Informatics and Applications
2020, Volume 14, Issue 1, pp 101-112
SIMULTANEOUS LOCALIZATION AND MAPPING METHOD IN THREE-DIMENSIONAL SPACE BASED ON THE COMBINED SOLUTION OF THE POINT-POINT VARIATION PROBLEM ICP FOR AN AFFINE TRANSFORMATION
- A. V. Vokhmintcev
- A. V. Melnikov
- S. A. Pachganov
Abstract
Simultaneous localization and mapping is a problem in which frame data are used as the only source of external information to define the position of a moving camera in space and at the same time, to reconstruct a map of the study area. Nowadays, this problem is considered solved for the construction of two-dimensional maps for small static scenes using range sensors such as lasers or sonar. However, for dynamic, complex, and large-scale scenes, the construction of an accurate three-dimensional map of the surrounding space is an active area of research. To solve this problem, the authors propose a solution of the point-point problem for an affine transformation and develop a fast iterative algorithm for point clouds registering in three-dimensional space. The performance and computational complexity ofthe proposed method are presented and discussed by an example of reference data. The results can be applied for navigation tasks of a mobile robot in real-time.
[+] References (22)
- Vidal-Calleja, T.A., C. Berger, J. Sola, and S. Lacroix. 2011. Large scale multiple robot visual mapping with heterogeneous landmarks in semi- structured terrain. J. Robotics Autonomous Systems 59(9):654-674. doi: 10.1016/j.robot.2011.05.008.
- Vokmintsev, A., M. Timchenko, and K. Yakovlev. 2017. Simultaneous localization and mapping in unknown environment using dynamic matching of images and registration of point clouds. 2nd Conference (International) on Industrial Engineering, Applications and Manufacturing. IEEE. Art. ID 7910967. 6 p. doi: 10.1109/ ICIEAM.2016.7910967.
- Bokovoy, A., and K. Yakovlev. 2018. Sparse 3D point- cloud map upsampling and noise removal as a vSLAM post-processing step: Experimental evaluation. Interactive collaborative robotics. Eds. A. Ronzhin, G. Rigoll, and R. Meshcheryakov. Lecture notes in computer science ser. Springer. 11097:23-33.
- Tam, G., Z.-Q. Cheng, Y.-K. Lai, F Langbein, Y. Liu, D. Marshall, R. Martin, and P. Rosin. 2013. Registration of 3D point clouds and meshes: A survey from rigid to nonrigid. IEEE T. Vis. Comput. Gr. 19(7):1199-1217. doi: 10.1109/tvcg.2012.310.
- Picos, K., V.H. Diaz-Ramirez, V. Kober, A. S. Mon- temayor, and J. J. Pantrigo. 2016. Accurate three-dimensional pose recognition from monocular images
using template matched filtering. Opt. Eng. 55(6):063102. doi: 10.1117/1.oe.55.6.063102.
- Besl, P., and N. McKay. 1992. A method for registration of 3-D shapes. IEEE T. Pattern Anal. 14(2):239-256. doi: 10.1109/34.121791.
- Cheng, S., I. Marras, S. Zafeiriou, andM. Pantic. 2017. Statistical non-rigid ICP algorithm and its application to 3D face alignment. IEEE Image Vision Comput. 58:3-12. doi: 10.1016/j.imavis.2016.10.007.
- Horn, B. 1987. Closed-form solution of absolute orientation using unit quaternions. J. Opt. Soc. Am. A 4(4):629- 642. doi: 10.1364/josaa.4.000629.
- Horn, B., H. Hilden, and S. Negahdaripour. 1988. Closed- form solution of absolute orientation using orthonormal matrices. J. Opt. Soc. Am. A 5(7):1127-1135. doi: 10.1364/JOSAA.5.001127.
- Khoshelham, K. 2016. Closed-form solutions for estimating a rigid motion from plane correspondences extracted from point clouds. J. ISPRS Photogramm. 114:78-91. doi: 10.1016/j.isprsjprs.2016.01.010.
