Measurement of Three-Dimensional Environment with a Fish-Eye Camera Based on Structure from Motion - Error Analysis

Kenji Terabayashi; Hisanori Mitsumoto; Toru Morita; Yohei Aragaki; Noriko Shimomura; Kazunori Umeda

doi:10.20965/jrm.2009.p0680

single-rb.php

« previous

JRM Vol.21 No.6 pp. 680-688

doi: 10.20965/jrm.2009.p0680

(2009)

Paper:

Views over last 60 days: 440

Measurement of Three-Dimensional Environment with a Fish-Eye Camera Based on Structure from Motion - Error Analysis

Kenji Terabayashi^,, Hisanori Mitsumoto^, Toru Morita^,
Yohei Aragaki^, Noriko Shimomura^, and Kazunori Umeda^,**

^*Dept. of Precision Mechanics, Faculty of Science and Engineering, Chuo University 1-13-27 Kasuga, Bunkyo-ku, Tokyo 112-8551, Japan

^**CREST Program, Japan Science and Technology Agency (JST)

^***Toyota Motor Corporation
375-1 Imazato, Susono, Shizuoka 410-1104, Japan

^****Nissan Motor Co.,Ltd. 1-1 Morinosatoaoyama, Atsugi-shi Kanagawa 243-0123, Japan

Received:

June 2, 2009

Accepted:

September 30, 2009

Published:

December 20, 2009

Keywords:

fish-eye, structure from motion, three dimensional measurement, error analysis

Abstract

This paper proposes a method for measuring 3-dimensional (3D) environment and estimating camera movement with two fish-eye images. This method deals with large distortion of images from a fish-eye camera to calibrate internal and external camera parameters precisely by simultaneous estimation. In this paper, we analyze 3D measurement accuracy based on a theoretical model and evaluate it in practical analysis in experimental and real environments. These analyses show that the theoretical measurement error model works over a wide range of fish-eye views.

Cite this article as:

K. Terabayashi, H. Mitsumoto, T. Morita, Y. Aragaki, N. Shimomura, and K. Umeda, “Measurement of Three-Dimensional Environment with a Fish-Eye Camera Based on Structure from Motion - Error Analysis,” J. Robot. Mechatron., Vol.21 No.6, pp. 680-688, 2009.

Data files:

References

[1] R. Bunschoten and B. Krose, “Robust scene reconstruction from an omnidirectional vision system,” IEEE Trans. on Robotics and Automation, 19, pp. 351-357, 2003.
[2] R. Kawanishi, A. Yamashita, and T. Kaneko, “Construction of 3D Environment Model from an Omni-Directional Image Sequence,” Proc. 3rd Asia Int. Symposium on Mechatronics (AISM2008), pp. 152-157, 2008.
[3] L. Shigang, “Monitoring Around a Vehicle by a Spherical Image Sensor,” IEEE Trans. on Intelligent Transportation Systems, 7, pp. 541-550, 2006.
[4] L. Shigang and Y. Shimomura, “Lane marking detection by side Fisheye Camera,” Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2008), pp. 606-611, 2008.
[5] S. Gehrig, C. Rabe, and L. Krueger, “6D Vision Goes Fisheye for Intersection Assistance,” Proc. of Canadian Conf. on Computer and Robot Vision (CRV2008), pp. 34-41, 2008.
[6] Nissan Motor Co. Ltd., http://www.nissan-global.com/EN/NEWS/2007/_STORY/071012-01-e.html
[7] T. Nishimoto and J. Yamaguchi, “Three dimensional measurement using fisheye stereo vision,” Proc. of SICE Annual Conf. 2007, pp. 2008-2012, 2007.
[8] D. Xiaoming, W. Fuchao, W. Yihong, and W. Chongwei, “Automatic spherical panorama generation with two fisheye images,” Proc. of 7th World Congress on Intelligent Control and Automation (WCICA2008), pp. 5955-5959, 2008.
[9] R. Okutsu, K. Terabayashi, Y. Aragaki, N. Shimomura, and K. Umeda, “Generation of Overhead View Images by Estimating Intrinsic and Extrinsic Camera Parameters of Multiple Fish-Eye Cameras,” Proc. of IAPR Conf. on Machine Vision Applications (MVA2009), 2009.
[10] B. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon, “Bundle Adjustment -A Modern Synthesis,” Vision Algorithms: Theory & Practice, Springer-Verlag LNSC 1883, 2000.
[11] J. Y. Bouguet, “Pyramidal Implementation of the Lucas Kanade Feature Tracker Description of the Algorithm,” OpenCV, Intel Corporation, 2000.
[12] D. G. Lowe, “Object Recognition from Local Scale Invariant Features,” Proc. of IEEE Int. Conf. on Computer Vision (ICCV), pp. 1150-1157, 1999.
[13] W. H. Press, S. A. Teukolsky, W. T. Vetterling, et al., “Numerical Recipes in C," Cambridge University Press, Cambridge, pp. 408-412, 1992.
[14] R. I. Hartley, “In Defense of the Eight-Point Algorithm,” IEEE Trans. on Pattern Analysis and Machine intelligence, Vol.19, No.6, pp. 580-593, 1997.
[15] M. A. Fischler and R. C. Bolles, “Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography,” Communications of the ACM, Vol.24, No.6, pp. 381-395, 1981.
[16] J. Kannala and S. S. Brandt, “A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses,” Vol.28, No.8, pp. 1335-1340, 2006.

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

[1] [1] R. Bunschoten and B. Krose, “Robust scene reconstruction from an omnidirectional vision system,” IEEE Trans. on Robotics and Automation, 19, pp. 351-357, 2003.

[2] [2] R. Kawanishi, A. Yamashita, and T. Kaneko, “Construction of 3D Environment Model from an Omni-Directional Image Sequence,” Proc. 3rd Asia Int. Symposium on Mechatronics (AISM2008), pp. 152-157, 2008.

[3] [3] L. Shigang, “Monitoring Around a Vehicle by a Spherical Image Sensor,” IEEE Trans. on Intelligent Transportation Systems, 7, pp. 541-550, 2006.

[4] [4] L. Shigang and Y. Shimomura, “Lane marking detection by side Fisheye Camera,” Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS2008), pp. 606-611, 2008.

[5] [5] S. Gehrig, C. Rabe, and L. Krueger, “6D Vision Goes Fisheye for Intersection Assistance,” Proc. of Canadian Conf. on Computer and Robot Vision (CRV2008), pp. 34-41, 2008.

[6] [6] Nissan Motor Co. Ltd., http://www.nissan-global.com/EN/NEWS/2007/_STORY/071012-01-e.html

[7] [7] T. Nishimoto and J. Yamaguchi, “Three dimensional measurement using fisheye stereo vision,” Proc. of SICE Annual Conf. 2007, pp. 2008-2012, 2007.

[8] [8] D. Xiaoming, W. Fuchao, W. Yihong, and W. Chongwei, “Automatic spherical panorama generation with two fisheye images,” Proc. of 7th World Congress on Intelligent Control and Automation (WCICA2008), pp. 5955-5959, 2008.

[9] [9] R. Okutsu, K. Terabayashi, Y. Aragaki, N. Shimomura, and K. Umeda, “Generation of Overhead View Images by Estimating Intrinsic and Extrinsic Camera Parameters of Multiple Fish-Eye Cameras,” Proc. of IAPR Conf. on Machine Vision Applications (MVA2009), 2009.

[10] [10] B. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon, “Bundle Adjustment -A Modern Synthesis,” Vision Algorithms: Theory & Practice, Springer-Verlag LNSC 1883, 2000.

[11] [11] J. Y. Bouguet, “Pyramidal Implementation of the Lucas Kanade Feature Tracker Description of the Algorithm,” OpenCV, Intel Corporation, 2000.

[12] [12] D. G. Lowe, “Object Recognition from Local Scale Invariant Features,” Proc. of IEEE Int. Conf. on Computer Vision (ICCV), pp. 1150-1157, 1999.

[13] [13] W. H. Press, S. A. Teukolsky, W. T. Vetterling, et al., “Numerical Recipes in C," Cambridge University Press, Cambridge, pp. 408-412, 1992.

[14] [14] R. I. Hartley, “In Defense of the Eight-Point Algorithm,” IEEE Trans. on Pattern Analysis and Machine intelligence, Vol.19, No.6, pp. 580-593, 1997.

[15] [15] M. A. Fischler and R. C. Bolles, “Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography,” Communications of the ACM, Vol.24, No.6, pp. 381-395, 1981.

[16] [16] J. Kannala and S. S. Brandt, “A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses,” Vol.28, No.8, pp. 1335-1340, 2006.

Measurement of Three-Dimensional Environment with a Fish-Eye Camera Based on Structure from Motion - Error Analysis

Kenji Terabayashi*,**, Hisanori Mitsumoto***, Toru Morita*, Yohei Aragaki****, Noriko Shimomura****, and Kazunori Umeda*,**

Kenji Terabayashi^,, Hisanori Mitsumoto^, Toru Morita^,
Yohei Aragaki^, Noriko Shimomura^, and Kazunori Umeda^,**