On improved calibration method for the catadioptric omnidirectional vision with a single viewpoint
- 88 Downloads
Abstract
The single viewpoint constraint is a principal optical characteristic for most catadioptric omnidirectional vision. Single viewpoint catadioptric omnidirectional vision is very useful because it allows the generation of geometrically correct perspective images from one omnidirectional image. Therefore precise calibration for single viewpoint constraint is needed during system assembling. However, in most image detection based calibration methods, the nonlinear optical distortion brought by lens is often neglected. Hence the calibration precision is poor. In this paper, a new calibration method of single viewpoint constraint for the catadioptric omni-directional vision is proposed. Firstly, an image correction algorithm is obtained by training a neural network. Then, according to characteristics of the space circular perspective projection, the corrected image of the mirror boundary is used to estimate its position and attitude relative to the camera to guide the calibration. Since the estimate is conducted based on actual imaging model rather than the simplified model, the estimate error is largely reduced, and the calibration accuracy is significantly improved. Experiments are conducted on simulated images and real images to show the accuracy and the effectiveness of the proposed method.
Keywords
Catadioptric omnidirectional vision Single viewpoint constraint Perspective projection Neural networkAbbreviations
- SVC
Single viewpoint constraint
- COV
Catadioptric omnidirectional vision
- NN
Neural network
References
- 1.Aliaga DG (2001) Accurate catadioptric calibration for real-time pose estimation of room size environments. Proc. of IEEE International conference on computer vision, I, pp 127–134Google Scholar
- 2.Baker S, Nayer S (1999) A theory of single-viewpoint catadioptric image formation. Int J Comput Vis 35(2):175–196CrossRefGoogle Scholar
- 3.Barreto JP, Araujo H (2005) Geometric properties of central catadioptric line images and their application in calibration. IEEE Trans Pattern Anal Mach Intell 27(8):1237–1333CrossRefGoogle Scholar
- 4.Davison A, Reid NI (2007) MonoSLAM: real-time single camera SLAM. IEEE Trans Pattern Anal Mach Intell 29(6):1052–1067CrossRefGoogle Scholar
- 5.Deng X-M, Wu F-C (2007) An easy calibration method for central catadioptric cameras. Acta automatica sinica 33(8):801–808Google Scholar
- 6.Geyere C, Daniilidis K (2001) Structure and motion from uncalibrated catadioptric views CVPR, I, pp 279–286Google Scholar
- 7.Ishiguro H, Ng KC, Capella R (2003) Omni-directional image-based modeling: three approaches to approximated plenoptic representations. Mach Vis Appl 14(2):94–102Google Scholar
- 8.Jeng S-W, Tsai W-H (2008) Analytic image unwarping by a systematic calibration method for omni-directional cameras with hyperbolic-shaped mirrors. Image Vis Comput 26:690–701CrossRefGoogle Scholar
- 9.Kang SB (2000) Catadioptric self-calibration. Proc. of IEEE Conference on Computer Vision and Patten Recognition pp 201–207Google Scholar
- 10.Mashita T, Iwai Y (2006) Calibration method for misaligned catadioptric camera Vol. E89-D, pp 1984–1993Google Scholar
- 11.Nagahara H, Yagi Y, Yachida M (2003) Super-resolution modeling using an omnidirectional image sensor. IEEE Trans Syst Man Cybern, Part B 33(4):607–615CrossRefGoogle Scholar
- 12.Scaramuzza D, Martinelli A, Siegwart R (2006) A flexible technique for accurate omnidirectional camera calibration and structure from motion. In Proc. of the IEEE International Conference on Vision Systems, New YorkGoogle Scholar
- 13.Spacek L, Burbridge C (2007) Instantaneous robot self-localization and motion estimation with omnidirectional vision. Robot Auton Syst 55(9):667–674CrossRefGoogle Scholar
- 14.Yagi Y, Kawato S (1994) Real-time omni-directional image sensor for vision-guided navigation. IEEE Trans Robot Autom 10(2):11–22CrossRefGoogle Scholar