[1]王世安,王向军,阴雷.基于扩展正交迭代的快速加权的相机位姿估计[J].红外技术,2020,42(3):205-212.[doi:10.11846/j.issn.1001_8891.202003001]
 WANG Shian,WANG Xiangjun,YIN Lei.Accelerative and Weighted Camera Pose Estimation Based on Extended Orthogonal Iterative Algorithm[J].Infrared Technology,2020,42(3):205-212.[doi:10.11846/j.issn.1001_8891.202003001]
点击复制

基于扩展正交迭代的快速加权的相机位姿估计
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
42卷
期数:
2020年第3期
页码:
205-212
栏目:
出版日期:
2020-03-23

文章信息/Info

Title:
Accelerative and Weighted Camera Pose Estimation Based on Extended Orthogonal Iterative Algorithm
文章编号:
1001-8891(2020)05-0205-08
作者:
王世安王向军阴雷
天津大学 精密测试技术及仪器国家重点实验室
Author(s):
WANG Shi’anWANG XiangjunYIN Lei
State Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University
关键词:
机器视觉图像处理位姿估计迭代算法计算复杂度
Keywords:
machine vision image processing pose estimation iterative algorithms computational complexity
分类号:
TP391
DOI:
10.11846/j.issn.1001_8891.202003001
文献标志码:
A
摘要:
相机位姿估计算法多基于参考点而较少利用图像中的直线信息,本文对于相机位姿估计算法的抗干扰性和实时性,在扩展正交迭代的基础上,提出了一种基于点和直线段结合的快速加权的相机位姿估计算法,该算法以加权共线性误差和加权共面性误差之和为误差函数,根据计算初值的深度信息和重投影误差确定权重系数,并对整体进行加速优化,将每次迭代计算的时间复杂度从O(n)降到了O(1)。仿真实验结果表明算法可以抑制异常点的干扰,减少计算时间,旋转矩阵计算误差比传统正交迭代算法减少48.31%,平移向量计算误差减少48.79%,加速优化后的计算时间为加速前的47.11%。实物实验表明该算法可以充分利用检测到的参考点和参考直线信息,提高计算精度,有较高的实际应用价值。
Abstract:
The camera pose estimation algorithm is typically more based on reference points and less on the linear information in the image. In this paper, based on the extended orthogonal iteration, an accelerative and weighted camera pose estimation algorithm based on the combination of point and line segments is proposed to ensure a good anti-interference and real-time performance of the algorithm. The algorithm considers the sum of the weighted collinearity error and the weighted coplanarity error as the error function. The weight coefficients are determined by the depth information and the re-projection error of the initial value. In addition, the algorithm accelerates the iterative process and reduces the time complexity of the iteration process dramatically from O(n) to O(1). The simulation results demonstrate that the algorithm can suppress the interference of abnormal points and reduce the calculation time. The calculation accuracy of the rotation matrix is 51.69% higher than that of the traditional orthogonal iterative algorithm, and the calculation accuracy of the translation vector is increased by 51.21%. Furthermore, the calculation time after the acceleration is reduced by 47.11%. The physical experiment shows that the algorithm can make full use of the detected reference points and reference line information, improve the calculation accuracy, reduce the cumulative error, and has high practical application value.

参考文献/References:

[1]? Mullen R. Manual of photogrammetry[M]. Barlow: Asprs Publications, 2004.
[2]? Hartley R, Zisserman A. Multiple view geometry in computer vision[M]. Cambridge: Cambridge university press, 2003.
[3]? Gingold Y, Igarashi T, Zorin D. Structured annotations for 2D-to-3D modeling[C]//ACM Transactions on Graphics (TOG). ACM, 2009, 28(5): 148.
[4]? DeSouza G N, Kak A C. Vision for mobile robot navigation: A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(2): 237-267.
[5]? Mur-Artal R, Montiel J M M, Tardos J D. ORB-SLAM: a versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics, 2015, 31(5): 1147-1163.
[6]? 钱萍, 王惠南. 基于对偶四元数的航天器交会对接位姿双目视觉测量算法[J]. 宇航学报, 2013, 34(1): 32-38.
QIAN Ping, WANG Huinan. A Binocular Vision Algorithm Based on Dual Quaternion for Relative Position and Attitude Determinati of RVD Spacecrafts[J]. Journal of Astronautics, 2013, 34(1): 32-38.
[7]? 吴凡路, 刘建军, 任鑫, 等. 基于圆形标志点的深空探测全景相机标定方法[J]. 光学学报, 2013, 33(11): 1115002.
WU Fanlu, LIU Jianjun, REN Xin, et al. Deep space exploration panoramic camera calibration technique basedon circular markers[J]. Acta Optica Sinica, 2013, 33(11): 1115002.
[8]? Azuma R, Baillot Y, Behringer R, et al. Recent advances in augmented reality[J]. IEEE computer graphics and applications, 2001, 21(6): 34-47.
[9]? Haralick R M, Joo H, Lee C N, et al. Pose estimation from corresponding point data[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1989, 19(6): 1426-1446.
[10]? 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.
[11]? Pumarola A, Vakhitov A, Agudo A, et al. PL-SLAM: Real-time monocular visual SLAM with points and lines[C]//2017 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2017: 4503-4508.
[12]? 许允喜, 蒋云良, 陈方. 基于点和直线段对应的扩展正交迭代位姿估计算法[J]. 光学学报, 2009(11): 3129-3135.
XU Yunxi, JIANGYunliang, CHEN Fang. An Extended Orthogonal Iteration Algorithm for Pose Estimation from Point and Line Segment Correspondences [J]. Acta Optica Sinica, 2009, 29(11): 3129-3135.
[13]? 周润, 张征宇, 黄叙辉. 相机位姿估计的加权正交迭代算法[J]. 光学学报, 2018, 38(5): 0515002.
ZHOU Run, ZHANG Zhengyu, HUANG Xuhui. Weighted Orthogonal Iteration Algorithm for Camera Pose Estimation[J]. Acta Optica Sinica, 2018, 38(5): 193-199.
[14]? ZHENG Y, KUANG Y, Sugimoto S, et al. Revisiting the pnp problem: A fast, general and optimal solution[C]//Proceedings of the IEEE International Conference on Computer Vision, 2013: 2344-2351.
[15]? LI S, 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.
[16]? Geiger A, Lenz P, Stiller C, et al. Vision meets robotics: The KITTI dataset[J]. The International Journal of Robotics Research, 2013, 32(11): 1231-1237.
[17]? VonGioi R G, Jakubowicz J, Morel J M, et al. LSD: A fast line segment detector with a false detection control[J]. IEEE transactions on pattern analysis and machine intelligence, 2008, 32(4): 722-732.

