Please wait a minute...
JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE)  2018, Vol. 52 Issue (1): 151-159    DOI: 10.3785/j.issn.1008-973X.2018.01.020
Automatic Technology     
Camera pose estimation based on three-view geometry constraint
ZHANG Zhen-jie, LI Jian-sheng, ZHAO Man-dan, ZHANG Xiao-dong
School of Navigation and Aerospace Engineering, Information Engineering University, Zhengzhou 450000, China
Download:   PDF(1647KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A novel pose estimation method based on three-view geometry constraint was proposed in order to solve camera pose estimation from image sequence. Image feature points were detected by using brute force selection mechanism, and feature points were matched based on optical flow algorithm and forward-backward error. Then pose estimation based on improved essential matrix decomposition was deduced. Object function was established according to epipolar geometry constraint, and rotation matrix was iteratively computed. Then a unique solution was obtained. The first and second camera projective matrices were obtained. The object function was built based on trifocal tensor and matching points, and the third camera pose matrix that was relative to the first camera was iteratively computed. Results show that the proposed method improves the robust, position accuracy and efficiency. The method can achieve a precision estimation fast and estimate the trajectory of rotor UAV.



Received: 07 September 2017      Published: 15 December 2017
CLC:  TP391  
Cite this article:

ZHANG Zhen-jie, LI Jian-sheng, ZHAO Man-dan, ZHANG Xiao-dong. Camera pose estimation based on three-view geometry constraint. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(1): 151-159.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2018.01.020     OR     http://www.zjujournals.com/eng/Y2018/V52/I1/151


基于三视图几何约束的摄像机相对位姿估计

针对从影像中恢复摄像机位姿的问题,提出基于三视图几何约束的位姿估计算法.利用强制选择机制对影像进行特征点提取,通过光流法和前后向误差实现相邻三帧影像的特征点匹配;推导基于本质矩阵优化分解的位姿估计,利用对极几何约束构建目标函数,通过迭代优化确定旋转矩阵的唯一解,优化了唯一解的确定方法,提高了相对位姿估计效率,得到第1、2摄像机矩阵;基于三视图的几何约束关系,由三焦点张量和匹配特征点建立目标函数,由迭代过程得到第3摄像机相对于第1摄像机的位姿参数.结果表明,提出算法的鲁棒性、精度以及算法效率均优于传统算法,能够快速、准确地估计摄像机相对位姿,可以实现对旋翼无人机的轨迹跟踪.

[1] 陈明芽,项志宇,刘济林. 单目视觉自然路标辅助的移动机器人定位方法[J]. 浙江大学学报:工学版, 2014, 48(2):285-291. CHEN Ming-ya, XIANG Zhi-yu,LIU Ji-lin. Assistance localization method for mobile robot based on monocular natural visual landmarks[J]. Journal of Zhejiang University:Engineering Science, 2014, 48(2):285-291.
[2] AFIA A B,DEAMBROGIO L,SALOS D,et al. Review and classification of vision-based localization techniques in unknown environments[J]. IET Radar, Sonar and Navigation, 2014, 8(9):1059-1072.
[3] HEE L G, FAUNDORFER F, POLLEFEYS M. Motion estimation for self-driving cars with a generalized camera[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Portland:IEEE, 2013:2746-2753.
[4] BLOSCH M, WEISS S, SCARAMUZZA D, et al. Vision based MAV navigation in unknown and unstructured environments[C]//Robotics and automation (ICRA). Anchorage:IEEE, 2010:21-28.
[5] CHRISTAN F,MATIA P,DAVIDE S. SVO:fast semi-direct monocular visual odometry[C]//IEEE International Conference on Robotics and Automation (ICRA). Hong Kong:IEEE, 2014:15-22.
[6] ENGEL J, SCHOPS T, CREMERS D. LSD-SLAM:large-scale direct monocular SLAM[C]//European Conference on Computer Vision. Zurich:Springer, 2014:834-849.
[7] 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.
[8] HARTLEY R I, ZISSERMAN A. Multiple view geometry in computer vision[M]. UK:Cambridge University Press, 2004.
[9] 李国栋,田国会,王洪君,等. 弱标定立体图像对的欧式极线校正框架[J].光学精密工程, 2014, 22(7):1955-1961. LI Guo-dong, TIAN Guo-hui,WANG Hong-jun, et al. Euclidean epipolar rectification frame of weakly calibrated stereo pairs[J]. Optics and Precision Engineering, 2014, 22(7):1955-1961.
[10] 黄以君,刘伟军,赵吉宾. 一种基于三焦点张量的度量重建方法[J].仪器仪表学报,2009, 30(6):1307-1312. HUANG Yi-jun, LIU Wei-jun, ZHAO Ji-bin. Approach to metric reconstruction based on trifocal tensor[J]. Chinese Journal of Scientific Instrument, 2009, 30(6):1307-1312.
[11] GUERREIO J J, MUROLLO A C, SAGUES C. Localization and matching using the planar trifocal tensor with bearing-only data[J]. IEEE Transactions on Robotics, 2008, 24(2):494-501.
[12] LOPEZ-NICOLAS G, GUERRERO J J, SAGUES C. Visual control through the trifocal tensor for nonholonomic robots[J]. Robotics and Autonomous Systems, 2010, 58(2):216-226.
[13] KITT B, GEIGER A, LATEGAHN H. Visual odometry based on stereo image sequences with RANSAC-based outlier rejection scheme[C]//Intelligent Vehicles Symposium. La Jolla:IEEE, 2010:486-492.
[14] JIA B, CHEN J, ZHANG K. Adaptive visual trajectory tracking of nonholonomic mobile robots based on trifocal tensor[C]//2015 IEEE/RSJ International Conference on IEEE Intelligent Robots and Systems (IROS). Hamburg:IEEE, 2015:3695-3700.
[15] INDELMAN V, GURFIL P, RIBLIN E, et al. Real-time vision-aided localization and navigation based on three-view geometry[J]. IEEE Transactions on Aerospace and Electronic Systems, 2012, 48(3):2239-2259.
[16] KALAL Z, MIKOLAJCZYK K, MATAS J. Forward-backward error:automatic detection of tracking failures[C]//201020th International Conference on Pattern Recognition (ICPR). Istanbul:IEEE, 2010:2756-2759.
[17] 张跃强,苏昂,刘海波,等. 基于多直线对应和加权最小二乘的位姿估计[J].光学精密工程, 2015, 23(6):1722-1731. ZHANG Yue-qiang, SU Ang, LIU Hai-bo, et al. Pose estimation based on multiple line hypothesis and iteratively reweighted least squares[J]. Optics and Precision Engineering, 2015, 23(6):1722-1731.
[18] BAY H, TUYTELAARS T, VAN G L. Surf:speeded up robust features[C]//European Conference on Computer Vision. Graz:Springer, 2006:404-417.

