基于立体视觉的岩石表面三维评估技术研究
|
摘要
星球探测中最重要的任务之一就是利用漫游车对行星表面岩石与土壤进行采样与分析。对于岩石等坚硬的物质,通常是利用车载机械臂对其进行研磨,去除表面覆盖层,并利用相关仪器进行实地采样与分析。完成这一任务的关键技术就是利用双目立体视觉对岩石表面进行三维重建,并利用相关算法自动找出近似平整的表平面,获取定位点三维坐标与定位法向量,从而引导车载机械臂准确定位于岩石表面并进行研磨工作。本文通过双目立体视觉采集岩石图像,利用Matlab标定工具箱对摄像机进行畸变补偿,使摄像机成像模型趋于理想的针孔模型,并与传统的DLT标定算法和Tsai两步法进行了比较。为了提高匹配速度,还对岩石图像进行了校正。考虑到校正后的图像在投影变换后会出现图像拉伸不均匀现象,从而影响匹配的精度,为此,本文提出一种基于极线校正逆变换的立体匹配方法,它在校正后的图像上进行开窗搜索,然后对窗内的图像坐标进行反校正,提取校正前的像素灰度值对基准点与匹配点进行灰度相关运算,有效的降低了由插值点造成的误匹配率。此外,文中又采用双向匹配方法,以初次匹配得到的匹配点为新的基准点,在参考图像上搜索新的匹配点,若新匹配点与原基准点是同一点,则认为匹配正确。为了进一步提高匹配速度,本文根据空间点在两幅图像上投影位置的不同,采取了一种快速的匹配搜索策略。在获取场景的空间坐标之后,首先,通过距离聚类将岩石数据与地面数据、背景数据分离。然后,对岩石的空间点云数据进行Delaunay三角剖分,计算每个三角片的法向量。最后,以法向量之间的夹角为基准,对三角片法向量之间的夹角进行聚类分析,达到评估岩石平整表面的目的。
One of the most important mission in planetary exploration is to sample and to analyze rock and soil from other planets surface by using rovers. The grinding work for hard material such as rock is usually be done by vehicle manipulator so as to remove the external covering layer, and use relevant equipment to sample and to analyze. The key technology in the mission is to reconstruct the 3-D information of rock surface based on binocular vision and to search for the approximate flat surface of rock automatically by use of relevant algorithms so that the 3-D locating point coordinate and locating normal vector could be obtained in order to guide vehicle manipulator to locate the rock surface accurately and to grind it. This paper sample the image of rock through binocular stereo vision, and use Matlab calibration toolbox to compensate for the distortion of camera so that the camera projection model could approach to ideal pinhole model.Besides that,the paper also compare the method with the traditional DLT calibration method and the Tsai two step calibration method. In order to improve matching speed, the image rectification is also necessary to be done. The phenomenon of inhomogeneous stretching will appear who could influence matching accuracy in rectified image after projection transformation. Therefore, the paper adopt stereo matching method based on the inverse transformation for epipolar line rectification. The method open the search window in the rectified image, and then inverse rectify the image coordinate for the points within the window so that the gray value of pixel in un-rectified image is extracted and the gray correlation operation is computed between reference point and matching point, this method decreased mismatching rate effectively caused by interpolated point. In addition, the paper adopted two-way matching, which take the first matching point as a new reference point and search for the new matching point in reference image, if the new matching point and the original reference point are same point then we consider that the matching is correct at this time. This paper also adopt a fast searching strategy of matching for the sake of improving matching speed according to principle that the projection points of space point located on different position. Firstly, the ground data and the background data are separated by clustering distance after obtaining space coordinate of scene. Then, the cloud point data of rock are triangulated by the method of Delaunay triangulation, and calculated normal vector of each triangular plane. Finally, the angle between normal vectors are clustered and analyzed so as to evaluate the flat surface of rock.
