摄像机在线标定问题研究综述
|
摘要
摄像机标定技术作为三维信息获取的一个关键步骤备受重视,近年来在智能机器人、航拍、医学影像等领域都有着广泛应用。针对目前离线进行的标定在环境改变导致摄像机参数发生变化时,必须重新进行标定的问题,对现有的在线进行的标定方法进行了探讨。首先,回顾了摄像机标定技术的发展情况,阐述了传统的摄像机离线标定法及其改进方法;然后,着重对在线标定的研究思路和方法进行了综述,论述了自标定与三维跟踪两种常见的在线标定方法,介绍了在线标定的意义即可以使摄像机在实际应用时实时更新标定参数;最后,总结了这两种方法在应用上的优缺点和摄像机标定未来的发展趋势。
As a key step of 3D information acquisition, the technology of camera calibration has drawn more and more attention. In recent years, it has been widely applied in the field of intelligent robot, aerial photography, medical imaging and so on. To solve the problem that the camera parameters change with the environmental transformation and deserve recalibrated in off-line calibration, the existing online calibration methods were discussed. First of all, the development of camera calibration technology was reviewed, and the traditional camera calibration methods and their improvements were expounded.Then, the research ideas and methods of online calibration were emphatically discussed. Two common online calibration methods, self-calibration and three-dimensional tracking were introduced. The meaning of online calibration is to make the camera update the calibration parameters in real-time. Finally, the advantages and disadvantages of these two methods as well as the future development trend of camera calibration were also summarized.
As a key step of 3D information acquisition, the technology of camera calibration has drawn more and more attention. In recent years, it has been widely applied in the field of intelligent robot, aerial photography, medical imaging and so on. To solve the problem that the camera parameters change with the environmental transformation and deserve recalibrated in off-line calibration, the existing online calibration methods were discussed. First of all, the development of camera calibration technology was reviewed, and the traditional camera calibration methods and their improvements were expounded.Then, the research ideas and methods of online calibration were emphatically discussed. Two common online calibration methods, self-calibration and three-dimensional tracking were introduced. The meaning of online calibration is to make the camera update the calibration parameters in real-time. Finally, the advantages and disadvantages of these two methods as well as the future development trend of camera calibration were also summarized.
引文
[1]徐德,谭民,李原.机器人视觉测量与控制[M].北京:国防工业出版社, 2016:35-80.
[2] ABDEL-AZIZ Y I, KARARA H M, HAUCK M. Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry[J]. Photogrammetric Engineering&Remote Sensing, 2015, 81(2):103-107.
[3] TSAI R Y. A versatile camera calibration technique for high-accuracy3D machine vision metrology using off-the-shelf cameras and lens[J].IEEE Journal on Robotics and Automation, 1987, 3(4):323-344.
[4] ZHANG Z. Flexible camera calibration by viewing a plane from unknown orientations[C]//Proceedings of the 7th IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2002, 1:666-673.
[5] ZHAO Z, YE D, ZHANG X, et al. Improved direct linear transformation for parameter decoupling in camera calibration[J]. Algorithms, 2016, 9(2):1-15.
[6]花开胜,王林.基于平面模板的摄像机标定方法[J].计算机工程, 2012, 38(15):264-267.
[7] LU J. Performing improved two-step camera calibration with weighted total least-squares[J]. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences,2012, 39:141-146.
[8] ABDERRAHMANI A E, SATORI K. Camera self-calibration with varying intrinsic parameters and arc of the circle[C]//Proceedings of the 2016 International Journal of Advanced Computer Science and Applications. Piscataway, NJ:IEEE, 2016:1309-1314.
[9] AKKAD N E, MMRRAS M, SAAIDI A, et al. Camera self-calibration with varying intrinsic parameters by an unknown three-dimensional scene[J]. Visual Computer, 2014, 30(5):519-530.
[10] LI B, PENG K, YING X, et al. Simultaneous vanishing point detection and camera calibration from single images[C]//Proceedings of the 2010 International Conference on Advances in Visual Computing,LNCS 6454. Berlin:Springer, 2010:151-160.
[11] BOUDINE B, KRAMM S, AKKADN E, et al. A flexible technique based on fundamental matrix for camera self-calibration with variable intrinsic parameters from two views[J]. Journal of Visual Communication&Image Representation, 2016, 39(C):40-50.
[12]罗安宁.基于机器视觉的道路检测算法[D].北京:清华大学,2014:9-29.
[13]刘毛毛.基于机器视觉的运动目标实时跟踪算法研究[D].太原:中北大学, 2015. 1-28.
[14] CHOI C, CHRISTENSEN H I. Real-time 3D model-based tracking using edge and keypoint features for robotic manipulation[C]//Proceedings of the 2010 International Conference on Robotics and Automation. Piscataway, NJ:IEEE, 2010:4048-4055.
