Algorithms for constructing 3d images of objects in problems of underwater robotics

B.A. Skorohod, P.V. Zhiyakov, A.V. Statsenko, S.I. Fateev

Sevastopol State University, RF, Sevastopol, Universitetskaya St., 33

E-mail: boris.skorohod@mail.ru, yany@mail.ru, lex00x1@mail.ru, fateev-si@ya.ru

DOI: 10.33075/2220-5861-2020-4-101-110

UDC 004.9:004.41

Abstract:

   Currently, intensive research is underway to develop remotely controlled and autonomous underwater robots that use technical vision systems. Typical examples of tasks that can be solved using them are: monitoring the environment; detecting objects and obstacles; approaching the robot to the object; performing operations with objects. This article focuses on the problems of constructing images of the workspace of an underwater robot designed to perform operations with objects based on information received from a stereo camera installed on it. A new approach to analyzing the accuracy of constructed 3D coordinates of its workspace is proposed. Its important feature is the ability to evaluate the impact of all sources of disturbances in the aggregate, including the design of a waterproof shell, based only on experimental data obtained in the underwater environment. In addition, the same approach can also be used to estimate the position of camera image centers, allowing for the presence of a waterproof shell to be taken into account for improved accuracy in image processing algorithms. Robust algorithms for constructing 3D images of the robot’s working space based on a perspective camera model and the joint use of triangulation and clustering methods are proposed and tested on real data.

Keywords: underwater robots, stereo vision, perspective camera model, 3D reconstruction of the working
space of an underwater robot, clustering.

Full text in PDF(RUS)

LIST OF REFERENCES

  1. Dario L., Kallasi F., Aleotti J., Oleari F. and Caselli S. Underwater vehicle for pipe manipulation tasks // Computers & Electrical Engineering. 2017. Vol. 58 February. P. 560–571.
  2. Bonin F., Burguera A., Oliver G. Imaging Systems for Advanced Underwater // Vehicles Journal od Maritime Research. 2011. Vol. VIII (1). P. 65–86.
  3. Dolin L. S., Levin I. M. Theory of underwater visibility / / Fundamental and applied Hydrophysics. 2015. Т. 8, № 2. P. 22–35.
  4. Schechner Y., Karpel N. Clear underwater vision // In Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA, 27 June–2 July 2004. P. 536–543.
  5. Drap P., Seinturier J., Scaradozzi D. Photogrammetry for virtual exploration of underwater archeological sites // In Proceedings of the 21st International Symposium, CIPA 2007: AntiCIPAting the Future of the Cultural Past, Athens, Greece, 1–6 October 2007. P. 1–6.
  6. Analysis of the accuracy of constructing 3d coordinates of the working space of an underwater robot / B. A. Skorokhod, P. S. Zhilyakov, A.V. Statsenko [et al.] / / environmental control Systems. 2020. No. 3 (41). Р. 163-170.
  7. Skorokhod B. A., Statsenko A.V., Fateev S. I. Influence of preprocessing and algorithms for selecting key points in the problem of simultaneous 3d reconstruction of underwater objects and construction of the camera trajectory. 2019. No. 2 (36). P. 30-36.
  8. Hartley R., Zisserman A. Multiple View Geometry in Computer Vision. Cambridge University Press, 2003. Computers. 655 p.
  9. Szeliski R. Computer Vision. Springer, 2010. 655 p.
  10. Statsenko A.V., Fateev S. I. Program for finding pairs of corresponding points on underwater images / / Certificate of state registration of the computer program No. 2019663217. Applicant and copyright holder of Sevastopol state University (RU). no. 2019661991; Publ. 11.10.2019. Register of computer programs. 1 p.
  11. Vorontsov K. V. algorithms for clustering and multidimensional scaling. Moscow: MSU, 2007.
  12. Ester M. A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise / M. Ester, H.-P. Kriegel, J. Sander, X. Xu // Third AAAI Conference on Human Computation and Crowdsourcing. 2015.
  13. Arthur D., Vassilvitskii S. k-means++: The Advantages of Careful Seeding // SODA ’07: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms. New Orleans, LA, January 2007. P. 1027–1035.
  14. Torr P.H.S., Zisserman A. MLESAC: A New Robust Estimator with Application to Estimating Image Geometry // Computer Vision and Image Understanding. 2000.

 

If you have found a spelling error, please, notify us by selecting that text and pressing Ctrl+Enter.

Translate »

Spelling error report

The following text will be sent to our editors: