基于计算机视觉的活立木三维重建方法
|
摘要
中国木材需求量大,产量不足,发展人工林是解决这一问题的有效办法。合理抚育是提高人工林木材产量和质量的重要环节,智能型抚育装备是现代抚育的关键装备,智能型抚育装备包括地面修枝机器、间伐机器和爬树整枝机等,都配装备有计算机视觉系统。未来自动联合采伐装备也将配备计算机视觉系统,在林区自主行走和进行采伐作业。活立木三维重建方法是智能型抚育装备和自动联合采伐装备等林业装备的视觉系统中的关键技术,也是本文的核心内容。
本文对针对智能型林业装备配备的单个相机或者两个相机从不同角度获取的同一活立木二维图像,利用双目立体视觉基本原理,研究活立木三维重建方法,即恢复活立木的三维信息。本文从活立木枝干提取、特征(角点)提取和匹配、射影重建、相机自标定和欧氏三维重建几个方面进行了详细的阐述。通过活立木枝干信息提取去除活立木的细小枝丫,得到活立木较大的枝干,为后续的三维重建服务;通过特征(角点)提取和匹配得到活立木不同角度图像中对应点对;在射影重建部分先求两幅图像之间的基本矩阵然后以第一幅图像拍摄位置的坐标为参考坐标进行射影重建;通过基于基本矩阵的相机自标定方法求解相机的内参数K,从本质矩阵估计相机的运动参数,即计算出旋转矩阵R和平移矢量t,最后根据相机内外参数和左右图象的匹配点坐标估计活立木枝干在欧氏空间下的三维坐标信息。本研究获得以下几点重要结论和创新点:
1.提出了两种活立木图像分割方法,一种是基于粒子群算法的水平集活立木图像分割方法,另一种是基于数学形态学的树木图像分割方法。基于粒子群算法的水平集图像分割方法将C-V模型PDE求解问题视为一个最优化问题,利用粒子群最优化算法进行求解,实验证明该方法对不同背景的图像的两类分割问题很有效。基于数学形态学的树木图像分割方法先对灰度图像用分水岭算法进行分割,再用自动阈值法消除分水岭算法产生的过度分割问题,实验表明该方法的分割效果比Sobel算子等方法有效。这两种方法都能有效解决了复杂背景下活立木的图像分割问题。
2.提出了一种基于SIFT角点检测和NCC匹配原则相结合的角点检测与匹配方法,该方法结合了SIFT角点检测尺度变换不变性的优点和NCC匹配速度快的优点,实验结果表明该方法检测角点的精度比Harris和SUSAN方法的高,运算速度比传统SIFT的快。
3.提出了一种基于粒子群算法的基本矩阵估计算法,该方法解决了8点法在匹配点对较多时如何选择最佳8对匹配点对的问题,得到了在全局最优意义下的基本矩阵估计方法;但该方法也有一定的缺点就是算法的时间复杂度较高,需要进一步研究快速算法。
4.提出了一种基于遗传算法的相机内参数估计方法,该方法将摄像机自标定转化为一个求解代价函数的最小值问题,用遗传算法进行求解。
5.本文采用计算机视觉基本理论对活立木进行三维重建,恢复活立木枝干的三维信息的方法是行之有效的。实验结果表明该方法可以应用到智能型林业装备的视觉系统中,解决其在作业过程中估计立木枝干三维信息的问题。
For China, the demand for the wood is great, while the output of the wood is relatively less. Developping the plantation forest is a potent way of approaching this problem. For plantation forest, the correct cultivation can improve the quality of the wood and the output of the wood for every hektare plantation forest. The intelligent cultivating machines with the machine vision system including intelligent pruning machine on trees, intelligent pruning machine on ground and the selective cleanng machine are the key equipments for the cultivation. For the future, the forest harvesting machine will be equipped with the computer vision system. The method of the 3D reconstruction for the standing trees is an important technology for the computer vision system of the intelligent forestry machine.
The main content of this thesis is to study the method of 3D reconstruction for the standing trees from the images got from different orientations by the camera on the intelligent forestry machine, that is to say to get the 3D information of the standing trees by using the binocular stereo vision. Getting the trunk and branches of the standing tree, extracting the corners and stereo matching, and projective reconstruction are discussed detailly in this thesis; also the camera self-calibration and 3D Euclidean reconstruction are presented in detail. Getting the trunk and branches, and eliminating the little branches and leaves are all done for the following 3D reconstruction. Extracting the corners and stereo matching are done to get the corresponding points on the different images. In the projective part, the fundamental matrix of two images can be computed firstly from the corresponding points of the two images, and then 3D reconstruction is made in the projective space according the cordinates of the position where the camera is to get the first image. In the camera self-calibration and 3D Euclidean reconstruction part, the intrinsic parameters K can be get from the fundamental matrix, and the rotation matrix R and transferation vector t can be got from the the essential matrix E computed from the the intrinsic parameters K and the fundamental matrix F. At last, the 3D information of the standing tree in Euclidean space can be computed from the intrinsic parameters and motion of the camera. Following main conclusions are drawn:
1. Two methods on standing tree image segmentation are proposed. One is level set method in standing tree image segmentation based on particle swarm optimization, the other is tree image segmentation based on mathmatical morphology. For the level set method on standing tree image segmentation based on particle swarm optimization, the image segmentation based on C-V model is considered as an optimal problem that was traditionally considered as a PDE problem before, and then is approached by the particle swarm optimization. The experimental results show that it is effictive for the two class-image segmentation with differnet backgrounds. For the tree image segmentation based on mathmatical morphology, the tree image is segmentated by the watershed algrithm and then segmentated by the auto-threshold method to remove the over-segmentated problem. The experimental results show that the segmentation effct of the mathematical morphology method is better than those of the Sobel and other operation method. So the two methods are all useful for the standing tree image segemtation with tanglesome background.
