SELECTION OF PLANE OBJECTS IN LINEAR-STRUCTURED 3D-IMAGES

V.P. Noskov
PhD in Technical Sciences, Bauman Moscow State Technical University (BMSTU), Head of Sector Scientific Research Institute of Special Machine Building, Assistant Professor, 5, 2-ya Baumanskaya ul., Moscow, 105005, Russia, tel.: +7(916)676-60-57, This email address is being protected from spambots. You need JavaScript enabled to view it.

I.O. Kiselev
BMSTU, Postgraduate Student, 5, 2-ya Baumanskaya ul., Moscow, 105005, Russia, tel.: +7(965)212-43-89, This email address is being protected from spambots. You need JavaScript enabled to view it.

Received 10 May 2018

Abstract
The actual problem of 3D reconstruction of the industrial-urban environment model solved by the selection of linear objects (lines and planes) in stadiametric 3D images is considered. The analysis of the known methods and algorithms of plane objects selection from the point cloud is carried out and the method is proposed, which is based on a two-stage transformation of the initial data taking into account their linear structuring. Performance of the proposed approach is compared with the famous ones. The effectiveness of the proposed algorithm is confirmed by the experiment.
This work is supported by the Russian Foundation for Basic Research (grant no.16-29-04178офи_м).

Key words
Industrial-urban environment, long-range 3D images, linear primitives, Hough Transform, geometrical model, semantic model, navigation.

Bibliographic description
Noskov, V. and Kiselev, I. (2018). Selection of plane objects in linear-structured 3D-images. Robotics and Technical Cybernetics, 2(19), pp.31-38.

UDC identifier:
004.932.2:007.52

References

1. Lapshov, V., Noskov, V., Rubzov, I., Rudianov, N., Ryabov, A. and Khrushev, V. (2011). Battle in the town. Battle and supporting robots are in urbanized conditions. Izestiya SFedU. Engineering sciences, 3, pp.142-146. (in Russian).
2. Kalyaev, A. and et al. (1990). Odnorodnye upravlyayushchie struktury adaptivnykh robotov [Homogeneous Control Structures of Adaptive Robots]. Moscow: Nauka Publ., p.147. (in Russian).
3. Noskov, A. and Noskov, V. (2001). Raspoznavanie orientirov v dal'nometricheskikh izobrazheniyakh [Landmarks recognition in long-range images]. In: Mobil'nye roboty i mekhatronnye sistemy [Mobile Robots and Mechatronic Systems]. Moscow: MSU Publ., pp.179-192. (in Russian).
4. Lakota, N. and et al. (2000). Opyt ispol'zovaniya elementov iskusstvennogo intellekta v sisteme upravleniya tsekhovogo transportnogo robota [Experience of AI elements application in control system of workshop transport robot]. Mekhatronika [Mechtronics], 4, pp.44-47. (in Russian).
5. Noskov, V. and Rubtsov, I. (2005). Opyt resheniya zadachi avtonomnogo upravleniya dvizheniem mobil'nykh robotov [Experience of problem solving for independent control of mobile robot motion]. Mechatronics, Automation, Control, 12, pp.21-24. (in Russian).
6. Segal, A., Haehnel, D. and Thrun, S. (2009). Generalized-ICP. In: Proceedings of Robotics: Science and Systems, RSS.
7. Mitra, N. and et al. (2004). Registration of Point Cloud Data from a Geometric Optimization Perspective. In: Proceedings of the 2004 Eurographics/ACM SIGGRAPH symposium on Geometry processing. pp.22-31.
8. Kazmin, V. and Noskov, V. (2015). Detecting geometric and semantic objects in range image for robot navigation and environment reconstruction. Izestiya SFedU. Engineering sciences, 10(171), pp.71-83. (in Russian).
9. Konouchine, A., Gaganov, V. and Veznevets, V. (2005). AMLESAC: A New Maximum Likelihood Robust Estimator. In: International Conference Graphicon. [online] Available at: http://www.graphicon.ru/html/2005/proceedings/papers/konouchin.pdf [Accessed 6 Apr. 2018].
10. Klasing, K. and et al. (2009). Comparison of Surface Normal Estimation Methods for Range Sensing Applications. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).
11. Holz, D. and et al. (2011). Real-Time Plane Segmentation using RGBD Cameras. In: Proceedings of the 15th RoboCup International Symposium.
12. Comaniciu, D. and Meer, P. (2002). Mean Shift: A Robust Approach Toward Feature Space Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence – PAMI, 24(5), pp.603-619.
13. Berkmann, J. and Caelli, T. (1994). Computation of Surface Geometry and Segmentation Using Covariance Techniques. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 16(11), pp.1114-1116.
14. Niloy, J., Nguyen, M. and Nguyen, A. (2003). Estimating surface normals in noisy point cloud data. In: Proc. of The 19th ACM Symposium on Computational Geometry (SCG). pp.322-328.
15. Velizhev, A. and et al. (2009). Avtomaticheskaya segmentatsiya oblakov tochek na osnove elementov poverkhnosti [Automatic segmentation of point clouds based on surface elements]. In: Proceedings of GraphiCon – 2009. pp.241-245. (in Russian).
16. Sedlacek, D. and Zara, J. (2009). Graph cut based point-cloud segmentation for polygonal reconstruction. In: Proceedings of International Symposium on Visual Computing. pp.218-227.
17. Hough, P. (1962). Method and means for recognizing complex patterns. US 3069654.
18. Borrmann, D. and et al. (2011). The 3D hough transform for plane detection in point clouds: A review and a new accumulator design. 3D Research, 2(2), p.3.
19. Goshin, E. and Loshkareva, G. (2016). Informatsionnaya tekhnologiya segmentatsii raznorakursnykh izobrazhenii s ispol'zovaniem trekhmernogo preobrazovaniya Khafa [Information technologies for segmentation of images with various angles using 3D Hough transformation]. In: Materialy mezhdunarodnoi konferentsii i molodezhnoi shkoly «Informatsionnye tekhnologii i nanotekhnologii» [International Conference and Youth School on Information Technology and Nanotechnology]. pp.342-349. (in Russian).