一种山体图像边缘快速立体匹配方法

魏振忠; 郗曼; 张广军

doi:10.3724/SP.J.1146.2008.01451

一种山体图像边缘快速立体匹配方法

doi: 10.3724/SP.J.1146.2008.01451

基金项目:

国家自然科学基金(50875014)，教育部新世纪优秀人才支持计划(NCET-07-0043)和北京市自然科学基金(3092014)资助课题

计量
- 文章访问数: 3964
- HTML全文浏览量: 79
- PDF下载量: 1101
- 被引次数: 0
出版历程
- 收稿日期: 2008-11-07
- 修回日期: 2009-03-27
- 刊出日期: 2009-06-19

A Fast Stereo Edge-Matching Algorithm Based on Mountain Images

摘要

摘要: 该文提出了一种新的针对山体图像边缘的立体匹配算法。为了保证匹配的准确性，首先引入极线方向上的视差梯度约束，然后在考察唯一性的基础上，通过搜索并考察边缘端点周围的角点信息来引导边缘的匹配，并且限定边缘端点的角点搜索范围，最终匹配结果保证了两幅图像中的匹配对是一对一的唯一对应。实验结果表明，不同约束方法的融合在很大程度上提高了匹配速度和匹配精度。
- 图像处理;边缘立体匹配;极线;视差梯度;角点
Abstract: A new fast stereo edge-matching algorithm based on mountain images is presented. In order to ensure the accuracy of the match. Firstly the disparity gradient restriction across the direction of epipolar lines is used, and then on the basis of exclusionism searched the corner information close to edge point to guide the matching with restricted corners-searched range. The final match results ensure that the matching pairs in two images are one-to-one correspondences. The algorithm results show that the amalgamation of different restrictions improved the matching speed and precision.

HTML全文

参考文献(1)

徐奕, 周军, 周源华. 基于稀疏-密集匹配算法的视差度量[J].红外与激光工程, 2003, 32(6): 630-634.Xu Yi, Zhou Jun, and Zhou Yuan-hua. Measurement ofdisparity based on sparse-to-dense matching approach[J].Infrared and Laser Engineering, 2003, 32(6): 630-634.[2]张广军. 机器视觉[M]. 第一版, 北京: 科学出版社, 2005, 第2章.Zhang Guang-jun. Machine Vision. Edition 1, Beijing: SciencePress, 2005, Chapter 2.[3]苏胤杰. 基于蚁群优化算法的立体匹配[J]. 微计算机信息,2008, 24(8-3): 227-228, 249.Su Yin-jie. Stereo matching based on ant colony optimizationalgorithm[J]. Microcomputer Information, 2008, 24(8-3):227-228, 249.[4]沈峰亭. 边缘检测在视觉图像中的应用分析[J]. 微计算机信息, 2008, 24(3-3): 304-305.Shen Feng-ting. Analysis of the application of several edgedetection operators in an image[J]. MicrocomputerInformation, 2008, 24(3-3): 304-305.[5]郭龙源, 夏永泉, 杨静宇. 基于视差梯度的快速区域匹配方法[J]. 计算机科学, 2007, 34(4): 239-240, 257.Guo Long-yuan, Xia Yong-quan, and Yang Jing-yu. Fastregion-matching approach based on disparity gradient[J].Computer Science, 2007, 34(4): 239-240, 257.[6]姜露露, 彭健. 基于极线几何约束的非标定图像的立体匹配[J]. 计算机应用, 2007, 27(11): 2800-2803.Jiang Lu-lu and Peng Jian. Stereo matching on uncalibratedimages based on epipolar geometry[J]. Journal of ComputerApplications, 2007, 27(11): 2800-2803.[7]吴熙, 钱盛友. 基于LoG 算子的图像边缘增强算法的改进[J].电气电子教学学报, 2007, 29(4): 25-27.Wu Xi and Qian Sheng-you. Improved edge enhancementalgorithm based on Gauss-Laplacian operator[J]. Journal ofElectrical Electronic Education, 2007, 29(4): 25-27.[8]Poward S B, Mayhew J E, and Frishy J P. PMF: A stereocorrepondence algorithm using a disparity gradient limit[J].Perception.1985, 14(4):449-470[9]Joon H H and Jong S P. Contour matching using epipolargeometry[J].IEEE Transactions on Pattern Analysis andMachine Intelligence.2000, 22(4):358-370[10]Zhang Z, Deriche R, and Faugeras O, et al.. A robusttechnique for matching two uncalibrated images through therecovery of the unknown epipolar geometry[J]. ArtificialIntelligence, 1995, 78(1): 87-119.[11]Schmid C and Mohr R. Matching by local invariants[R].Reserach Report, INRIA, France, 1995.[12]Schmid C and Mohr R. Local grayvalue invariants for imageretrieval[J].IEEE Transactions on Pattern Analysis andMatching Intelligence.1997, 19(5):530-535[13]Lowe D G. Distinctive image features from scale-invariantkeypoints[J].International Journal of Computer Vision.2004,60(2):91-110[14]Harris C and Stepens M. A combined corner and edgedetector[C]. The Fourth Alvey Conference, Manchester,America, 1988: 147-151.[15]Fusiello A, Tmcci E, and Vem A. A compact algorithm forrectification of stereo pairs[J].Machine Vision andApplications.2000, 12(1):16-22[16]马颂德, 张正友. 计算机视觉[M]. 第一版, 北京: 科学出版社,1998, 第2 章.Ma Song-de and Zhang Zheng-you. Computer Vision[M].Beijing: Science Press, 1998, Chapter 2.

施引文献

资源附件(0)

访问统计