2. One method on corner detection and matching is proposed. The method combine the scale invariant strongpoint for corner detection of the SIFT and the merit for fastly computing of the NCC matching rule. The experimental results show that the method is more accurate than the Harris and has higher computing velocity than the traditional SIFT.
3. One method on computing the fundamental matrix based on particle swarm optimization is proposed.The method can solve the problem how to select eight groups of the corresponding points in eight-point method. It is an optimal approaching to computing the fundamental matrix in the global space. But it is researched deeply that the fast computing algrithm of the method, because the method with higher time-complexity.
4. One method on estimating the intrinsic parameters based on genetic algrithm is proposed. For the method, the camera self-calibration is considered as an optimal problem to get the minal value of the cost function, and it is solved by the genetic algrithm in this thesis.
5. The method on 3D reconstruction or getting the 3D information of the standing tree by using the principle of computer vision is valid. The experimental results show that the method can be used in the vision system of the intelligent forestry machine to solving the problem of getting the 3D information of the standing trees.
本文对针对智能型林业装备配备的单个相机或者两个相机从不同角度获取的同一活立木二维图像,利用双目立体视觉基本原理,研究活立木三维重建方法,即恢复活立木的三维信息。本文从活立木枝干提取、特征(角点)提取和匹配、射影重建、相机自标定和欧氏三维重建几个方面进行了详细的阐述。通过活立木枝干信息提取去除活立木的细小枝丫,得到活立木较大的枝干,为后续的三维重建服务;通过特征(角点)提取和匹配得到活立木不同角度图像中对应点对;在射影重建部分先求两幅图像之间的基本矩阵然后以第一幅图像拍摄位置的坐标为参考坐标进行射影重建;通过基于基本矩阵的相机自标定方法求解相机的内参数K,从本质矩阵估计相机的运动参数,即计算出旋转矩阵R和平移矢量t,最后根据相机内外参数和左右图象的匹配点坐标估计活立木枝干在欧氏空间下的三维坐标信息。本研究获得以下几点重要结论和创新点:
1.提出了两种活立木图像分割方法,一种是基于粒子群算法的水平集活立木图像分割方法,另一种是基于数学形态学的树木图像分割方法。基于粒子群算法的水平集图像分割方法将C-V模型PDE求解问题视为一个最优化问题,利用粒子群最优化算法进行求解,实验证明该方法对不同背景的图像的两类分割问题很有效。基于数学形态学的树木图像分割方法先对灰度图像用分水岭算法进行分割,再用自动阈值法消除分水岭算法产生的过度分割问题,实验表明该方法的分割效果比Sobel算子等方法有效。这两种方法都能有效解决了复杂背景下活立木的图像分割问题。
2.提出了一种基于SIFT角点检测和NCC匹配原则相结合的角点检测与匹配方法,该方法结合了SIFT角点检测尺度变换不变性的优点和NCC匹配速度快的优点,实验结果表明该方法检测角点的精度比Harris和SUSAN方法的高,运算速度比传统SIFT的快。
3.提出了一种基于粒子群算法的基本矩阵估计算法,该方法解决了8点法在匹配点对较多时如何选择最佳8对匹配点对的问题,得到了在全局最优意义下的基本矩阵估计方法;但该方法也有一定的缺点就是算法的时间复杂度较高,需要进一步研究快速算法。
4.提出了一种基于遗传算法的相机内参数估计方法,该方法将摄像机自标定转化为一个求解代价函数的最小值问题,用遗传算法进行求解。
5.本文采用计算机视觉基本理论对活立木进行三维重建,恢复活立木枝干的三维信息的方法是行之有效的。实验结果表明该方法可以应用到智能型林业装备的视觉系统中,解决其在作业过程中估计立木枝干三维信息的问题。
For China, the demand for the wood is great, while the output of the wood is relatively less. Developping the plantation forest is a potent way of approaching this problem. For plantation forest, the correct cultivation can improve the quality of the wood and the output of the wood for every hektare plantation forest. The intelligent cultivating machines with the machine vision system including intelligent pruning machine on trees, intelligent pruning machine on ground and the selective cleanng machine are the key equipments for the cultivation. For the future, the forest harvesting machine will be equipped with the computer vision system. The method of the 3D reconstruction for the standing trees is an important technology for the computer vision system of the intelligent forestry machine.
The main content of this thesis is to study the method of 3D reconstruction for the standing trees from the images got from different orientations by the camera on the intelligent forestry machine, that is to say to get the 3D information of the standing trees by using the binocular stereo vision. Getting the trunk and branches of the standing tree, extracting the corners and stereo matching, and projective reconstruction are discussed detailly in this thesis; also the camera self-calibration and 3D Euclidean reconstruction are presented in detail. Getting the trunk and branches, and eliminating the little branches and leaves are all done for the following 3D reconstruction. Extracting the corners and stereo matching are done to get the corresponding points on the different images. In the projective part, the fundamental matrix of two images can be computed firstly from the corresponding points of the two images, and then 3D reconstruction is made in the projective space according the cordinates of the position where the camera is to get the first image. In the camera self-calibration and 3D Euclidean reconstruction part, the intrinsic parameters K can be get from the fundamental matrix, and the rotation matrix R and transferation vector t can be got from the the essential matrix E computed from the the intrinsic parameters K and the fundamental matrix F. At last, the 3D information of the standing tree in Euclidean space can be computed from the intrinsic parameters and motion of the camera. Following main conclusions are drawn:
1. Two methods on standing tree image segmentation are proposed. One is level set method in standing tree image segmentation based on particle swarm optimization, the other is tree image segmentation based on mathmatical morphology. For the level set method on standing tree image segmentation based on particle swarm optimization, the image segmentation based on C-V model is considered as an optimal problem that was traditionally considered as a PDE problem before, and then is approached by the particle swarm optimization. The experimental results show that it is effictive for the two class-image segmentation with differnet backgrounds. For the tree image segmentation based on mathmatical morphology, the tree image is segmentated by the watershed algrithm and then segmentated by the auto-threshold method to remove the over-segmentated problem. The experimental results show that the segmentation effct of the mathematical morphology method is better than those of the Sobel and other operation method. So the two methods are all useful for the standing tree image segemtation with tanglesome background.
2. One method on corner detection and matching is proposed. The method combine the scale invariant strongpoint for corner detection of the SIFT and the merit for fastly computing of the NCC matching rule. The experimental results show that the method is more accurate than the Harris and has higher computing velocity than the traditional SIFT.
3. One method on computing the fundamental matrix based on particle swarm optimization is proposed.The method can solve the problem how to select eight groups of the corresponding points in eight-point method. It is an optimal approaching to computing the fundamental matrix in the global space. But it is researched deeply that the fast computing algrithm of the method, because the method with higher time-complexity.
4. One method on estimating the intrinsic parameters based on genetic algrithm is proposed. For the method, the camera self-calibration is considered as an optimal problem to get the minal value of the cost function, and it is solved by the genetic algrithm in this thesis.
5. The method on 3D reconstruction or getting the 3D information of the standing tree by using the principle of computer vision is valid. The experimental results show that the method can be used in the vision system of the intelligent forestry machine to solving the problem of getting the 3D information of the standing trees.
引文
[1]单欣,王耀明,董建萍.基于RANSAC算法的基本矩阵估计的匹配方法[J].上海电机学院学报,2006,9(4):66-69.
[2]陈乐,吕文阁,丁少华.角点检测技术研究进展[J].自动化技术与应用,2005,24(5):1-8.
[3]陈泽志,吴成柯.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):840-845.
[4]邓宝松,高宇,杨冰,等.一种三维准欧氏重建方法[J].小型微型计算机系统,2006,27(4):741-744.
[5]邓志东,牛建军,张竞丹.基于立体视觉的三维建模方法[J].系统仿真学报,2007,19(14):3258-3262.
[6]杜宇慧,姬光荣,尹学明.基于全局性极小化二维反投影误差的射影重建方法[J].中国海洋大学学报,2006,36(2):316-320.
[7]飞思科技产品研发中心.小波分析理论与Matlab7实现[M].北京:电子工业出版社,2005:99-108.
[8]郭海霞,解凯.角点检测技术的研究[J].哈尔滨师范大学自然科学学报,2007,23(2):73-75.
[9]胡凌山,朱齐丹.计算机视觉中基本矩阵的估计方法[J].应用科技,2005,32(10):41-43.
[10]胡明星,袁保宗.投影三维重建中基础矩阵的鲁棒性估计方法[J].北方交通大学学报,2001,25(2):5-9。
[11]阚江明,李文彬.基于数学形态学的树木图像分割方法[J].北京林业大学学报,2006,Vol.28(sup.2):132-136.
[12]阚江明,李文彬,孙仁山.基于计算机视觉的立木枝干直径自动测量方法[J],北京林业大学学报,2007,29(4):5-9.
[13]雷成,吴福朝,胡占义.Kruppa方程与摄像机自标定[J].自动化学报,2001,27(5):621-630.
[14]李海超,张广军.基于分层思想的快速边缘匹配方法及射影重建[J].光电工程,2007,34(7):54-62.
[15]李华,胡占义.基于射影重建的线性摄像机自标定方法[J].软件学报,2002,13(12):2286-2296.
[16]李艳灵,李刚.粒子群优化算法研究进展[J].重庆工学院学报,2007,21(5):79-81.
[17]刘金颂,原思聪,张庆阳,等.双目立体视觉中的摄像机标定技术研究[J].计算机工程与应用,2008,44(6):237-239.
[18]吕海霞,陈红林.改进的SUSAN角点提取算法[J].电光与控制,2008,15(3):45-48.
[19]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,北京,2003.
[20]神会存.基于手持单相机序列图像的三维重建[J].计算机工程与应用,2006,23:43-46.
[21]苏守宝,汪继文,方杰.粒子群优化技术的研究与应用进展[J].计算机技术与发展,2007,17(5):249-254.
[22]孙仁山.立木枝干机器视觉识别技术研究[D].北京:北京林业大学,2006,6.
[23]孙亦南,刘伟军,王越超.由序列图像进行三维测量的新方法[J].光电工程,2005,32(7):59-63.
[24]王国美,陈孝威.SIFT特征匹配算法研究[J].盐城工学院学报(自然科学 版),2007,20(2):1-5.
[25]王建琦,邓雁萍,李介谷.一种改进的角点提取方法[J].上海交通大学学报,2000,34(7):913-916.
[26]王小平,曹立明.遗传算法一理论、应用与软件实现[M]。西安西安交通大学出版社,2002.
[27]王新宇.基于计算机立体视觉的三维重建[D].湖南,中南大学,2004,5.
[28]吴玲达,邓宝松,高宇,等.基于近似相机内参数的精确三维欧氏重建算法[J].系统仿真学报,2007,19(10):2235-2240.
[29]向长波,刘太辉,宋建中.基本矩阵的鲁棒贪心估计算法[J].计算机辅助设计与图形学学报,2007,19(5):651-655.
[30]杨长江,汪威,胡占义.一种基于主动视觉的摄像机内参数自标定方法[J].计算机学报,1998,21(5):428-435.
[31]杨磊,李文彬,阚江明.基于数学形态学的立木树枝信息提取方法,森林工程,2008,24(3):1-5.
[32]张春美,龚志辉,孙雷.改进SIFT特征在图像匹配中的应用[J].计算机工程与应用,2008,44(2):95-97.
[33]张坤华,王敬儒,张启衡.多特征复合的角点提取方法[J].中国图像图形学报,2002,7(4):319-324.