- Du, S., J. Liu, C. Zhang, J. Zhu, and K. Li. 2015. Prob-ability iterative closest point algorithm for m-D point set registration with noise. Neurocomputing 157(1):187-198. doi: 10.1016/j.neucom.2015.01.019.
- Cheng, S., I. Marras, and S. Zafeiriou. 2015. Active nonrigid ICP algorithm. IEEE 11th Conference (Inter-national) and Workshops on Automatic Face and Gesture Recognition Proceedings. Art. ID 7163161. 8 p. doi: 10.1109/FG.2015.7163161.
- Echeagaray-Patron, B.A., V. Kober, V. Karnaukhov, and
V Kuznetsov. 2017. Amethod of face recognition using 3D facial surfaces. J. Commun. Technol. El. 62(6):648-652. doi: 10.1134/s1064226917060067.
- Low, K. L. 2004. Linear least-squares optimization for point-to-plane ICP surface registration. Chapel Hill, NC: University of North Carolina at Chapel Hill, Department of Computer Science. Technical Report TTR04-004.
Available at: https://www.comp.nus.edu.sg/~lowkl/ publications/lowk_poi nt-to-plane_icp_techrep.pdf (ac-cessed December 17, 2019).
- Vokhmintcev, A. V., I. V. Sochenkov, V. V. Kuznetsov, and D.V. Tikhonkikh. 2016. Face recognition based on a matching algorithm with recursive calculation oforient- ed gradient histograms. Doklady Mathematics 93(1):37- 41. doi: 10.1134/s1064562416010178.
- Diaz-Escobar, J., and V. Kober. 2016. A robust HOG- based descriptor for pattern recognition. Proc. SPIE 9971:99712A. doi: 10.1117/12.2237963.
- Vokhmintcev, A., and K. Yakovlev. 2016. A real-time algorithm for mobile robot mapping based on rotation- invariant descriptors and ICP. Comm. Comp. Inf. Sc. 661:357-369.
- Silberman, N., P. Kohli, D. Hoiem, and R. Fergus. NYU depth dataset V2. Available at: https://cs.nyu.edu/ ~silberman/datasets/nyu_depth_v2.html (accessed De-cember 17, 2019).
- Silberman, N., D. Hoiem, P. Kohli, and R. Fergus. 2012. Indoor segmentation and support inference from RGBD Images. Computer vision. Eds. A. W. Fitzgibbon, S. Lazeb- nik, P. Perona, et al. Lecture notes in computer science ser. 7576:746-760.
- Vokhmintcev, A., T. Botova, I. Sochenkov, A. Sochenko- va, and A. Makovetskii. 2017. Robot mapping algorithm based on Kalman filtering and symbolic tags. Proc. SPIE 10396:103962I. doi: 10.1117/12.2273562.
- Vokhmintcev, A., M. Timchenko, A. Melnikov, A. Kozko, and A. Makovetskii. 2017. Robot path planning algorithm based on symbolic tags in dynamic environment. Proc. SPIE 10396:103962E. doi: 10.1117/12.2273279.
- Sochenkov, I., and A. Vokhmintsev. 2015. Visual duplicates image search for a non-cooperative person recognition at a distance. Procedia Engineer. 129:440-445. doi: 10.1016/j.proeng.2015.12.147.
[+] About this article
Title
SIMULTANEOUS LOCALIZATION AND MAPPING METHOD IN THREE-DIMENSIONAL SPACE BASED ON THE COMBINED SOLUTION OF THE POINT-POINT VARIATION PROBLEM ICP FOR AN AFFINE TRANSFORMATION
Journal
Informatics and Applications
2020, Volume 14, Issue 1, pp 101-112
Cover Date
2020-03-30
DOI
10.14357/19922264200114
Print ISSN
1992-2264
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
registration problem; localization; simultaneous localization and mapping; affine transformation; two-dimensional descriptors; iterative closest point
Authors
A. V. Vokhmintcev  ,  , A. V. Melnikov , and S. A. Pachganov
Author Affiliations
Chelyabinsk State University, 129 Br. Kashirinyh Str., Chelyabinsk 454001, Russian Federation
Ugra State University, 16 Chekhov Str., Khanty-Mansiysk 628012, Russian Federation
|