[15] CHOI C, BAEK S M, LEE S. Real-time 3D object pose estimation and tracking for natural landmark based visual servo[C]//Proceedings of the 2008 International Conference on Intelligent Robots and Systems. Piscataway, NJ:IEEE, 2008:3983-3989.
[16] KRINIDIS M, NIKOLAIDIS N, PITAS I. Feature-based tracking using 3D physics-based deformable surfaces[C]//Proceedings of the 2005 13th European Signal Processing Conference. Piscataway,NJ:IEEE, 2005:1-4
[17] ALZAROK H, FLETCHER S, LONGSTAFF A P. 3D visual tracking of an articulated robot in precision automated tasks[J]. Sensors, 2017, 17(1):104.
[18] PAUWELS K, RUBIO L, DIA Z, et al. Real-time model-based rigid object pose estimation and tracking combining dense and sparse visual cues[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:2347-2354.
[19] HOUSSINEAU J, CLARK D E, IVEKOVIC S, et al. A unified approach for multi-object triangulation, tracking and camera calibration[J]. IEEE Transactions on Signal Processing, 2016, 64(11):2934-2948.
[2] ABDEL-AZIZ Y I, KARARA H M, HAUCK M. Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry[J]. Photogrammetric Engineering&Remote Sensing, 2015, 81(2):103-107.
[3] TSAI R Y. A versatile camera calibration technique for high-accuracy3D machine vision metrology using off-the-shelf cameras and lens[J].IEEE Journal on Robotics and Automation, 1987, 3(4):323-344.
[4] ZHANG Z. Flexible camera calibration by viewing a plane from unknown orientations[C]//Proceedings of the 7th IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2002, 1:666-673.
[5] ZHAO Z, YE D, ZHANG X, et al. Improved direct linear transformation for parameter decoupling in camera calibration[J]. Algorithms, 2016, 9(2):1-15.
[6]花开胜,王林.基于平面模板的摄像机标定方法[J].计算机工程, 2012, 38(15):264-267.
[7] LU J. Performing improved two-step camera calibration with weighted total least-squares[J]. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences,2012, 39:141-146.
[8] ABDERRAHMANI A E, SATORI K. Camera self-calibration with varying intrinsic parameters and arc of the circle[C]//Proceedings of the 2016 International Journal of Advanced Computer Science and Applications. Piscataway, NJ:IEEE, 2016:1309-1314.
[9] AKKAD N E, MMRRAS M, SAAIDI A, et al. Camera self-calibration with varying intrinsic parameters by an unknown three-dimensional scene[J]. Visual Computer, 2014, 30(5):519-530.
[10] LI B, PENG K, YING X, et al. Simultaneous vanishing point detection and camera calibration from single images[C]//Proceedings of the 2010 International Conference on Advances in Visual Computing,LNCS 6454. Berlin:Springer, 2010:151-160.
[11] BOUDINE B, KRAMM S, AKKADN E, et al. A flexible technique based on fundamental matrix for camera self-calibration with variable intrinsic parameters from two views[J]. Journal of Visual Communication&Image Representation, 2016, 39(C):40-50.
[12]罗安宁.基于机器视觉的道路检测算法[D].北京:清华大学,2014:9-29.
[13]刘毛毛.基于机器视觉的运动目标实时跟踪算法研究[D].太原:中北大学, 2015. 1-28.
[14] CHOI C, CHRISTENSEN H I. Real-time 3D model-based tracking using edge and keypoint features for robotic manipulation[C]//Proceedings of the 2010 International Conference on Robotics and Automation. Piscataway, NJ:IEEE, 2010:4048-4055.
[15] CHOI C, BAEK S M, LEE S. Real-time 3D object pose estimation and tracking for natural landmark based visual servo[C]//Proceedings of the 2008 International Conference on Intelligent Robots and Systems. Piscataway, NJ:IEEE, 2008:3983-3989.
[16] KRINIDIS M, NIKOLAIDIS N, PITAS I. Feature-based tracking using 3D physics-based deformable surfaces[C]//Proceedings of the 2005 13th European Signal Processing Conference. Piscataway,NJ:IEEE, 2005:1-4
[17] ALZAROK H, FLETCHER S, LONGSTAFF A P. 3D visual tracking of an articulated robot in precision automated tasks[J]. Sensors, 2017, 17(1):104.
[18] PAUWELS K, RUBIO L, DIA Z, et al. Real-time model-based rigid object pose estimation and tracking combining dense and sparse visual cues[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:2347-2354.
[19] HOUSSINEAU J, CLARK D E, IVEKOVIC S, et al. A unified approach for multi-object triangulation, tracking and camera calibration[J]. IEEE Transactions on Signal Processing, 2016, 64(11):2934-2948.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |