰.多源遥感影像高精度自动配准的方法研究[J].遥感学报,2005,9(1):73-77)
[9]You Hongjian,Hu Yanfeng.Investigation on Fine Registration for SAR and Optical Image[J].Journal of Radars,2014,3(1):78-84(尤红建,胡岩峰.SAR和光学图像精配准技术的研究[J].雷达学报,2014,3(1):78-84)
[10]Li Ming,Li Deren,Fan Dengke,et al.An Automatic PC-SIFT-Based Registration of Multi-source Images from Optical Satellites[J].Geomatics and Information Science of Wuhan University,2015,40(1):64-70(李明,李德仁,范登科,等.利用PC-SIFT的多源光学卫星影像自动配准方法[J].武汉大学学报·信息科学版,2015,40(1):64-70)
[11]Zhang Zexu,Li Jinzong,Li Dongdong.Research of Automated Image Registration Technique for Infrared Images Based on Optical Flow Field Analysis[J].Journal of Infrared and Millimeter Waves,2003,22(4):307-312(张泽旭,李金宗,李冬冬.基于光流场分析的红外图像自动配准方法研究[J].红外与微波毫米学报,2003,22(4):307-312)
[12]Feng Li.Development of Super Resolution Techniques for Finer Scale Remote Sensing Image Mapping[D].Sydney:University of New South Wales,2009
[13]Feng Li,ChuanRong Li,LingLi Tang,Yi Guo.Elastic Registration for Airborne Multispectral Line Scanners[J].Journal of Applied Remote Sensing,2016,8(1):4 480-4 494
[14]Bay H,Tuytelaars T,Gool L V.SURF:Speeded Up Robust Features[J].Computer Vision and Image Understanding,2008,110(3):346-359
[15]Fishler M A,Bolles R C.Random Sample Consensus:A Paradigm for Model Fitting with Application to Image Analysis and Automated Cartography[J].Communication of Association for Computing Machinery,1981,24(6):381-395
[16]Zhang Qian,Jia Yonghong,Hu Zhongwen.An Improved SIFT Algorithm for Multi-source Remote Sensing Image Registration[J].Geomatics and Information Science of Wuhan University,2013,38(4):455-459(张谦,贾永红,胡忠文.多源遥感影像配准中的SIFT特征匹配改进[J].武汉大学学报·信息科学版,2013,38(4):455-459)
[17]Bruzzone L,Bovolo F,Marchesi S.A Multiscale Change Detection Technique Robust to Registration Noise[J].Pattern Recognition and Machine Intelligence,2007,LNCS 4815:77-86
[18]Celik T.Multiscale Change Detection in Multitemporal Satellite Images[J].IEEE Geoscience and Remote Sensing Letters,2009,6(4):820-824