One of the most important mission in planetary exploration is to sample and to analyze rock and soil from other planets surface by using rovers. The grinding work for hard material such as rock is usually be done by vehicle manipulator so as to remove the external covering layer, and use relevant equipment to sample and to analyze. The key technology in the mission is to reconstruct the 3-D information of rock surface based on binocular vision and to search for the approximate flat surface of rock automatically by use of relevant algorithms so that the 3-D locating point coordinate and locating normal vector could be obtained in order to guide vehicle manipulator to locate the rock surface accurately and to grind it. This paper sample the image of rock through binocular stereo vision, and use Matlab calibration toolbox to compensate for the distortion of camera so that the camera projection model could approach to ideal pinhole model.Besides that,the paper also compare the method with the traditional DLT calibration method and the Tsai two step calibration method. In order to improve matching speed, the image rectification is also necessary to be done. The phenomenon of inhomogeneous stretching will appear who could influence matching accuracy in rectified image after projection transformation. Therefore, the paper adopt stereo matching method based on the inverse transformation for epipolar line rectification. The method open the search window in the rectified image, and then inverse rectify the image coordinate for the points within the window so that the gray value of pixel in un-rectified image is extracted and the gray correlation operation is computed between reference point and matching point, this method decreased mismatching rate effectively caused by interpolated point. In addition, the paper adopted two-way matching, which take the first matching point as a new reference point and search for the new matching point in reference image, if the new matching point and the original reference point are same point then we consider that the matching is correct at this time. This paper also adopt a fast searching strategy of matching for the sake of improving matching speed according to principle that the projection points of space point located on different position. Firstly, the ground data and the background data are separated by clustering distance after obtaining space coordinate of scene. Then, the cloud point data of rock are triangulated by the method of Delaunay triangulation, and calculated normal vector of each triangular plane. Finally, the angle between normal vectors are clustered and analyzed so as to evaluate the flat surface of rock.
引文
[1] S Hayati,R Volpe,P Backes,et al.The Rocky 7 rover a Mars sciencecraft prototype. IEEE Int.Conf.on Robotics and Automation.1997,(3):2458-2464
