A Method on Monocular Vision of Camera for Spatial Position

Abstract:

In this paper, a method on monocular vision for spatial position is presented. The geometric model of digital camera is built and decomposed to intrinsic and extrinsic parameter matrixes under a certain assumption. Firstly, the intrinsic parameter matrix of camera is determined. Then, the extrinsic parameter matrix is solved according to the information of image. The edge detection operators are worked and in order to detect the accuracy of this method, the point of some feature points are obtained by using the principle of least squares. Compared with the conventional calibration method, this method is simple, fast and robust.

• Periodical: Applied Mechanics and Materials (Volume 281)
• Pages: 14-18
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.281.14
• Online since: January 2013
• Authors: Zhen Yang, Ming Jun Wu, Fang Wang, Li Zhang, Li Na Gong
• Keywords: Canny Operator, Extrinsic Parameter Matrix, Intrinsic Parameter Matrix, Principle of Least Squares

References

[1] Guo Lei, Xu You chun, Li Ke qiang, et al. Study on Real-Time Distance Detection Based on Monocular Vision Technique. Journal of Image and Graphics, 2006, 11(1): 74~81.

[2] Qu Yan cheng, Huang Heng jun, Wang Chang hong. Research on Vision-Based Localization Method of Mobile Robot Formation. Computer Engineering and Applications, 2005, 41(26): 66~68.

[3] Zhang Guang jun, Zhou Fu qiang. Position and Orientation Estimation Method for Landing of Unmanned Aerial Vehicle with Two Circle Based Computer Vision. Acta Aeronautica et Astronautica Sinica, 2005, 26 (3): 344 ~ 348.

[4] Liu Bing ru, Xie Yun, Yang Yi min, et al. A Self-Localization Method with Monocular Vision for Autonomous Soccer Robot. IEEE International Conference on Industrial Technology, 2005, 888~892.

DOI: 10.1109/icit.2005.1600761

[5] Omar Ait Aider, Philippe Hoppenot, Etienne Colle. A model-based method for indoor mobile robot localization using monocular vision and straight-line correspondences[J]. Robotics and Autonomous Systems, 2005, (52): 229-246.

DOI: 10.1016/j.robot.2005.03.002

[6] Rorer E, Lhuillier M. Monocular vision for mobile robot localization and autonomous navigation[J]. International Journal of Computer Vision, 2007, 74(3): 237-260.

DOI: 10.1007/s11263-006-0023-y

[7] Saxena A, Sun Min, Ng A Y. Make 3D: Learning 3D scene structure from a single still image[J]. Transactions on Pattern Analysis and Machine Intelligence, 2009, 5: 824-840.

DOI: 10.1109/tpami.2008.132

[8] Sasa S, Gomi H, Ninomiya T, et al. Position and Attitude Estimation Using Image Processing of Runway. AIAA: Aerospace Sciences Meeting and Exhibit, 38th, Reno, NV, Jan, 2000, 10~13.

DOI: 10.2514/6.2000-301

[9] Zhu Shi ping, Qiang Xi fu. Study on Monocular Vision Method Used for Camera Positioning. Acta Optica Sinica, 2001, 21(3): 339~34.

[10] Liang G, Zha H, Liu H. Affine Correspondence Based Head Pose Estimation for a Sequence of Images by Using a 3D Model. Proceedings of IEEE 6th International Conference on Automatic Face and Gesture Recognition (FG 2004). 2004, 632~637.

DOI: 10.1109/afgr.2004.1301604