|Table of Contents|

[1] Yang Ankang, Liu Jingnan, Yoshihisa Uchida, Yoshiyuki Uchida, et al. Fast estimation of fundamental matrix based on stripe constraints [J]. Journal of Southeast University (English Edition), 2008, 24 (4): 473-477. [doi:10.3969/j.issn.1003-7985.2008.04.015]
Copy

Fast estimation of fundamental matrix based on stripe constraints()
基于条纹边界约束的基本矩阵快速估算
Share:

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
24
Issue:
2008 4
Page:
473-477
Research Field:
Computer Science and Engineering
Publishing date:
2008-12-30

Info

Title:
Fast estimation of fundamental matrix based on stripe constraints
基于条纹边界约束的基本矩阵快速估算
Author(s):
Yang Ankang1 Liu Jingnan1 Yoshihisa Uchida2 Yoshiyuki Uchida2
1 School of Automation, Southeast University, Nanjing 210096, China
2 Department of Information Network Engineering, Aichi Institute of Technology, Toyoda 470-0392, Japan
杨安康1 刘京南1 内田敬久2 内田悦行2
1东南大学自动化学院, 南京 210096; 2爱知工业大学情报通讯工学科, 日本爱知丰田 470-0392
Keywords:
fundamental matrix structured-light stripe code pattern stereo vision
基本矩阵 结构光 条纹编码模式 双目视觉
PACS:
TP391
DOI:
10.3969/j.issn.1003-7985.2008.04.015
Abstract:
In order to improve the performance of estimating the fundamental matrix, a key problem arising in stereo vision, a novel method based on stripe constraints is presented.In contrast to traditional methods based on algebraic least-square algorithms, the proposed approach aims to minimize a cost function that is derived from the minimum radius of the Hough transform.In a structured-light system with a particular stripe code pattern, there are linear constraints that the points with the same code are on the same surface.Using the Hough transform, the pixels with the same code map to the Hough space, and the radius of the intersections can be defined as the evaluation function in the optimization progress.The global optimum solution of the fundamental matrix can be estimated using a Levenberg-Marquardt optimization iterative process based on the Hough transform radius.Results illustrate the validity of this algorithm, and prove that this method can obtain good performance with high efficiency.
为了提高计算机视觉领域中核心问题之一的基础矩阵估算的效率, 基于条纹边界编码约束实现了一种快速估算方法.与传统的基于代数最小二乘法算法不同, 该算法利用Hough变换将Hough半径作为最优化过程的最小化因子.在特定条纹边界编码的结构光投影系统模型下, 利用条纹编码的共面性构造线性约束, 采用Hough变换将同码像素映射到Hough空间, 其交点的半径可作为最优化评价函数的最小化因子.再通过Levenberg-Marquardt最优化迭代过程估算出基本矩阵的全局最优解.实验结果表明了该算法的正确性, 并证明了其可有效提高估算精度与效率.

References:

[1] Mittal A, Davis L S.A general method for sensor planning in multi-sensor systems:extension to random occlusion [J].International Journal of Computer Vision, 2008, 76(1):31-52.
[2] Tang C Y, Chou H L, Wu Y L, et al.Robust fundamental matrix estimation using coplanar constraints [J].International Journal of Pattern Recognition and Artificial Intelligence, 2008, 22(4):783-805.
[3] Hua M, McMenemy K, Ferguson S, et al.Epipolar geometry estimation based on evolutionary agents[J].Pattern Recognition, 2008, 41(2):575-591.
[4] Huang J F, Lai S H, Cheng C M.Robust fundamental matrix estimation with accurate outlier detection[J].Journal of Information Science and Engineering, 2007, 23(4):1213-1225.
[5] Chojnacki W, Brooks M J.On the consistency of the normalized eight-point algorithm [J].Journal of Mathematical Imaging and Vision, 2007, 28(1):19-27.
[6] Brandt S.On the probabilistic epipolar geometry [J].Image and Vision Computing, 2008, 26(3):405-414.
[7] Tang C Y, Wu Y L, Lai Y H.Fundamental matrix estimation using evolutionary algorithms with multi-objective functions [J].Journal of Information Science and Engineering, 2008, 24(3):785-800.

Memo

Memo:
Biographies: Yang Ankang(1977—), male, graduate;Liu Jingnan(corresponding author), male, doctor, professor, liujn@seu.edu.cn.
Citation: Yang Ankang, Liu Jingnan, Yoshihisa Uchida, et al.Fast estimation of fundamental matrix based on stripe constraints[J].Journal of Southeast University(English Edition), 2008, 24(4):473-477.
Last Update: 2008-12-20