|
Аннотация.
В работе предложен новый точный комбинированный метод решения вариационной задачи точка-плоскость в замкнутой форме для ортогональных преобразований, который используется для построения трехмерной модели окружающей среды по набору изображений и данным карты глубины, полученным с датчиков, расположенных на мобильных платформах. Проведено сравнение предложенного метода с методом Хорна для метрики точка-точка. Результаты компьютерного моделирования показали, что предложенный метод лучше известных методов регистрации, как по точности, так и с точки зрения вычислительной сложности в неконтролируемых условиях.
Ключевые слова: задача регистрации данных, метрика точка-плоскость, локализация, ортогональное преобразование, двумерные дескрипторы, итеративный алгоритм ближайших точек.
Стр. 3-14.
DOI: 10.14357/20790279200101 Литература
1. Davison A. J., Reid I. D., Molton N. D., Stasse O. MonoSLAM: Real-Time single camera SLAM //Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence. 2007. № 29 (6), p. 1052-1067. 2. Hertzberg C., Wagner R., Birbach O. Experiences in building a visual slam system from open source components // IEEE International Conference on Robotics and Automation Proceedings. 2011, p. 2644-2651. 3. Vokhmintsev A., Yakovlev K. A Real-time Algorithm for Mobile Robot Mapping Based on Rotation-invariant Descriptors and ICP // The 5th International Conference on Analysis of Images, Social Networks and Texts / Eds. D. I. Ignatov, M. Yu. Khachay, V. G. Labunets, et al. – Communications in Computer and Information Science. – Springer. 2016, 661, p. 357–369. 4. Henry P., Krainin M., Herbst E., Ren X., Fox D. RGB-D mapping: Using depth cameras for dense 3D modeling of indoor environments // 12-th International Symposium on Experimental Robotics Proceedings. 2014, 79, p. 477-491. 5. Endres F., Hess J., Engelhard N., Sturm J. An evaluation of the RGB-D SLAM system // IEEE International Conference on Robotics and Automation Proceedings. 2012. P. 1691-1696. 6. Redmon J., Farhadi A. YOLO9000: Better, Faster, Stronger // IEEE Conference on Computer Vision and Pattern Recognition-CVPR Proceedings. 2017. 7. Antonello M., Wolf D., Prankl J., Ghidoni S., Menegatti E., Vincze M. Multi-view 3d entangled forest for semantic segmentation and mapping // IEEE International Conference in Robotics and Automation Proceedings. 2018, p. 1-8. 8. Besl P., McKay N. A method for registration of 3D shapes // Journal of IEEE Transaction on Pattern Analysis and Machine Intelligence. 1992. № 14(2), p. 239-256. 9. Tam G.K., Cheng Z.Q., Lai Y.K, Langbein F.C., Liu Y., Marshall D., Martin R.R, Sun X.F., Rosin P.L. Registration of 3D point clouds and meshes: A survey from rigid to nonrigid // Journal of IEEE Transactions on Visualization and Computer Graphics. 2013. № 19 (7), p. 1199–1217. 10. Rusinkiewicz S., Levoy M. Efficient variants of the Iterative closest point algorithm // 3-rd International Conference on 3D Digital Imaging and Modeling Proceedings. 2001, p. 145–152. 11. Khoshelham K. Closed-form solutions for estimating a rigid motion from plane correspondences extracted from point clouds // ISPRS Journal of Photogrammetry and Remote Sensing. 2016. № 114, p. 78–91. 12. Du S., Zheng N., Ying S., Liu J. Affine iterative closest point algorithm for point set registration // Journal of Pattern Recognition Letters. 2010. №31(9), p. 791–799. 13. Chen Y., Medioni G. Object modeling by registration of multiple range images // IEEE International Conference on Robotics and Automation Proceedings. 1991, № 10(3), p. 2724-2729. 14. Horn B. Closed-Form Solution of Absolute Orientation Using Unit Quaternions // Journal of the Optical Society of America A. № 4(4), p. 629–642. 15. Horn B., Hilden H., Negahdaripour S. Closedform Solution of Absolute Orientation Using Orthonormal Matrices // Journal of the Optical Society of America A. 1988, № 5(7), p. 1127–1135. 16. Low K.L. Linear least-squares optimization for point-to-plane ICP surface registration. Department of Computer Science, University of North Carolina at Chapel Hill. Technical Report TTR04-004. Available at: https://www.comp.nus.edu.sg/~lowkl/publications/lowk_point-to-plane_icp_techrep.pdf (accessed February 17, 2004). 17. Segal A., Haehnel D., Thrun S. Generalized-ICP // Science and Systems Proceedings of Robotics. 2009, 2(4), p. 645-653. 18. Vokhmintcev A.V., Melnikov A.V., Mironov K.V., Burlutskiy V.V. Reconstruction of threedimensional map based on closed form solution of variational problem of multi-sensor data registration // Journal of Doklady Mathematics.2019. № 99 (1), p. 108–112. 19. Vokhmintcev A., Melnikov A., Pachganov S., Burlutskii V. The New Combined Closed-Solution for 3D Reconstruction of Environment Based on Iterative Closest Point Algorithm // 7 th Scientific Conference on Information Technologies for Intelligent Decision Making Support Proceedings. 2019, p. 23-27. 20. Langis C., Greenspan M., Godin G. The parallel Iterative closest point algorithm // IEEE 3-rd International Conference 3D Digital Imaging and Modeling Proceedings. 2001, p. 195-204. 21. Thrun S., Burgard W., Fox D. A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping // IEEE International Conference on Robotics and Automation Proceedings. 2000, p. 321–328. 22. Vokhmintcev A., Sochenkov I., Kuznetsov V., Tikhonkikh D. Face recognition based on matching algorithm with recursive calculation of local oriented gradient histogram // Journal of Doklady Mathematics. 2016. № 93 (1), p 37-41. 23. New York University depth dataset V2. Available at: https://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html (accessed December 28, 2012).
|