[34]张俊梅,李文彬,王德明,等.人工工业用材林整枝机器人无线电遥测系统的遥测系统的研制[J].北京:林业机械与木工设备,2003,31(10):7-9.
[35]张俊梅.人工林无线电传输特性与林木整枝机控制系统研究[D].北京:北京林业大学,2005,12.
[36]章毓晋.图像分割[M].北京:科学出版社,2001:22-23.
[37]祝海江,吴福朝,胡占义.一种基于4对图像对应点的欧氏重建方法[J].中国图象图形学报,2004,9(12):1421-1430.
[38]Adalsteinsson D,Sethian J A.A fast level set method for propagating interfaces [J].Journal Computing Physics,1995(118):269-277.
[39]Beardsley P,Tort P,Zisserman A.3D model acquisition from extended image sequences[C].Proceedings of the 4~(th) European Conference on Computer Vision,LNCS 1065,Cambridge,1996:683-695.
[40]Chan T,Vese L.Active contours without edges[J].IEEE Transactions on Image,2001,10(2):266-277.
[41]Chang M Y,Wong K H.Model Reconstruction and Pose Acquisition using Extended Lowe's Method[J].IEEE Transactions on Multimedia(S1520-9210),2005,7(2):253-260.
[42]Chum O,Werner T,Matas J.Epipolar geometry estimation via RANSAC benefits from the oriented epipoIar constraint[C].Proceedings of the 17~(th) International Conference on Pattern Recognition,Los AIamitos,and 2004:112-115.
[43]Clerc M,Kennedy J.The particle swarm- explosion,stability,and convergence in a multidimensional complex space[J].IEEE Transactions on Evolutionary Computation,2002,6(1):58-73.
[44]David G Lowe.Object Recognition from Local Scale-Invariant Features[C].7th International Conference on Computer Vision, 1999:1150-1157.
[45] David G Lowe. Distinctive Image Features from Scale-Invariant Interest Points [J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[46] Debevec P E, Taylor C J , Malik J. Modeling and rendering architecture form photographs: A hybrid geometry and image-based approach [C]. Proceedings of Computer Graphics (SIGGERPH' 96 Proceedings), New Orleans, Lousiana, 1996, (30):11-20.
[47] Dhond U R, Aggarwal J K. Structure from Stereo—A Review [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1989, 19: 1489-1510.
[48] Dreschler, Nagel. On the selection of critical points and local curvature extrema of region boundaries for interframe matching [C]. Proceedings of the International Conference on Pattern Recognition, 1982:542-544.
[49] EBERHART R, SHI Yu-hui. Particle swarm optimization: developments, applications and resources [A]. Proceedings of Congress on Evolutionary Computation[C]. Seoul:IEEE Press, 2001. 81-86.
[50] Faugeras O, Luong Q T, Maybank S. Camera Self-Calibration: Theory and Experiments [C]. Proceedings of the 7~(th) European Conference on Computer Vision, Lecture Notes in Computer Science, Springer-Verlag, 1992, (588):321-334.
[51] Faugeras O, Robert L, Laveau S. 3D Reconstruction of Urban Scenes from Sequences of Images [J]. Computer Vision and Image Understanding, 1998, 69(3):292-309.
[52] Gonzalez R C, Woods R E. Digital Image Processing, Second Edition [M]. New Jersey:Prentice Hall, 2002.
[53] GUOQiuyan, AN Ping, ZHANG Zhanyang. Camera Self-Calibration from MultiViews Images [J].Chinese Journal of Electron Device, 2008, 31(0:29-35.
[54] Habed A, Boufama B. Camera Self-calibration: A New Approach for Solving the Modulus Constraint[C]. Proceedings of the 17~(th) International Conference on Pattern Recognition, Cambridge, 2004, (4):116-119.
[55] Han X H, Chen Y W, Nakao Z. Robust Edge Detection by Independent Component Analysis in Noisy Images [J].IEICT Transactions on Information & Systems, 2004, E87-D(9):2204-2211.
[56] Harris C, M Stephens. A Combined Corner and Edge Detector[C]. Proceedings of the Alvey Vision Conference, 1988:189-192.
[57] Hartley R, Gupta R, Chang T. Stereo from uncalibrated cameras[C]. Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, 1992, 761-764.
[58] Hartley R. Euclidean reconstruction from uncalibrated views [C]. Proceedings of 2~(nd) Europe-US Workshop on Invariance, Azores, Portugal, 1993:237-256.
[59] Hartley R. Projective reconstruction and Invariants from multiple images [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1994, 16(10): 1036-1041.
[60] Hartley R. A linear Method for reconstruction from lines and points[C]. Proceedings of International Conference on Computer Vision, 1995:882-887.
[61] Hartley R. Euclidean reconstruction and invariants from multiple images[C]. Proceedings of the International Conference on Pattern Recognition, IEEE Computer Society Press, 1996:339-343.
[62] Hartley R. In defense of the 8-point algorithm [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(2): 133-137.
[63] Hartley R, Zisserman. A Multiple View Geometry in Computer Vision [M]. Cambridge:Cambridge University Press, 2000.
[64] Higashi N, Iba H. Particle Swarm Optimization with Gaussian Mutation[C].Proceedings of the 2003 Congress on Evolutionary Computation. Piscataway, NJ,2003:72-79.
[65] Kan jiangming, Li Hongjun, Li wenbin. Level Set method in standing tree image segmentation based on particle swarm optimization[C]. Preceeding of the 5~(th) International Symposium on Multispectral Image Processing & Pattern Recognition, November 15-17, Wuhan, China, 2007, 6786, 4V1-4v4.
[66] Kan jiangming, Li wenbin, Sun renshan.Automatic Measurement of Trunk and Branch Diameter of Standing Trees Based on Computer Vision[C]. Proceedings of 2~(nd) IEEE Conference on Industrial Electronics and Applications ,3-5 June, 2008: 995-998.
