Algorithm for determining the distance to the nearest work object

Authors: Cabrera Pantoha Jose Jesus
Published in issue: #1(42)/2020
DOI: 10.18698/2541-8009-2020-1-572
Category: Mechanical Engineering and Machine Science | Chapter: Robots, Mechatronics, and Robotic Systems
Keywords: mobile robot, work object, television camera, image specific points, distance calculation, Harris detector, FAST detector, algorithm, computer vision
Published: 03.02.2020

The paper considers the problem of determining the distance to the nearest of the objects located in the work area using a single camera, which is located on a mobile robot. The distance is calculated based on the analysis of the displacement of the specific points of the object in two successive images obtained from the camera. The ORB, FAST, and Harris detectors were used to isolate specific points, and the Lucas and Kenned method was used to track their displacement. The performance of the proposed algorithm was verified using simulation and a full-scale experiment. A proven algorithm has two solutions. The experiments showed that this algorithm allows one to calculate the distance to the nearest object with acceptable accuracy.

References

[1] Alizadeh P., Zeinali M. A real-time object distance measurement using a monocular camera. Proc. IASTED Int. Conf. Modelling, Simulation and Optimatization, 2013. DOI: http://dx.doi.org/10.2316/P.2013.802-048

[2] Kim I., Yow K.Ch. Object location estimation from a single flying camera. UBICOMM, 2015, pp. 82–88.

[3] Bay Ts. Mobile robot indoor map building and localization using binocular vision. Politekhnicheskiy molodezhnyy zhurnal [Politechnical student journal], 2018, no. 11. DOI: http://dx.doi.org/10.18698/2541-8009-2018-11-405 (in Russ.).

[4] Sánchez J., Monzón N., Salgado A. An analysis and implementation of the Harris corner. IPOL, 2018, no. 8, pp. 305–328. DOI: https://doi.org/10.5201/ipol.2018.229

[5] Rublee E., Rabaud V., Konolige K., et al. ORB: and efficient alternative to SIFT or SURF. IEEE ICCV, 2011, pp. 2564–2571. DOI: https://doi.org/10.1109/ICCV.2011.6126544

[6] Rosten E., Drummond T. Fusing points and lines for high performance tracking. 10th IEEE ICCV, 2005, vol. 1, pp 1508–1515. DOI: https://doi.org/10.1109/ICCV.2005.104

[7] Konushin A. Point feature tracking. Komp’yuternaya grafika i mul’timedia, 2003, no. 1(5) (in Russ.). URL: https://docplayer.ru/52828701-Slezhenie-za-tochechnymi-osobennostyami-sceny-point-feature-tracking.html (accessed: 12.09.2019).

[8] Gaganov V. Invariant match algorithms for point features of the images. Komp’yuternaya grafika i mul’timedia, 2009, no. 7(1) (in Russ.). URL: http://masters.donntu.org/2012/iii/chigarev/library/article3.htm (accessed: 12.09.2019).

[9] Corke P. Robotics, vision and control. Fundamental algorithms in MATLAB. Springer, 2013.

[10] Vorotnikov S.A. Informatsionnye ustroystva robototekhnicheskikh system [Information devices of robotic systems]. Moscow, Bauman MSTU Publ., 2005 (in Russ.).