Stereo matching of objects with same features based on delaunay triangulation and affine constraint

被引：0
作者：
Wang X. [1 ,2 ]
Xing F. [1 ,2 ]
Liu F. [1 ,2 ]
机构：
[1] State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin
[2] Key Laboratory of MOEMS of the Ministry of Education, Tianjin University, Tianjin
来源：
Liu, Feng (tjuliufeng@tju.edu.cn) | 1600年 / Chinese Optical Society卷 / 36期
关键词：
Affine constraint; Affine scale-invariant feature transform algorithm; Delaunay triangulation; Machine vision; Multiple objects with same features; Stereo matching;
D O I：
10.3788/AOS201636.1115004
中图分类号：
学科分类号：
摘要：
For practical demand of the localization of multiple random objects with large view filed, long distance and same features, a 3D coordinate measuring system is established based on the binocular stereo vision theory. To precisely position the multiple random objects with the same features, the multiple objects need matching correctly. An innovative method based on the Delaunay triangulation and affine constraint is proposed to achieve correct matching of the multiple objects with same features. The matching points on the background images are obtained with the affine scale-invariant feature transform (ASIFT) algorithm that has an anti-affine transformation. The Delaunay triangulation algorithm is used to generate triangular meshes by the seed points. The affine matrix of the triangular region is calculated by using vertexes of matched triangles. According to the distribution of object points in different matched triangles, the multiple objects with same features will be matched by the affine constraint. Experimental results show that the proposed method realizes the fast and efficient matching of multiple objects with same features. The time of object extraction and real-time matching is about 30 ms, which satisfies the requirement of 25 frame/s real-time processing for cameras. The proposed method solves the problem of matching of multiple objects with same features on the arc slope in large 3D space. © 2016, Chinese Lasers Press. All right reserved.
引用
收藏
页数：8
相关论文
共 16 条
  • [1] Zhu Z., Yuan Y., Li Y., Et al., High precision matching and 3D surface reconstruction of Chang'E 1 lunar images, Acta Optica Sinica, 34, 2, (2014)
  • [2] Tong Y., Lu C., Development of a simple 3D image measurement system for construction and renovation, IEEE 6th International Conference on Awareness Science and Technology, (2014)
  • [3] Wu X., Guo B., Wang J., Cylindrical panoramic image automatic mosaic algorithm based on phase correlation, Acta Optica Sinica, 29, 7, pp. 1824-1829, (2009)
  • [4] Brown M., Lowe D.G., Automatic panoramic image stitching using invariant features, International Journal of Computer Vision, 74, 1, pp. 59-73, (2007)
  • [5] Wang X., Wang Y., Li Z., Fast target recognition and tracking method based on characteristic corner, Acta Optica Sinica, 27, 2, pp. 360-364, (2007)
  • [6] Li G., Wang W., Wang Y., Et al., Nano-manipulation based on real-time compressive tracking, IEEE Transactions on Nanotechnology, 14, 5, pp. 837-846, (2015)
  • [7] Wang X., Bian Y., Liu F., Et al., Optimization of structural parameters of binocular vision system in remote 3D coordinate measurement, Optics and Precision Engineering, 23, 10, pp. 2902-2908, (2015)
  • [8] Hartley R., Zisserman A., Multiple View Geometry in Computer Vision, pp. 1865-1872, (2003)
  • [9] Bentolila J., Francos J.M., Homography and fundamental matrix estimation from region matches using an affine error metric, Journal of Mathematical Imaging & Vision, 49, 2, pp. 481-491, (2014)
  • [10] Guo L., Zhu J., Ye S., Precision registration of corresponding uncode points in large-sized 3D surface measurement using three images, Infrared and Laser Engineering, 37, 6, pp. 1079-1082, (2008)
12