[2]庞之浩.美国火星漫游车及其探测历程和成果[A].中国宇航学会深空探测技术专业委员会第二届学术会议论文集[C].2005:297-303
[3]胡群芳,陈永杰.中国掀起月球车研制热[J].中国航天,2004,(5):8-9
[4] http://baike.baidu.com/view/3466514.htm?fr=ala0_1
[5]马颂德,张正友.计算机视觉—计算理论与算法基础[M].北京:科学出版社,2003:52-70
[6]黄桂平,李广云.单目视觉测量技术研究[J].计量学报.2004,25(4):314-317
[7] Alfredo Liverani,Francesco Leali and Marcello Pellicciari.Real-time 3D features reconstruction through monocular vision.International Journal on Interactive Design and Manufacturing.2010,2,(4):103-112
[8]隋婧.双目立体视觉技术的实现及其进展[J].电子技术应用.2004,30(10):4-6
[9]于勇,张晖,林茂松.基于双目立体视觉三维重建系统的研究与设计[J].计算机技术与发展.2009,19(6):127-130
[10]王俊龙.多CCD视觉检测技术的研究[J].传感器与微系统.2010,29(1):114-120
[11]邱茂林,马颂德,李毅.计算机视觉中摄像机定标综述[J].自动化学报.2000,26(1):43-53
[12] Abdel-Aziz Y I,Karara HM.Direct linear transformation into object space coordinates in close-Range photogrammetry.In:Proc Symposium on Close-Range Photogrammetry,1971:1-18
[13]高立志,方勇,林志航.立体视觉测量中摄像机标定的新技术[J].电子学报.1999,27(2):1-9
[14]张艳珍.一种新的摄像机线性标定方法[J].中国图象图形学报A辑.2001,6(8):727-730
[15]毛剑飞,邹细勇,诸静.改进的平面模板两步法标定摄像机[J].中国图象图形学报A辑.2004,9(7):846-850
[16]周船,谈大龙,朱枫.基于模型的位姿估计中优化方法研究[A].仪器仪表学报2004增刊(上册)[C].2004:122-124
[17]王建文,陶瑞.快速有效的摄像机标定方法[J].计算机工程与设计.2010,31(11):2614-2619
[18]赵文彬,张艳宁.角点检测技术综述[J].计算机应用研究.2006,23(10):17-19
[19]李玲玲.图像配准中角点检测算法的研究与比较[J].郑州航空工业管理学院学报.2006,25(2):190-191
[20] Roger Y.Tsai.A Versatile Camera Calibration Technique for High-Accuracy 3D Machine Vision Metrology Using Off-the-Shelf TV Cameras and Lenses.IEEE JOURNAL OF ROBOTICS AND AUTOMATION,1987,3(4):323-344
[21] Roger Y.Tsai.An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision.Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,Miami Beach,FL,USA,1986:364-374
[22]孙玉青,冀小平. Matlab标定工具箱在摄像机定标中的应用[J].太原科技.2010,(3):99-100
[23] http://www.vision.caltech.edu/bouguetj/calib_doc
[24]郝晓红,张阳.智能优化算法在无功优化中的应用综述[J].工业仪表与自动化装置.2010(2):12-15
[25]刘志平,石林英.最小二乘法原理及其MATLAB实现[J].中国西部科技.2008,7,(17):33-34
[26] O D Faugeras.Three-Dimensional Computer Vision:A Geometric Viewpoint [M]. The MIT Press, Cambridge, MA, 1993:165-240
[27] Hartley R.Theory and practice of projective rectification[J].International Journal of Computer Vision.1999,35(2):115-127
[28]胡东红,汪浩,艾君等.两种图像校正算法在实际应用中的比较[J].计算机工程与应用.2009,45(13):191-193
[29] Charles Loop.Computing rectifying homographies for stereo vision[A].1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99), vol.1[C].1999:3-9
[30] A Fusiello,E Trucco,A Verri.A compact algorithm for rectification of stereo pairs[J].Machine Vision and Applications,2000,(12):1-22
[31]陈泽志.一种高精度估计的基础矩阵的线性算法[J].软件学报.2002,13(4): 840-844
[32]陈卫东,王锋,刘睿.一种基础矩阵的线性估计方法[J].河南科技.2009,(13):52-53
[33]张钧,刘小茂,柳健.一种新的三维表面重建方法——基础矩阵法的研究[J].红外与激光工程,2001,30(1):8-9
[34]颜洁.基于图像匹配的定位分析[J].无线电通信技术,2010,36(3):17-19