[67] Kitchen, Rosenfeld. Gray-Level Corner Detection [J]. Pattern Recognition Letters,1982, (1):95-102.
[68] Liebowitz D,Zisserman A. Metric Rectification for Perspective Images of Planes [C]. Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, Santa Barbara,1998:482-488.
[69] Lhuillier M, Luong Q T. Robust Dense Matching Using Local and Global Geometric Constraints[C]. Proceedings of the 16~(th) International Conference on Pattern Recognition, Barcelona, Spain, 2000, (1):968-972.
[70] Longuet-Higgins H C. A Computer Algorithm for Reconstructing a Scene from Two Projections [J]. Nature (S0028-0836), 1981, 293(10):133-135.
[71] Luong Q T, Faugeras O. The Fundamental matrix: theory, algorithms, and stability analysis [J]. The International Joural of Computer Vision, 1996, 1(17):43-76.
[72] Mahamud S, Hebert M. Iterative Projective Reconstruction from Multiple Views [C].Proceedings of IEEE Computer Vision & Pattern Recognition, Hilton Head Island, SC,USA, 2000, (2): 430-437.
[73] Mahamud S, Hebert M. Provably convergent iterative methods for projective structure and motion [C]. Proceedings of the IEEE Computer Vision & Pattern Recognition. Kauai,Hawaii, USA, 2001, (1):1018-1025.
[74] Maybank S J, Faugeras 0. A Theory of Self-Calibration of a Moving Camera [J].International Journal of Computer Vision, 1992, 8(2):123-151.
[75] Milan S, Vaclav H, Roger B. Image Processing, Analysis, and Machine Vision [M].Thoms. Brooks/Code: People' s Post and Telecom Press (2002) 8-13.
[76] Mohr R, Veillon F, Quan L. Relative 3D Reconstruction Using Multiple Uncalibrated Tmages[C]. Proceedings of IEEE Computer Vision & Pattern Recognition, 1993: 543-548.
[77] Moons T, Gool L V, Van Diest M, et al. Affine reconstruction from perspective image pairs [C]. Proceedings of the DARPA-ESPRIT Workshop on Applications of Invariants in Computer Vision, Azores, Portugal, 1994: 249-266.
[78] Morency L P, Rahimi A, Darrell T. Fast 3D Model Acquisition from Stereo Images [C].Proceedings of International Conference on 3D Data Processing Visualization and Transmission, Padova, Italy, 2002: 172-176.
[79] Morimoto M, Fujii K. A Portable 3D Scanner Based on Structured Light and Stereo Camera[C]. Proceedings of International Symposium on Communications and Information Technology, Beijing, 2005:569-572.
[80] Noble A. Finding corners [J]. Image and Vision Computing, 1988, 6(2):121-128.
[81] Pajdla T, Hlavac V. Camera calibration and euclidean reconstruction from known observer translations[C]. Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition, Santa Barbara, California, USA,1998:421-426.
[82] Park J S, Han J H. Contour Motion estimation from image sequences using curvature information [J]. Pattern Recognition, 1998, 13(1):1168-1180.
[83] Pierre Soille. Morphological Image analysis: Principles and Applications, Second Edition [M]. Germany: Springer, 2003.
[84] Pilu M. A Direct Method for Stereo Correspondence based on Singular Value Decomposition[C]. Proceedings of Computer Vision & Pattern Recognition Puerto Rico,1997:445-453.
[85] Pollefeys M, Gool L V, Osterlinck A. The modulus constraint: a new constraint for self-calibration[C]. Proceedings of International Conference of Pattern Recognition, Vienna, 1996:349-353.
[86] Pollefeys M, Gool L V. Self-calibration from the absolute conic on the plane at infinity[C]. Proceedings of the 7~(th) International Conference on Computer Analysis of Images and Patterns, 1997:175-182.
[87] Pollefeys M, Koch R, VanGool L. Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters [C]. Proceedings of the 6~(th) International Conference on Computer Vision. Washington, DC, USA: IEEE Computer Society, 1998:90-95.
[88] Pollefeys M. Self-Calibration and Metric 3D Reconstruction from Uncalibrated Image Sequences [D]. PhD. thesis, Leuven, Belgium: K.U. Leuven, 1999.
[89] Pritchett P, Zisserman A. Matching and Reconstruction from Widely Separated Views [J].Lecture Notes in Computer Science, Springer-Verlag, 1998, (1506):78-92.
[90] Smith S M, Brady J M. SUSAN-a new approach to low level image processing [J].International Journal of Computer Vision, 1997, 23(1):45-78.
[91] Sturm P, Triggs B. A Factorization-based Algorithm forMulti-Image Projective Structure and Motion [C]. Proceedings of European Conference on Computer Vision, Cambridge, England, 1996:709-720.
[92] Tomasi C, Kanade T. Detection and tracking of point features[R].Technical Report,CMU-CS-91132, Carnegie-Mellon University, 1991.
[93] Tomasi C, Kanade T. Shape and Motion from Image Streams under Orthography: A Factorization Method [J]. International Journal of Computer Vision, 1992, 9(2):137-154.
[94] Torr P H S, Murray D W. The development and comparison of robust methods for estimating the fundamental matrix [J]. International Journal of Computer Vision,1997, 24(3):271-300.
[95] Triggs B. Auto-calibration and the absolute quadric[C]. Proceedings of the Conference on Computer Vision & Pattern Recognition, Puerto Rico, USA,1997:609-614.
[96] Triggs B, McLauchlan P F, Hartley R I, et al. Bundle adjustment—a modern synthesis [J]. Vision Algorithms: Theory and Practice, 2000: 298-375.
[97] Ueshiba T, Tomita F. A factorization method for projective and Euclidean reconstruction from multiple perspective views via iterative depth estimation[C].Proceedings of the 5" European Conference on Computer Vision, Freiburg, ALLEMAGNE,1998, (1407):296-310.
[98] VESTLUND K, HELLSTROM T. Requirements and system design for a robot performing selective cleaning in young forest stands [J]. Journal of terramechics, 2006,43:505-525.
[99] Wang W, Feng J. Image Segmentation Based on Variational Level Set Method [J]. Computer Engineering and Applications, 2006, 42(18):68-70.
[100] XAVIER A, JOAQUIM S. Overall view regarding fundamental matrix estimation [J]. Image and Vision Computing, 2003, 21:205-220.
[101] Zhang Z. Flexible Camera Calibration by Viewing a Plane from Unknown Orientations [C]. Proceedings of the 7~(th) International Conference on Computer Vision, Kerkyra,Greece, 1999:666-673.
[2]陈乐,吕文阁,丁少华.角点检测技术研究进展[J].自动化技术与应用,2005,24(5):1-8.
[3]陈泽志,吴成柯.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):840-845.
[4]邓宝松,高宇,杨冰,等.一种三维准欧氏重建方法[J].小型微型计算机系统,2006,27(4):741-744.
[5]邓志东,牛建军,张竞丹.基于立体视觉的三维建模方法[J].系统仿真学报,2007,19(14):3258-3262.
[6]杜宇慧,姬光荣,尹学明.基于全局性极小化二维反投影误差的射影重建方法[J].中国海洋大学学报,2006,36(2):316-320.
[7]飞思科技产品研发中心.小波分析理论与Matlab7实现[M].北京:电子工业出版社,2005:99-108.
[8]郭海霞,解凯.角点检测技术的研究[J].哈尔滨师范大学自然科学学报,2007,23(2):73-75.
[9]胡凌山,朱齐丹.计算机视觉中基本矩阵的估计方法[J].应用科技,2005,32(10):41-43.
[10]胡明星,袁保宗.投影三维重建中基础矩阵的鲁棒性估计方法[J].北方交通大学学报,2001,25(2):5-9。
[11]阚江明,李文彬.基于数学形态学的树木图像分割方法[J].北京林业大学学报,2006,Vol.28(sup.2):132-136.
[12]阚江明,李文彬,孙仁山.基于计算机视觉的立木枝干直径自动测量方法[J],北京林业大学学报,2007,29(4):5-9.
[13]雷成,吴福朝,胡占义.Kruppa方程与摄像机自标定[J].自动化学报,2001,27(5):621-630.
[14]李海超,张广军.基于分层思想的快速边缘匹配方法及射影重建[J].光电工程,2007,34(7):54-62.
[15]李华,胡占义.基于射影重建的线性摄像机自标定方法[J].软件学报,2002,13(12):2286-2296.
[16]李艳灵,李刚.粒子群优化算法研究进展[J].重庆工学院学报,2007,21(5):79-81.
[17]刘金颂,原思聪,张庆阳,等.双目立体视觉中的摄像机标定技术研究[J].计算机工程与应用,2008,44(6):237-239.
[18]吕海霞,陈红林.改进的SUSAN角点提取算法[J].电光与控制,2008,15(3):45-48.
[19]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,北京,2003.
[20]神会存.基于手持单相机序列图像的三维重建[J].计算机工程与应用,2006,23:43-46.
[21]苏守宝,汪继文,方杰.粒子群优化技术的研究与应用进展[J].计算机技术与发展,2007,17(5):249-254.
[22]孙仁山.立木枝干机器视觉识别技术研究[D].北京:北京林业大学,2006,6.
[23]孙亦南,刘伟军,王越超.由序列图像进行三维测量的新方法[J].光电工程,2005,32(7):59-63.
[24]王国美,陈孝威.SIFT特征匹配算法研究[J].盐城工学院学报(自然科学 版),2007,20(2):1-5.
[25]王建琦,邓雁萍,李介谷.一种改进的角点提取方法[J].上海交通大学学报,2000,34(7):913-916.
[26]王小平,曹立明.遗传算法一理论、应用与软件实现[M]。西安西安交通大学出版社,2002.
[27]王新宇.基于计算机立体视觉的三维重建[D].湖南,中南大学,2004,5.
[28]吴玲达,邓宝松,高宇,等.基于近似相机内参数的精确三维欧氏重建算法[J].系统仿真学报,2007,19(10):2235-2240.
[29]向长波,刘太辉,宋建中.基本矩阵的鲁棒贪心估计算法[J].计算机辅助设计与图形学学报,2007,19(5):651-655.
[30]杨长江,汪威,胡占义.一种基于主动视觉的摄像机内参数自标定方法[J].计算机学报,1998,21(5):428-435.
[31]杨磊,李文彬,阚江明.基于数学形态学的立木树枝信息提取方法,森林工程,2008,24(3):1-5.
[32]张春美,龚志辉,孙雷.改进SIFT特征在图像匹配中的应用[J].计算机工程与应用,2008,44(2):95-97.
[33]张坤华,王敬儒,张启衡.多特征复合的角点提取方法[J].中国图像图形学报,2002,7(4):319-324.
[34]张俊梅,李文彬,王德明,等.人工工业用材林整枝机器人无线电遥测系统的遥测系统的研制[J].北京:林业机械与木工设备,2003,31(10):7-9.
[35]张俊梅.人工林无线电传输特性与林木整枝机控制系统研究[D].北京:北京林业大学,2005,12.
[36]章毓晋.图像分割[M].北京:科学出版社,2001:22-23.
[37]祝海江,吴福朝,胡占义.一种基于4对图像对应点的欧氏重建方法[J].中国图象图形学报,2004,9(12):1421-1430.
[38]Adalsteinsson D,Sethian J A.A fast level set method for propagating interfaces [J].Journal Computing Physics,1995(118):269-277.
[39]Beardsley P,Tort P,Zisserman A.3D model acquisition from extended image sequences[C].Proceedings of the 4~(th) European Conference on Computer Vision,LNCS 1065,Cambridge,1996:683-695.
[40]Chan T,Vese L.Active contours without edges[J].IEEE Transactions on Image,2001,10(2):266-277.
[41]Chang M Y,Wong K H.Model Reconstruction and Pose Acquisition using Extended Lowe's Method[J].IEEE Transactions on Multimedia(S1520-9210),2005,7(2):253-260.
[42]Chum O,Werner T,Matas J.Epipolar geometry estimation via RANSAC benefits from the oriented epipoIar constraint[C].Proceedings of the 17~(th) International Conference on Pattern Recognition,Los AIamitos,and 2004:112-115.
[43]Clerc M,Kennedy J.The particle swarm- explosion,stability,and convergence in a multidimensional complex space[J].IEEE Transactions on Evolutionary Computation,2002,6(1):58-73.
[44]David G Lowe.Object Recognition from Local Scale-Invariant Features[C].7th International Conference on Computer Vision, 1999:1150-1157.
[45] David G Lowe. Distinctive Image Features from Scale-Invariant Interest Points [J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[46] Debevec P E, Taylor C J , Malik J. Modeling and rendering architecture form photographs: A hybrid geometry and image-based approach [C]. Proceedings of Computer Graphics (SIGGERPH' 96 Proceedings), New Orleans, Lousiana, 1996, (30):11-20.
[47] Dhond U R, Aggarwal J K. Structure from Stereo—A Review [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1989, 19: 1489-1510.
[48] Dreschler, Nagel. On the selection of critical points and local curvature extrema of region boundaries for interframe matching [C]. Proceedings of the International Conference on Pattern Recognition, 1982:542-544.
[49] EBERHART R, SHI Yu-hui. Particle swarm optimization: developments, applications and resources [A]. Proceedings of Congress on Evolutionary Computation[C]. Seoul:IEEE Press, 2001. 81-86.
[50] Faugeras O, Luong Q T, Maybank S. Camera Self-Calibration: Theory and Experiments [C]. Proceedings of the 7~(th) European Conference on Computer Vision, Lecture Notes in Computer Science, Springer-Verlag, 1992, (588):321-334.
[51] Faugeras O, Robert L, Laveau S. 3D Reconstruction of Urban Scenes from Sequences of Images [J]. Computer Vision and Image Understanding, 1998, 69(3):292-309.
[52] Gonzalez R C, Woods R E. Digital Image Processing, Second Edition [M]. New Jersey:Prentice Hall, 2002.
[53] GUOQiuyan, AN Ping, ZHANG Zhanyang. Camera Self-Calibration from MultiViews Images [J].Chinese Journal of Electron Device, 2008, 31(0:29-35.
[54] Habed A, Boufama B. Camera Self-calibration: A New Approach for Solving the Modulus Constraint[C]. Proceedings of the 17~(th) International Conference on Pattern Recognition, Cambridge, 2004, (4):116-119.
[55] Han X H, Chen Y W, Nakao Z. Robust Edge Detection by Independent Component Analysis in Noisy Images [J].IEICT Transactions on Information & Systems, 2004, E87-D(9):2204-2211.
[56] Harris C, M Stephens. A Combined Corner and Edge Detector[C]. Proceedings of the Alvey Vision Conference, 1988:189-192.
[57] Hartley R, Gupta R, Chang T. Stereo from uncalibrated cameras[C]. Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, 1992, 761-764.
[58] Hartley R. Euclidean reconstruction from uncalibrated views [C]. Proceedings of 2~(nd) Europe-US Workshop on Invariance, Azores, Portugal, 1993:237-256.
[59] Hartley R. Projective reconstruction and Invariants from multiple images [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1994, 16(10): 1036-1041.
[60] Hartley R. A linear Method for reconstruction from lines and points[C]. Proceedings of International Conference on Computer Vision, 1995:882-887.
[61] Hartley R. Euclidean reconstruction and invariants from multiple images[C]. Proceedings of the International Conference on Pattern Recognition, IEEE Computer Society Press, 1996:339-343.
[62] Hartley R. In defense of the 8-point algorithm [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(2): 133-137.
[63] Hartley R, Zisserman. A Multiple View Geometry in Computer Vision [M]. Cambridge:Cambridge University Press, 2000.
[64] Higashi N, Iba H. Particle Swarm Optimization with Gaussian Mutation[C].Proceedings of the 2003 Congress on Evolutionary Computation. Piscataway, NJ,2003:72-79.
[65] Kan jiangming, Li Hongjun, Li wenbin. Level Set method in standing tree image segmentation based on particle swarm optimization[C]. Preceeding of the 5~(th) International Symposium on Multispectral Image Processing & Pattern Recognition, November 15-17, Wuhan, China, 2007, 6786, 4V1-4v4.
[66] Kan jiangming, Li wenbin, Sun renshan.Automatic Measurement of Trunk and Branch Diameter of Standing Trees Based on Computer Vision[C]. Proceedings of 2~(nd) IEEE Conference on Industrial Electronics and Applications ,3-5 June, 2008: 995-998.
[67] Kitchen, Rosenfeld. Gray-Level Corner Detection [J]. Pattern Recognition Letters,1982, (1):95-102.
[68] Liebowitz D,Zisserman A. Metric Rectification for Perspective Images of Planes [C]. Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, Santa Barbara,1998:482-488.
[69] Lhuillier M, Luong Q T. Robust Dense Matching Using Local and Global Geometric Constraints[C]. Proceedings of the 16~(th) International Conference on Pattern Recognition, Barcelona, Spain, 2000, (1):968-972.
[70] Longuet-Higgins H C. A Computer Algorithm for Reconstructing a Scene from Two Projections [J]. Nature (S0028-0836), 1981, 293(10):133-135.
