应用序贯相似检测的基本矩阵快速鲁棒估计

唐永鹤; 胡旭峰; 卢焕章

doi:10.3788/OPE.20111911.2759

您当前的位置：

首页 >

文章列表页 >

应用序贯相似检测的基本矩阵快速鲁棒估计

信息科学 | 更新时间：2020-08-12

- 应用序贯相似检测的基本矩阵快速鲁棒估计
- Fast and robust fundamental matrix estimation based on SSDA
- 光学精密工程 2011年19卷第11期页码：2759-2766
- 作者机构：
  
  国防科学技术大学 ATR实验室,湖南长沙,410073
- 作者简介：
- 基金信息：
  
  国家863高技术研究发展计划资助项目(No.2015AA123703)
- DOI：10.3788/OPE.20111911.2759
  中图分类号： TP391
- 收稿日期：2011-05-09，
  
  修回日期：2011-06-22，
  
  网络出版日期：2011-11-25，
  
  纸质出版日期：2011-11-25
- 稿件说明：
移动端阅览
唐永鹤, 胡旭峰, 卢焕章. 应用序贯相似检测的基本矩阵快速鲁棒估计[J]. 光学精密工程, 2011,19(11): 2759-2766

TANG Yong-he, HU Xu-feng, LU Huan-zhang. Fast and robust fundamental matrix estimation based on SSDA[J]. Editorial Office of Optics and Precision Engineering, 2011,19(11): 2759-2766
唐永鹤, 胡旭峰, 卢焕章. 应用序贯相似检测的基本矩阵快速鲁棒估计[J]. 光学精密工程, 2011,19(11): 2759-2766 DOI： 10.3788/OPE.20111911.2759.

TANG Yong-he, HU Xu-feng, LU Huan-zhang. Fast and robust fundamental matrix estimation based on SSDA[J]. Editorial Office of Optics and Precision Engineering, 2011,19(11): 2759-2766 DOI： 10.3788/OPE.20111911.2759.

摘要

提出了一种基于序贯相似检测(SSDA)的快速鲁棒基本矩阵估计算法来估计基本矩阵。在最大后验一致性(MAPSAC)算法中引入SSDA搜索最优模型参数

通过及时剔除错误模型减少计算成本函数的累加次数

不仅保持了MAPSAC的良好鲁棒性

而且有效减少了算法的计算量。用M估计算法对改进的MAPSAC算法获得的初始内点集进行优化

剔除估计余差较大的内点

并用优化的内点集求解基本矩阵

进一步提高算法的估计精度和鲁棒性。实验结果表明

该算法不仅估计精度较高

鲁棒性较好

而且平均处理速度比MAPSAC算法提高了30%以上

基本满足三维重建、匹配和跟踪、相机自标定等应用领域对实时性、鲁棒性和精度的要求。

Abstract

A fast and robust fundamental matrix estimation method based on Sequential Similarity Detection Algorithm (SSDA) is presented to estimate the fundamental matrix rapidly and accurately. The SSDA is introduced into the Maximum a Posteriori Sample Consensus (MAPSAC) to search the optimum model parameters and the accumulation times of computing a cost function are cut down by eliminating the false model as soon as possible

which not only keeps the better robustness of MAPSAC

but also reduces its computation effectively. Then

the initial inliers obtained by the improved MAPSAC are optimized with a M-estimator. Those inliers with larger residual errors are removed and the optimized inliers are used to compute the fundamental matrix to enhance the precision and improve the robustness of the algorithm. Experiment results demonstrate that the proposed algorithm performs better in accuracy and robustness

and its average speed has increased at least 30% as compared with that of the MAPSAC. The proposed algorithm can satisfy the requirements for real-time

precision and robustness in the fields such as three-dimensional reconstruction

image matching

image tracking and camera self-calibration.