[35] Candocia, F.A similarity measure for stereo feature matching[J].IEEE Transactions on Image Processing,1997,6(10):1460-1464
[36]徐奕,周军,周源华.立体视觉匹配技术[J].计算机工程与应用,2003,39(15):1-5
[37]汪洋.图像匹配方法综述[J].电脑与电信,2009,(5):84-86
[38] Roy S,Meunier J,Cox I.Cylindrical rectification to minimize epipolar distortion [C].In:Proc.IEEE Conference on Computer Vision and Pattern Recognition. 1997:393-399
[39] Loop C,Zhang Z.Computing Rectifying Homographies for Stereo Vision[C].In: Baldwin T, Sipple RS, eds. Proceeding of the International Conference on Computer Vision and Pattern Recognition. Los Alamitos:IEEE Press, 1999:125-131
[40]周亦鹏.基于双目视觉的深度图立体匹配算法研究改进[J].计算机测量与控制,2008,16(9):1332-1334
[41]袁红照,李勇,何方.三维点云数据获取技术[J].安阳师范学院学报,2009,(2):75-79
[42]张永春,达飞鹏,宋文忠.三维散乱点集的曲面三角剖分[J].中国图形图像学报A辑,2003,8(12):1379-1387
[43]周佳文,薛之昕,万施.三角剖分综述[J].计算机与现代化,2010,(7):75-78
[44]何国林,王林旭,崔雪峰.OpenGL纹理映射技术在三维图形逼真绘制中的应用研究[A].国第20届计算机技术与应用(CACIS)学术会议论文集[C], 2009:627-630
[45]王新宇.基于计算机立体视觉的三维重建[D].中南大学,2004,5:43-44
[46]陈寿文,李明东.遗传聚类算法及其改进[J].宿州学院学报,2008,23(4):101-103
[47]张玉芳,毛嘉莉,熊忠阳.一种改进的K-means算法[J].计算机应用,2003,23(8):31-33
[48]荆丰伟,刘冀伟,王淑盛.改进的K-均值算法在岩相识别中的应用[J].微计算机信息,2004,(7):41-42
[49] Pedersen, L. Science target assessment for Mars rover instrument deployment [C]. IEEE/RSJ International Conference on Intelligent Robots and System, vol.1, 2002:817-822
[50]官云兰等.一种稳健的点云数据平面拟合方法[J].同济大学学报,2008,36(7):981-984
[51]白高峰.一种基于平面拟合的图像恢复方法[J].计算机应用,2004,24(11):126-127
[52]同济大学应用数学系.高等数学[M].北京:高等教育出版社,2002,第五版,上册:328-329
[2]庞之浩.美国火星漫游车及其探测历程和成果[A].中国宇航学会深空探测技术专业委员会第二届学术会议论文集[C].2005:297-303
[3]胡群芳,陈永杰.中国掀起月球车研制热[J].中国航天,2004,(5):8-9
[4] http://baike.baidu.com/view/3466514.htm?fr=ala0_1
[5]马颂德,张正友.计算机视觉—计算理论与算法基础[M].北京:科学出版社,2003:52-70
[6]黄桂平,李广云.单目视觉测量技术研究[J].计量学报.2004,25(4):314-317
[7] Alfredo Liverani,Francesco Leali and Marcello Pellicciari.Real-time 3D features reconstruction through monocular vision.International Journal on Interactive Design and Manufacturing.2010,2,(4):103-112
[8]隋婧.双目立体视觉技术的实现及其进展[J].电子技术应用.2004,30(10):4-6
[9]于勇,张晖,林茂松.基于双目立体视觉三维重建系统的研究与设计[J].计算机技术与发展.2009,19(6):127-130
[10]王俊龙.多CCD视觉检测技术的研究[J].传感器与微系统.2010,29(1):114-120
[11]邱茂林,马颂德,李毅.计算机视觉中摄像机定标综述[J].自动化学报.2000,26(1):43-53
[12] Abdel-Aziz Y I,Karara HM.Direct linear transformation into object space coordinates in close-Range photogrammetry.In:Proc Symposium on Close-Range Photogrammetry,1971:1-18
[13]高立志,方勇,林志航.立体视觉测量中摄像机标定的新技术[J].电子学报.1999,27(2):1-9
[14]张艳珍.一种新的摄像机线性标定方法[J].中国图象图形学报A辑.2001,6(8):727-730
[15]毛剑飞,邹细勇,诸静.改进的平面模板两步法标定摄像机[J].中国图象图形学报A辑.2004,9(7):846-850
[16]周船,谈大龙,朱枫.基于模型的位姿估计中优化方法研究[A].仪器仪表学报2004增刊(上册)[C].2004:122-124
[17]王建文,陶瑞.快速有效的摄像机标定方法[J].计算机工程与设计.2010,31(11):2614-2619
[18]赵文彬,张艳宁.角点检测技术综述[J].计算机应用研究.2006,23(10):17-19
[19]李玲玲.图像配准中角点检测算法的研究与比较[J].郑州航空工业管理学院学报.2006,25(2):190-191