[71] Luong Q T, Faugeras O. The Fundamental matrix: theory, algorithms, and stability analysis [J]. The International Joural of Computer Vision, 1996, 1(17):43-76.
[72] Mahamud S, Hebert M. Iterative Projective Reconstruction from Multiple Views [C].Proceedings of IEEE Computer Vision & Pattern Recognition, Hilton Head Island, SC,USA, 2000, (2): 430-437.
[73] Mahamud S, Hebert M. Provably convergent iterative methods for projective structure and motion [C]. Proceedings of the IEEE Computer Vision & Pattern Recognition. Kauai,Hawaii, USA, 2001, (1):1018-1025.
[74] Maybank S J, Faugeras 0. A Theory of Self-Calibration of a Moving Camera [J].International Journal of Computer Vision, 1992, 8(2):123-151.
[75] Milan S, Vaclav H, Roger B. Image Processing, Analysis, and Machine Vision [M].Thoms. Brooks/Code: People' s Post and Telecom Press (2002) 8-13.
[76] Mohr R, Veillon F, Quan L. Relative 3D Reconstruction Using Multiple Uncalibrated Tmages[C]. Proceedings of IEEE Computer Vision & Pattern Recognition, 1993: 543-548.
[77] Moons T, Gool L V, Van Diest M, et al. Affine reconstruction from perspective image pairs [C]. Proceedings of the DARPA-ESPRIT Workshop on Applications of Invariants in Computer Vision, Azores, Portugal, 1994: 249-266.
[78] Morency L P, Rahimi A, Darrell T. Fast 3D Model Acquisition from Stereo Images [C].Proceedings of International Conference on 3D Data Processing Visualization and Transmission, Padova, Italy, 2002: 172-176.
[79] Morimoto M, Fujii K. A Portable 3D Scanner Based on Structured Light and Stereo Camera[C]. Proceedings of International Symposium on Communications and Information Technology, Beijing, 2005:569-572.
[80] Noble A. Finding corners [J]. Image and Vision Computing, 1988, 6(2):121-128.
[81] Pajdla T, Hlavac V. Camera calibration and euclidean reconstruction from known observer translations[C]. Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition, Santa Barbara, California, USA,1998:421-426.
[82] Park J S, Han J H. Contour Motion estimation from image sequences using curvature information [J]. Pattern Recognition, 1998, 13(1):1168-1180.
[83] Pierre Soille. Morphological Image analysis: Principles and Applications, Second Edition [M]. Germany: Springer, 2003.
[84] Pilu M. A Direct Method for Stereo Correspondence based on Singular Value Decomposition[C]. Proceedings of Computer Vision & Pattern Recognition Puerto Rico,1997:445-453.
[85] Pollefeys M, Gool L V, Osterlinck A. The modulus constraint: a new constraint for self-calibration[C]. Proceedings of International Conference of Pattern Recognition, Vienna, 1996:349-353.
[86] Pollefeys M, Gool L V. Self-calibration from the absolute conic on the plane at infinity[C]. Proceedings of the 7~(th) International Conference on Computer Analysis of Images and Patterns, 1997:175-182.
[87] Pollefeys M, Koch R, VanGool L. Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters [C]. Proceedings of the 6~(th) International Conference on Computer Vision. Washington, DC, USA: IEEE Computer Society, 1998:90-95.
[88] Pollefeys M. Self-Calibration and Metric 3D Reconstruction from Uncalibrated Image Sequences [D]. PhD. thesis, Leuven, Belgium: K.U. Leuven, 1999.
[89] Pritchett P, Zisserman A. Matching and Reconstruction from Widely Separated Views [J].Lecture Notes in Computer Science, Springer-Verlag, 1998, (1506):78-92.
[90] Smith S M, Brady J M. SUSAN-a new approach to low level image processing [J].International Journal of Computer Vision, 1997, 23(1):45-78.
[91] Sturm P, Triggs B. A Factorization-based Algorithm forMulti-Image Projective Structure and Motion [C]. Proceedings of European Conference on Computer Vision, Cambridge, England, 1996:709-720.
[92] Tomasi C, Kanade T. Detection and tracking of point features[R].Technical Report,CMU-CS-91132, Carnegie-Mellon University, 1991.
[93] Tomasi C, Kanade T. Shape and Motion from Image Streams under Orthography: A Factorization Method [J]. International Journal of Computer Vision, 1992, 9(2):137-154.
[94] Torr P H S, Murray D W. The development and comparison of robust methods for estimating the fundamental matrix [J]. International Journal of Computer Vision,1997, 24(3):271-300.
[95] Triggs B. Auto-calibration and the absolute quadric[C]. Proceedings of the Conference on Computer Vision & Pattern Recognition, Puerto Rico, USA,1997:609-614.
[96] Triggs B, McLauchlan P F, Hartley R I, et al. Bundle adjustment—a modern synthesis [J]. Vision Algorithms: Theory and Practice, 2000: 298-375.
[97] Ueshiba T, Tomita F. A factorization method for projective and Euclidean reconstruction from multiple perspective views via iterative depth estimation[C].Proceedings of the 5" European Conference on Computer Vision, Freiburg, ALLEMAGNE,1998, (1407):296-310.
[98] VESTLUND K, HELLSTROM T. Requirements and system design for a robot performing selective cleaning in young forest stands [J]. Journal of terramechics, 2006,43:505-525.
[99] Wang W, Feng J. Image Segmentation Based on Variational Level Set Method [J]. Computer Engineering and Applications, 2006, 42(18):68-70.
[100] XAVIER A, JOAQUIM S. Overall view regarding fundamental matrix estimation [J]. Image and Vision Computing, 2003, 21:205-220.
[101] Zhang Z. Flexible Camera Calibration by Viewing a Plane from Unknown Orientations [C]. Proceedings of the 7~(th) International Conference on Computer Vision, Kerkyra,Greece, 1999:666-673.