基于灰度投影的数字近景摄影立体影像匹配

盛业华; 张卡; 叶春; 牛芩涛; 韩冰

光学学报, 2005, 25 (12): 1623, 网络出版: 2006-05-23

基于灰度投影的数字近景摄影立体影像匹配

Stereo Image Matching for Digital Close-Range Photogrammetry Based on Gray-Scale Projection

论文大纲

盛业华 ^*张卡叶春牛芩涛韩冰

作者单位

南京师范大学地理信息科学江苏省重点实验室,南京 210097

摘要

根据数字近景摄影测量的特点,针对建筑物三维建模的需要,提出了基于灰度投影的影像匹配算法。该算法将影像行、列两个方向上的一维灰度投影,拓展为行、列、主对角线和次对角线四个方向上的一维灰度投影,计算左右影像的四个一维投影向量间的相似性测度的加权平均值作为最后的匹配测度。利用相对定向线性变换(RLT)算法来确定同名核线,以改进的动态定界法来控制待匹配点序列中后续点沿核线匹配的搜索范围,以减少匹配的搜索空间并提高匹配的准确度。利用该算法对建筑物数字近景摄影影像进行了实验,结果表明该算法具有较高的匹配速度和匹配准确率。

Abstract

For the purposes of three-dimensional modeling of buildings, a new stereo image matching algorithm based on the gray-scale projection is advanced considering the characteristics of the digital close-range photogrammetry. The algorithm extends the one-dimensional gray-scale projection from two directions to four directions. The gray-scale projections in the column, row, major diagonal and secondary diagonal directions are calculated simultaneously. The weighted average of similarity measure of these four one-dimensional projection vectors between the left image and right image is computed for the final matching decision. Homonymous epipolar lines are found by using the relative orientation linear transformation (RLT). To decrease the searching scope and improve the matching accuracy, an improved dynamic bounding approach is proposed to control the searching scope of sequential points in the point list to be matched along the homonymy epipolar-line. The new algorithm is applied to actual stereo images of a building taken by a digital close-range photogrammetric system and the experimental result shows that the algorithm has a higher matching speed and matching accuracy than the pyramid image matching algorithm.

参考文献

[1] . Discussions on the issues in digital close-range-photogrammetry with non-metric images[J]. J. Kunming University of Science and Technology, 2002, 27(4): 6-11.

[2] Liu Zhangwen, Gu Tianxiang. Three-dimensional measurement of object by using gray gradient of CCD image[J]. Acta Optica Sinica, 2003, 23(11): 1384～1387 (in Chinese)
刘章文,古天祥. 利用CCD图像的灰度梯度实现物体三维测量[J]. 光学学报, 2003, 23(11): 1384～1387

[3] Zhu Qing, Lin Hui. Geographical Information System for Cyber-City: Exploration 3 Dimensional City Model in Virtual City Environment[M]. Wuhan: Wuhan University Press, 2004 (in Chinese)
朱庆,林珲. 数码城市地理信息系统虚拟城市环境中的三维城市模型初探[M]. 武汉: 武汉大学出版社,2004

[4] Zhang Zhuxun, Zhang Jianqing. Digital Photogrammetry[M]. Wuhan: Wuhan University Press, 1997. 114～120 (in Chinese)
张祖勋,张剑清. 数字摄影测量学[M]. 武汉: 武汉大学出版社, 1997 114～120

[5] . Automatic image matching based on wavelet pyramid[J]. J. Institute of Surveying and Mapping, 2002, 19(1): 25-27.

[6] . Robust image matching under partial occlusion and spatially varying illumination change[J]. Computer Vision and Image Understanding, 2000, 78(1): 84-98.

[7] Cheng Gang, Jin Guofan, Liu Haisong et al.. Using optical walsh transformation for feature extraction in image matching[J]. Acta Optica Sinica, 2001, 21(2): 167～172 (in Chinese)
成罡,金国藩,刘海松等. 基于光学沃尔什变换特征提取的图像匹配[J]. 光学学报, 2001, 21(2): 167～172

[8] . . Feature-based image mathcing for aerial images[J]. Geomatics and Information Science of Wuhan University, 2003, 28(5): 510-513.

[9] . A feature-based and least square image matching with constraints[J]. J. Image and Graphics, 1998, 3(4): 299-302.

[10] Peng Zhenming, Zhang Qiheng, Wei Yuxing et al.. Image matching based on multi-features fusion[J]. High Power Laser and Particle Beams, 2004, 16(3): 281～284 (in Chinese)
彭真明,张启衡,魏宇星等. 基于多特征融合的图像匹配模式[J]. 强激光与粒子束, 2004, 16(3): 281～284

[11] . Adnan, Y. Mustafa. Fuzzy shape matching with boundary signatures[J]. Pattern Recognition Lett., 2002, 23(12): 1473-1482.

[12] . Biswas, A. Konar, K. Achintya et al.. Image matching with fuzzy moment descriptors[J]. Engineering Applications of Artificial Intelligence, 2001, 14(1): 43-49.

[13] . Balslev. Noise tolerance of moment invariants in pattern recognition[J]. Pattern Recognition Lett., 1998, 19(13): 1183-1189.

[14] . Image matching using run-length feature[J]. Pattern Recognition Lett., 2001, 22(5): 447-455.

[15] . El Ansari, L. Masmoudi, L. Radouane. A new region matching method for stereoscopic images[J]. Pattern Recognition Lett., 2000, 21(4): 283-294.

[16] Liu Yaxuan, Su Xiuqin, Wang Ping. Image matching based on local projection entropy[J]. Acta Photonica Sinica, 2004, 33(1): 105～107 (in Chinese)
刘雅轩,苏秀琴,王萍. 一种基于局部投影熵的图像匹配新算法[J]. 光子学报, 2004, 33(1): 105～107

[17] Zeng Luan, Li Yingchun. A method of enhancing image matching speed[J]. Application of Electronic Technique, 2000, (8): 13～14 (in Chinese)
曾峦,李迎春. 提高图像匹配速度的一种方法[J]. 电子技术应用, 2000, (8): 13～14

盛业华, 张卡, 叶春, 牛芩涛, 韩冰. 基于灰度投影的数字近景摄影立体影像匹配[J]. 光学学报, 2005, 25(12): 1623. 盛业华, 张卡, 叶春, 牛芩涛, 韩冰. Stereo Image Matching for Digital Close-Range Photogrammetry Based on Gray-Scale Projection[J]. Acta Optica Sinica, 2005, 25(12): 1623.

基于灰度投影的数字近景摄影立体影像匹配

关于本站 Cookie 的使用提示

全站搜索

基于灰度投影的数字近景摄影立体影像匹配

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索