基于机器视觉的最大似然位姿估计算法

屈也频; 张超然; 吕余海

doi:doi:10.5768/jao201940.0202002

应用光学, 2019, 40 (2): 253, 网络出版: 2019-03-26

基于机器视觉的最大似然位姿估计算法

Maximum likelihood pose estimation using machine vision

论文大纲

屈也频 ^*张超然吕余海

作者单位

海军研究院, 上海 200235

机器视觉位姿估计最大似然估计克拉美-罗界 machine vision pose estimation maximum likelihood estimation Cramér-Rao bound

摘要

针对现有位姿估计算法对采样数据不做任何的统计假设, 缺少评判标准等问题, 从信号的概率密度函数出发, 推导了基于机器视觉的最大似然位姿估计的一般形式, 并证明利用单幅图像时, 在各向同性高斯噪声情况下传统迭代算法与最大似然估计等效。推导了位姿估计的克拉美-罗界, 给出了位姿估计的方差下限。根据仿真结果可以看出, 利用10张图像时, 最大似然算法在噪声功率大于5 dB的情况下, 性能明显优于传统迭代算法, 证明适当增加图像数可有效提高估计性能。

Abstract

The existing pose estimation algorithms do not make any statistical assumptions on the sampled data, and lack the evaluation criteria. Aiming at this problem, based on the probability density function of the signal, we derived the general form of maximum likelihood pose estimation based on machine vision was and proved that the traditional iterative algorithm is equivalent to the maximum likelihood estimation using single imag ein the case of isotropic Gaussian noise.What′s more, we derived the Cramér-Rao bound of pose estimation, which could be regarded as the variance low bound of any unbiased estimations. By the analysis of the simulation, the maximum likelihood method is much better than the traditional iterative method by using 10 pictures when noise power is greater than 5 dB, it proves that the performance of pose estimation can be improved by increasing the number of images.

参考文献

[1] LI S Q, XU C. Efficient lookup table based camera pose estimation for augmented reality［J］. Computer Animation and Virtual Worlds, 2011, 22(1): 47-58.

[2] CAMPA G, MAMMARELLA M, NAPOLITANO M R, et al．A comparison of pose estimation algorithms for machine vision based aerial refueling for UAV［C］. US: IEEE, 2006.

[3] 汪启跃, 王中宇. 基于单目视觉的航天器位姿测量［J］. 应用光学, 2017, 38(2): 250-255.

WANG Qiyue, WANG Zhongyu. Position and pose measurement of spacecraft based on monocular vision［J］. Journal of Applied Optics, 2017, 38(2): 250-255.

[4] LI S Q, XU C, XIE M. A robust O(n) solution to the perspective-n-point problem［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1444-1450.

[5] LEPETIT V, MORENO-NOGUER F, FUA P. EPnP: an accurate O(n) solution to the PnP problem［J］. International Journal of Computer Vision, 2009, 81(2): 155-166.

[6] HMAM H, KIM J. Optimal non-iterative pose estimation via convex relaxation［J］. Image and Vision Computing, 2010, 28(11): 1515-1523.

[7] LOWE D G. Three-dimensional object recognition from single two-dimensional images［J］. Artificial Intelligence, 1987, 31(3): 355-395.

[8] 陈鹏. 基于单目视觉的像机位姿估计技术［D］. 北京: 北京科技大学, 2015.

CHEN Peng. Monocular based camera pose estimation［D］. Beijing: University of Science and Technology Beijing, 2015.

[9] LU C P, HAGER G D, MJOLSNESS E. Fast and globally convergent pose estimation from video images［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(6): 610-622.

[10] 李鑫, 龙古灿, 刘进博, 等. 相机位姿估计的加速正交迭代算法［J］. 光学学报, 2015, 35(1): 258-265.

LI Xin, LONG Gucan, LIU Jinbo, et al. Accelerative orthogonal iteration algorithm for camera pose estimation［J］. Acta Optica Sinica, 2015, 35(1): 258-265.

[11] SCHWEIGHOFER G, PINZ A．Robust pose estimation from a planar target［J］．IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12): 2024-2030.

[12] 罗鹏飞, 张文明, 刘忠, 等．统计信号处理基础［M］．北京: 电子工业出版社, 2014: 155-202.

LUO Pengfei, ZHANG Wenming, LIU Zhong, et al．Fundamentals of statistical signal processing［M］．Beijing: Publishing House of Electronics Industry, 2014: 155-202.

[13] STOICA P, NEHORIA A．Mode, maximum likelihood, and Cramér-Rao bound: conditional and unconditional results［R］. New Haven: Center for Systems Science Yale University, 1989.

[14] FRIEDLANDER B, PORAT B. The exact Cramer-Rao bound for Gaussian autoregressive processes［J］. IEEE Transactions on Aerospace and Electronic Systems, 1989, 25(1): 3-7.

[15] VAN TREES H L．Detection, estimation, and modulation theory, Part VI［M］. New York: Wiley Interscience, 2001: 689-785.

屈也频, 张超然, 吕余海. 基于机器视觉的最大似然位姿估计算法[J]. 应用光学, 2019, 40(2): 253. QU Yepin, ZHANG Chaoran, LYU Yuhai. Maximum likelihood pose estimation using machine vision[J]. Journal of Applied Optics, 2019, 40(2): 253.

基于机器视觉的最大似然位姿估计算法

关于本站 Cookie 的使用提示

全站搜索

基于机器视觉的最大似然位姿估计算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索