关键词

Keywords

references

ZHOU H Y, PATRICK R G, ANDREW M. Estimation of epipolar geometry by linear mixed-effect modelling[J]. Neurocomputing, 2009, 72(16-18): 3881-3890.[2] 向长波, 谢丹, 刘太辉,等. 估计多视点摄像机姿态的两步法[J]. 光学精密工程, 2008, 16(10): 1982-1987. XIANG C B, XIE D, LIU T H, et al.. A two step algorithm for estimating postures of cameras located in different points of view[J]. Opt. Precision Eng., 2008, 16(10): 1982-1987. (in Chinese)[3] ONAY U, THORSTEN T, HELLWARD B, et al.. Algebraic error analysis of collinear feature points for camera parameter estimation[J]. Computer Vision and Image Understanding, 2011, 115(4): 467-475.[4] 张灵飞, 陈刚, 叶东,等. 用自由移动的刚性球杆校准多摄像机内外参数[J]. 光学精密工程, 2009, 17(8): 1942-1952. ZHANG L F, CHEN G, YE D, et al.. Calibrating internal and external parameters of multi-cameras by moving freely rigid ball bar[J]. Opt. Precision Eng., 2009, 17(8): 1942-1952. (in Chinese)[5] 孙军华, 吴子彦, 刘谦哲,等. 大视场双目视觉传感器的现场标定[J]. 光学精密工程, 2009, 17(3): 633-640. SUN J H, WU Z Y, LIU Q ZH, et al.. Field calibration of stereo vision senor with large FOV[J]. Opt. Precision Eng., 2009, 17(3): 633-640. (in Chinese)[6] SERGIU N, CATALIN G, COSMIN M. Improving accuracy for ego vehicle motion estimation using epipolar geometry . Proceedings of the 12th International IEEE Conference on Intelligent Transportation Systems, St. Louis, MO, USA, 2009: 596-602.[7] 汪剑鸣, 闫志杰, 段晓杰,等. 相机自运动参数的鲁棒性估计[J]. 红外与激光工程, 2010, 39(6): 1168-1172. WANG J M,YAN ZH J, DUAN X J, et al.. Robust estimation of camera ego-motion parameters[J] Infrared and Laser Engineering, 2010, 39(6): 1168-1172. (in Chinese)[8] LI Q, XING G M. New similarity measures of localities for a two-layer matching scheme and estimation of fundamental matrices[J]. Neurocomputing, 2010, 73(16-18): 3114-3122.[9] ARMANGUE X, SALVI J. Overall view regarding fundamental matrix estimation[J]. Image and Vision Computing, 2003, 21: 205-220.[10] ZHANG ZH Y. Determining the epipolar geometry and its uncertainty: a review[J]. International Journal of Computer Vision, 1998, 27(2): 161-198.[11] HARTLEY R. In defense of the eight-point algorithm[J]. IEEE Transactions on Pattern Recognition and Machine Intelligence, 1997, 19(6): 580-593.[12] 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. CHEN Z ZH, WU CH K. A linear algorithm with high accuracy for estimating fundamental matrix[J]. Journal of Software, 2002, 13(4): 840-845. (in Chinese)[13] HARTLEY R, ZISSERMAN A. Multiple View Geometry in Computer Vision[M]. London: Cambridge University Press, 2000.[14] 陈付幸, 王润生. 基于预检验的快速随机抽样一致性算法[J]. 软件学报, 2005, 16(8):1431-1437. CHEN F X, WANG R SH. Fast RANSAC with preview model parameters evaluation[J]. Journal of Software, 2005, 16(8):1431-1437. (in Chinese)[15] TORDOFF B, MURRAY D W. Guided-MLESAC: faster image transform estimation by using matching priors[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1523-1535.[16] TORR P H S. Bayesian model estimation and selection for epipolar geometry and generic manifold fitting[J]. International Journal of Computer Vision. 2002, 50 (1): 35-61.[17] 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. XIANG CH B, LIU T H, SONG J ZH. A robust greedy algorithm for estimating the fundamental matrix[J]. Journal of Computer-Aided Design & Computer Graphics, 2007, 19(5): 651-655. (in Chinese)[18] 仲训昱, 朱齐丹, 张智. 数字稳像中的快速和鲁棒运动估计研究[J]. 电子学报, 2010, 38(1): 251-256. ZHONG X Y, ZHU Q D, ZHANG ZH. Study of fast and robust motion estimation in the digital image stabilization[J]. Acta Electronica Sinica, 2010, 38(1): 251-256. (in Chinese)[19] 陈夏艳, 伍先达. 基于距离特征的自适应阈值视频拼接算法 [J]. 模式识别与人工智能, 2010, 23(5): 727-730. CHEN X Y, WU X D. Adaptive threshold video splicing algorithm based on distance feature[J]. Pattern Recognition and Artificial Intelligence, 2010, 23(5): 727-730. (in Chinese)[20] 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.

浏览量

418

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据