[1] HAN Yong, NING Lian-ju, ZHENG Xiao-lin, LIN Wei-hua, SUN Zhong-yuan. Matrix factorization recommendation based on social information and item exposure[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2019, 53(1): 89-98.
[2] ZHENG Zhou, ZHANG Xue-chang, ZHENG Si-ming, SHI Yue-ding. Liver segmentation in CT images based on region-growing and unified level set method[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(12): 2382-2396.
[3] ZHAO Li-ke, ZHENG Shun-yi, WANG Xiao-nan, HUANG Xia. Rigid object position and orientation measurement based on monocular sequence[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(12): 2372-2381.
[4] HE Jie-guang, PENG Zhi-ping, CUI De-long, LI Qi-rui. Teaching-learning-based optimization algorithm with local dimension improvement[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(11): 2159-2170.
[5] LI Zhi, SHAN Hong, MA Tao, HUANG Jun. Group discovery of mobile terminal users based on reverse-label propagation algorithm[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(11): 2171-2179.
[6] WANG Shuo-peng, YANG Peng, SUN Hao. Construction process optimization of fingerprint database for auditory localization[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(10): 1973-1979.
[7] WEI Xiao-feng, CHENG Cheng-qi, CHEN Bo, WANG Hai-yan. Chain code based on independent edge number[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(9): 1686-1693.
[8] CHEN Rong-hua, WANG Ying-han, BU Jia-jun, YU Zhi, GAO Fei. Website accessibility sampling evaluation based on KNN and local regression[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(9): 1702-1708.
[9] ZHANG Cheng-zhi, FENG Hua-jun, XU Zhi-hai, LI Qi, CHEN Yue-ting. Piecewise noise variance estimation of images based on wavelet transform[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(9): 1804-1810.
[10] LIU Zhou-zhou, LI Shi-ning, LI Bin, WANG Hao, ZHANG Qian-yun, ZHENG Ran. New elastic collision optimization algorithm and its application in sensor cloud resource scheduling[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(8): 1431-1443.
[11] WANG Yong-chao, ZHU Kai-lin, WU Qi-xuan, LU Dong-ming. Adaptive display technology of high precision model based on local rendering[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(8): 1461-1466.
[12] SUN Nian, LI Yu-qiang, LIU Ai-hua, LIU Chun, LI Wei-wei. Microblog sentiment analysis based on collaborative learning under loose conditions[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(8): 1452-1460.
[13] ZHENG Shou-guo, CUI Yan-min, WANG Qing, YANG Fei, CHENG Liang. Design of field data acquisition platform for aircraft assembly[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(8): 1526-1534.
[14] BI Xiao-jun, WANG Chao. Many-objective evolutionary algorithm based on hyperplane projection[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(7): 1284-1293.
[15] ZHANG Ting-rong, TENG Qi-zhi, LI Zheng-ji, QING Lin-bo, HE Xiao-hai. Super-resolution reconstruction for three-dimensional core CT image[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(7): 1294-1301.