3D reconstruction of premises using the binocular vision system

Authors: Bai Caiyan
Published in issue: #6(35)/2019
DOI: 10.18698/2541-8009-2019-6-491
Category: Mechanical Engineering and Machine Science | Chapter: Robots, Mechatronics, and Robotic Systems
Keywords: binocular vision system, camera calibration, image attribute, plane image description, 3D reconstruction
Published: 19.06.2019

In this paper, the author considered the task of the reconstructing 3D space using a binocular vision system that located on a mobile robot. To calibrate the binocular vision system, a simple plane-level calibration method with high accuracy was used. After calibration and elimination of the distortions, the images are segmented to detect edges and highlight characteristic points. Based on the analysis of pairs of the typical points on the images of the left and right cameras, their spatial coordinates are calculated. The author used the method of least squares to describe the fragments of the room — local planes. Using the obtained fragments, a reconstruction of 3D surrounding space was performed. The author verified the obtained results experimentally.

References

[1] Volodin Yu.S. Televizionnaya sistema ob’’emnogo zreniya dlya upravleniya dvizheniem mobil’nogo robota. Avtoref. diss. kand. tekh. nauk [Television system of stereoscopic vision for control on mobile robot movement. Abs. kand. tech. sci. diss.]. Moscow, 2011 (in Russ.).

[2] Shapiro L.G., Stockman G.C. Computer vision. Pearson, 2001. (Russ. ed.: Komp’yuternoe zrenie. Moscow, Binom. Laboratoriya znaniy Publ., 2006.)

[3] Bay Tsayyan’. Mobile robot indoor map building and localization using binocular vision. Politekhnicheskiy molodezhnyy zhurnal [Politechnical student journal], 2018, no. 11. DOI: 10.18698/2541-8009-2018-11-405 URL: http://ptsj.ru/catalog/menms/robots/405.html (in Russ.).

[4] Mikhaylov B.B. [Using technical vision systems for control on mobile robots]. 10 Vseross. Mul’tikonf. po problemam upravleniya [10th Russ. Conf. on Control Problems]. Rostov-na-Donu, Tagarog, SFeDU Publ., 2017, pp. 230–232 (in Russ.).

[5] Dunn P.F., Davis M.P. Measurement and data analysis for engineering and science. McGraw Hill, 2005.

[6] Zhang Z. Flexible camera calibration by viewing a plane from unknown orientations. Proc. 7th IEEE Int. Conf. Computer Vision, 1999 pp. 666–673. DOI: 10.1109/ICCV.1999.791289 URL: https://ieeexplore.ieee.org/document/791289

[7] Zhang Z. A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell., 2000, vol. 22, no. 11, pp. 1330–1334. DOI: 10.1109/34.888718 URL: https://ieeexplore.ieee.org/document/888718

[8] Gonzalez R.C., Woods R.E., Eddins S.L. Digital image processing. Prentice-Hall, 2002.

[9] Kirschvink J.L. The least-squares line and plane and the analysis of palaeomagnetic data. Geophys. J. Int., 1980, vol. 62, no. 3, pp. 699–718. DOI: 10.1111/j.1365-246X.1980.tb02601.x URL: https://academic.oup.com/gji/article/62/3/699/655282

[10] Eberly D. Least squares fitting of data by linear or quadratic structures. URL: https://www.geometrictools.com/Documentation/LeastSquaresFitting.pdf (accessed: 15.04.2019).