Parallel RANSAC for Point Cloud Registration

Koguciuk, Daniel

doi:10.1515/fcds-2017-0010

Abstract

In this paper, a project and implementation of the parallel RANSAC algorithm in CUDA architecture for point cloud registration are presented. At the beginning, a serial state of the art method with several heuristic improvements from the literature compared to basic RANSAC is introduced. Subsequently, its algorithmic parallelization and CUDA implementation details are discussed. The comparative test has proven a significant program execution acceleration. The result is finding of the local coordinate system of the object in the scene in the near real-time conditions. The source code is shared on the Internet as a part of the Heuros system.

References

[1] Alehdaghi M., Esfahani M. A., and Harati A. Parallel ransac: Speeding up plane extraction in rgbd image sequences using gpu. In Computer and Knowledge Engineering (ICCKE), 2015 5th International Conference on, pages 295–300, Oct 2015.10.1109/ICCKE.2015.7365845
Search in Google Scholar Back to article
[2] Blelloch G. E. Vector Models for Data-parallel Computing. MIT Press, Cambridge, MA, USA, 1990.
Search in Google Scholar Back to article
[3] Buch A., Kraft D., Kamarainen J.-K., Petersen H., and Kruger N. Pose estimation using local structure-specific shape and appearance context. In Robotics and Automation (ICRA), 2013 IEEE International Conference on, pages 2080–2087, May 2013.10.1109/ICRA.2013.6630856
Search in Google Scholar Back to article
[4] Chum O. and Matas J. Randomized ransac with t d,d test. In IMAGE AND VISION COMPUTING, pages 448–457, 2002.
Search in Google Scholar Back to article
[5] Chum O., Matas J., and Kittler J. Locally optimized ransac. In Michaelis B. and Krell G., editors, Pattern Recognition, volume 2781 of Lecture Notes in Computer Science, pages 236–243. Springer Berlin Heidelberg, 2003.10.1007/978-3-540-45243-0_31
Search in Google Scholar Back to article
[6] Fischler M. A. and Bolles R. C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM, 24(6):381–395, June 1981.10.1145/358669.358692
Search in Google Scholar Back to article
[7] Hänsch R., Weber T., and Hellwich O. Comparison of 3D interest point detectors and descriptors for point cloud fusion. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, pages 57–64, Aug. 2014.10.5194/isprsannals-II-3-57-2014
Search in Google Scholar Back to article
[8] Hartley R. and Zisserman A. Multiple view geometry in computer vision. Cambridge University Press, Cambridge, 2003. Choix de documents en appendice.10.1017/CBO9780511811685
Search in Google Scholar Back to article
[9] Heuros 3D object recognition system. https://bitbucket.org/rrgwut/heuros. Accessed: 04-05-2015.
Search in Google Scholar Back to article
[10] Izadi S., Kim D., Hilliges O., Molyneaux D., Newcombe R., Kohli P., Shotton J., Hodges S., Freeman D., Davison A., and Fitzgibbon A. Kinectfusion: real-time 3D reconstruction and interaction using a moving depth camera. In Proceedings of the 24th annual ACM symposium on User interface software and technology, UIST ‘11, pages 559–568, New York, NY, USA, 2011. ACM.10.1145/2047196.2047270
Search in Google Scholar Back to article
[11] Koguciuk D. and Harasymowicz-Boggio B. Wykorzystanie obszarów nieznanych w dopasowywaniu chmur punktów. Prace Naukowe Politechniki Warszawskiej. Elektronika, pages 267 – 276, 2014.
Search in Google Scholar Back to article
[12] Mian A., Bennamoun M., and Owens R. Three-dimensional model-based object recognition and segmentation in cluttered scenes. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 28(10):1584–1601, Oct 2006.10.1109/TPAMI.2006.21316986541
Search in Google Scholar Back to article
[13] NVIDIA Corporation. NVIDIA CUDA C programming guide, 2015. Version 7.0.
Search in Google Scholar Back to article
[14] Raguram R., Frahm J.-M., and Pollefeys M. A comparative analysis of ransac techniques leading to adaptive real-time random sample consensus. In Forsyth D., Torr P., and Zisserman A., editors, Computer Vision - ECCV 2008, volume 5303 of Lecture Notes in Computer Science, pages 500–513. Springer Berlin Heidelberg, 2008.10.1007/978-3-540-88688-4_37
Search in Google Scholar Back to article
[15] Rusu R., Blodow N., and Beetz M. Fast point feature histograms (fpfh) for 3d registration. In Robotics and Automation, 2009. ICRA ‘09. IEEE International Conference on, pages 3212–3217, May 2009.10.1109/ROBOT.2009.5152473
Search in Google Scholar Back to article
[16] Rusu R. B. and Cousins S. 3d is here: Point cloud library (pcl). In International Conference on Robotics and Automation, Shanghai, China, 2011 2011.10.1109/ICRA.2011.5980567
Search in Google Scholar Back to article
[17] Sengupta S., Harris M., Zhang Y., and Owens J. D. Scan primitives for gpu computing. In Graphics Hardware 2007, pages 97–106. ACM, Aug. 2007.
Search in Google Scholar Back to article

Parallel RANSAC for Point Cloud Registration

Abstract

Paradigm

My account