[20] Roger Y.Tsai.A Versatile Camera Calibration Technique for High-Accuracy 3D Machine Vision Metrology Using Off-the-Shelf TV Cameras and Lenses.IEEE JOURNAL OF ROBOTICS AND AUTOMATION,1987,3(4):323-344
[21] Roger Y.Tsai.An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision.Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,Miami Beach,FL,USA,1986:364-374
[22]孙玉青,冀小平. Matlab标定工具箱在摄像机定标中的应用[J].太原科技.2010,(3):99-100
[23] http://www.vision.caltech.edu/bouguetj/calib_doc
[24]郝晓红,张阳.智能优化算法在无功优化中的应用综述[J].工业仪表与自动化装置.2010(2):12-15
[25]刘志平,石林英.最小二乘法原理及其MATLAB实现[J].中国西部科技.2008,7,(17):33-34
[26] O D Faugeras.Three-Dimensional Computer Vision:A Geometric Viewpoint [M]. The MIT Press, Cambridge, MA, 1993:165-240
[27] Hartley R.Theory and practice of projective rectification[J].International Journal of Computer Vision.1999,35(2):115-127
[28]胡东红,汪浩,艾君等.两种图像校正算法在实际应用中的比较[J].计算机工程与应用.2009,45(13):191-193
[29] Charles Loop.Computing rectifying homographies for stereo vision[A].1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99), vol.1[C].1999:3-9
[30] A Fusiello,E Trucco,A Verri.A compact algorithm for rectification of stereo pairs[J].Machine Vision and Applications,2000,(12):1-22
[31]陈泽志.一种高精度估计的基础矩阵的线性算法[J].软件学报.2002,13(4): 840-844
[32]陈卫东,王锋,刘睿.一种基础矩阵的线性估计方法[J].河南科技.2009,(13):52-53
[33]张钧,刘小茂,柳健.一种新的三维表面重建方法——基础矩阵法的研究[J].红外与激光工程,2001,30(1):8-9
[34]颜洁.基于图像匹配的定位分析[J].无线电通信技术,2010,36(3):17-19
[35] Candocia, F.A similarity measure for stereo feature matching[J].IEEE Transactions on Image Processing,1997,6(10):1460-1464
[36]徐奕,周军,周源华.立体视觉匹配技术[J].计算机工程与应用,2003,39(15):1-5
[37]汪洋.图像匹配方法综述[J].电脑与电信,2009,(5):84-86
[38] Roy S,Meunier J,Cox I.Cylindrical rectification to minimize epipolar distortion [C].In:Proc.IEEE Conference on Computer Vision and Pattern Recognition. 1997:393-399
[39] Loop C,Zhang Z.Computing Rectifying Homographies for Stereo Vision[C].In: Baldwin T, Sipple RS, eds. Proceeding of the International Conference on Computer Vision and Pattern Recognition. Los Alamitos:IEEE Press, 1999:125-131
[40]周亦鹏.基于双目视觉的深度图立体匹配算法研究改进[J].计算机测量与控制,2008,16(9):1332-1334
[41]袁红照,李勇,何方.三维点云数据获取技术[J].安阳师范学院学报,2009,(2):75-79
[42]张永春,达飞鹏,宋文忠.三维散乱点集的曲面三角剖分[J].中国图形图像学报A辑,2003,8(12):1379-1387
[43]周佳文,薛之昕,万施.三角剖分综述[J].计算机与现代化,2010,(7):75-78
[44]何国林,王林旭,崔雪峰.OpenGL纹理映射技术在三维图形逼真绘制中的应用研究[A].国第20届计算机技术与应用(CACIS)学术会议论文集[C], 2009:627-630
[45]王新宇.基于计算机立体视觉的三维重建[D].中南大学,2004,5:43-44
[46]陈寿文,李明东.遗传聚类算法及其改进[J].宿州学院学报,2008,23(4):101-103
[47]张玉芳,毛嘉莉,熊忠阳.一种改进的K-means算法[J].计算机应用,2003,23(8):31-33
[48]荆丰伟,刘冀伟,王淑盛.改进的K-均值算法在岩相识别中的应用[J].微计算机信息,2004,(7):41-42
[49] Pedersen, L. Science target assessment for Mars rover instrument deployment [C]. IEEE/RSJ International Conference on Intelligent Robots and System, vol.1, 2002:817-822
[50]官云兰等.一种稳健的点云数据平面拟合方法[J].同济大学学报,2008,36(7):981-984
[51]白高峰.一种基于平面拟合的图像恢复方法[J].计算机应用,2004,24(11):126-127
[52]同济大学应用数学系.高等数学[M].北京:高等教育出版社,2002,第五版,上册:328-329