相似文献/References:

[1]宋燕星,高琴,姚振静,等.主动红外探测式视觉生命探测系统[J].红外技术,2012,34(09):521.
 SONG Yan-xing,YANG Jing-song,YAO Zhen-jing,et al.Visual Detection System with Active Infrared Detection Method[J].Infrared Technology,2012,34(3):521.
[2]张双垒,林剑春,段东,等.基于遗传算法红外小目标检测的研究[J].红外技术,2012,34(08):472.
 ZHANG Shuang-lei,LIN Jian-chun,DUAN Dong,et al.Infrared Small Target Detection Research Based on Genetic Algorithm[J].Infrared Technology,2012,34(3):472.
[3]邢勇,邢冀川,宋艳.基于CCD的脉冲激光器远场发散角工程化研究[J].红外技术,2011,33(09):525.
 XING Yong,XING Ji-chuan,SONG Yan.Engineering Study on the CCD-based Measurement?of Pulse Laser far-field Divergence Angle[J].Infrared Technology,2011,33(3):525.
[4]李一芒,何 昕,魏仲慧.多级式红外预警图像处理系统设计与实现[J].红外技术,2014,36(2):131.[doi:10.11846/j.issn.1001_8891.201402009]
 LI Yi-mang,HE Xin,WEI Zhong-hui.Design and Implementation of Multistage Infrared Early Warning System[J].Infrared Technology,2014,36(3):131.[doi:10.11846/j.issn.1001_8891.201402009]
[5]许真,孙韶媛,代中华,等.基于纹理特征库的微光图像色彩纹理传递[J].红外技术,2011,33(01):049.
 XU Zhen,SUN Shao-yuan,DAI Zhong-hua,et al.Texture Library Based Color & Texture Transferring for LLL Images[J].Infrared Technology,2011,33(3):049.
[6]吴先权,华文深,赵莉君,等.红外上转换薄膜的分辨率数字化测试研究[J].红外技术,2010,32(11):632.
 WU Xian-quan,HUA Wen-shen,ZHAO Li-jun,et al.Study on Digitalized Resolution Testing of Infrared Up-conversion Thin Film[J].Infrared Technology,2010,32(3):632.
[7]代中华,孙韶媛,许真,等.一种车载红外视频彩色化算法[J].红外技术,2010,32(10):595.
 DAI Zhong-hua,SUN Shao-yuan,XU Zhen,et al.A Colorization Algorithm for Vehicle Infrared Video[J].Infrared Technology,2010,32(3):595.
[8]魏振忠,郭雨蓉,何小妹,等.基于蚁群算法和线段分析的建筑物特征提取[J].红外技术,2009,31(2):119.
 WEI Zhen-zhong,GUO Yu-rong,HE Xiao-mei,et al.The Extraction of Building Based on Ant Colony Algorithm?and the Analysis of Line Segment[J].Infrared Technology,2009,31(3):119.
[9]胡茂海,符建辉,陶纯堪.基于DSP实时联合变换相关器系统设计[J].红外技术,2009,31(4):196.
 HU Mao-hai,FU Jian-hui,TAO Chun-kan.The System Design of Real-time Joint Transform Correlator Based on DSP[J].Infrared Technology,2009,31(3):196.
[10]孙君顶,赵慧慧.图像稀疏表示及其在图像处理中的应用[J].红外技术,2014,36(7):533.[doi:10.11846/j.issn.1001_8891.201407004]
 SUN Jun-ding,ZHAO Hui-hui.Sparse Representation and Applications in Image Processing[J].Infrared Technology,2014,36(3):533.[doi:10.11846/j.issn.1001_8891.201407004]

备注/Memo

备注/Memo:
收稿日期:2019-10-09;修订日期:2020-02-27.
作者简介:王世安(1995-),男,硕士,主要研究方向为计算机视觉和图像处理。E-mail:sean_wang@tju.edu.cn。

更新日期/Last Update: 2020-03-17