Rejestracja chmur punktów: komponenty systemu

pol Article in Polish DOI: 10.14313/PAR_223/19

send Tomasz Kornuta *, Marta Jolanta Łępicka ** * IBM Research - Almaden, 650 Harry Rd, San Jose, CA 95120, Stany Zjednoczone ** Politechnika Warszawska, Instytut Automatyki i Informatyki Stosowanej

Download Article


Dwuczęściowy artykuł dotyczy problemu rejestracji obrazów RGB-D. W robotyce problem ten znany jest pod pojęciem V-SLAM (ang. Visual Simultaneous Localization and Mapping). W poniższej, pierwszej części artykułu omówiono pokrótce główne komponenty typowego systemu rejestracji, a następnie zawężono uwagę do algorytmu ICP (ang. Iterative Closest Point), służącego do wzajemnej rejestracji chmur punktów. W drugiej części artykułu uwagę skupiono na asocjacji chmur punktów, różnego rodzaju atrybutach punktów, które mogą być wykorzystane podczas znajdowania  dopasowań oraz szeregu metryk operujących na tych atrybutach. Pokrótce omówiono zastosowaną metodykę badań, zaprezentowano eksperymenty mające na celu porównanie wybranych odmian algorytmu ICP oraz omówiono otrzymane wyniki.

Słowa kluczowe

chmura punktów, ICP, obraz RGB-D, rejestracja, V-SLAM, wzajemne łączenie

Registration of RGB-D Images: Components of the System


The two-part article focuses on the problem of registration of RGB-D images, a problem that in the robotics domain is known as Visual Simultaneous Localization and Mapping, or V-SLAM in short. The following, first part of the article presents a bird’s eye view on the main components of V-SLAM systems and focuses on the ICP (Iterative Closest Point), an algorithm for a pairwise registration of point clouds. In the second part we present different types of attributes of points that can be used during the association step along with different metrics that operate on those attributes and that can be employed during the registration. We also describe the methodology used in the conducted experiments and discuss the results of comparison of selected flavours of ICP.


ICP, pairwise registration, point cloud, RGB-D image, V-SLAM


  1. Alahi A., Ortiz R., Vandergheynst P., FREAK: Fast Retina Keypoint. 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 510–517, IEEE, 2012.
  2. Belter D., Łabęcki P., Fankhauser P., Siegwart R., RGB–D terrain perception and dense mapping for legged robots. “International Journal of Applied Mathematics and Computer Science”, 26(1):81–97, 2016.
  3. Besl P., McKay N., A method for registration of 3-D shapes. “IEEE Transactions on Pattern Analysis and Machine Intelligence”, 14(2):239–256, 1992.
  4. Cadena C., Carlone L., Carrillo H., Latif Y., Scaramuzza D., Neira J., Reid I., Leonard J.J., Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. “IEEE Transactions on Robotics”,  32(6):1309–1332, 2016.
  5. Calonder M., Lepetit V., Strecha C., Fua P., BRIEF: Binary Robust Independent Elementary Features. Computer Vision – ECCV 2010, 778–792, Springer, 2010.
  6. Censi A., An ICP variant using a point-to-line metric. 2008 IEEE International Conference on Robotics and Automation, ICRA 2008, 19–25, DOI: 10.1109/ROBOT.2008.4543181.
  7. Chen Y., Medioni G., Object modelling by registration of multiple range images, 1991 IEEE International Conference on Robotics and Automation, Proceedings Vol. 3, 2724–2729.
  8. Dryanovski I., Valenti R., Xiao J., Fast visual odometry and mapping from RGB-D data. 2013 IEEE International Conference on Robotics and Automation (ICRA), 2305–2310, DOI: 10.1109/ICRA.2013.6630889.
  9. Endres F., Hess J., Engelhard N., Sturm J., Cremers D., Burgard W., An evaluation of the RGB-D SLAM system. 2012 IEEE International Conference on Robotics and Automation (ICRA), 1691–1696, May 2012.
  10. Fischler M.A., Bolles R.C., Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. “Communications of the ACM”, 24(6):381–395, 1981, DOI: 10.1145/358669.358692.
  11. Fraundorfer F., Scaramuzza D., Visual odometry: Part II: Matching, robustness, optimization, and applications. “IEEE Robotics & Automation Magazine”, 19(2):78–90, 2012, DOI: 10.1109/MRA.2012.2182810.
  12. Henry P., Krainin M., Herbst E., Ren X., Fox D., RGB-D Mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments. “International Journal of Robotics Research”, 31(5):647–663, 2012.
  13. Holz D., Ichim A.E., Tombari F., Rusu R.B., Behnke S., Registration with the point cloud library – A modular framework for aligning in 3-D. “IEEE Robotics & Automation Magazine”, 22(4):110–124, 2015, DOI: 10.1109/MRA.2015.2432331.
  14. Kornuta T., Laszkowski M., Perception subsystem for object recognition and pose estimation in RGB-D images. Challenges in Automation, Robotics and Measurement Techniques, 597–607. Springer, 2016, DOI: 10.1007/978-3-319-29357-8_52.
  15. Kornuta T., Stefanczyk M., Utilization of textured stereovision for registration of 3D models of objects. 21st International Conference on Methods and Models in Automation and Robotics (MMAR), 2016, 1088–1093. IEEE, DOI: 10.1109/MMAR.2016.7575289.
  16. Kornuta T., Stefańczyk M., Akwizycja obrazów RGB-D: czujniki. „Pomiary Automatyka Robotyka”, 18(2):92–99, 2014.
  17. Leutenegger S., Chli M., Siegwart R., BRISK: Binary Robust invariant scalable keypoints. 2011 IEEE International Conference on Computer Vision (ICCV), 2548–2555, DOI: 10.1109/ICCV.2011.6126542.
  18. Lowe D., Object recognition from local scale-invariant features. The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999, Vol. 2, 1150–1157.
  19. Men H., Gebre B., Pochiraju K., Color point cloud registration with 4D ICP algorithm. 2011 IEEE International Conference on Robotics and Automation (ICRA), 1511–1516, DOI: 10.1109/ICRA.2011.5980407.
  20. Moravec H.P., Obstacle avoidance and navigation in the real world by a seeing robot rover. Memo AIM-340, Stanford Artificial Intelligence Laboratory, 1980.
  21. Muja M., Lowe D.G., Fast approximate nearest neighbors with automatic algorithm configuration. International Conference on Computer Vision Theory and Application VISSAPP ’09, 331–340. INSTICC Press, 2009.
  22. Muja M., Lowe D.G., Fast matching of binary features. 2012 Ninth Conference on Computer and Robot Vision (CRV), 404–410. IEEE, 2012.
  23. Nistér D., Naroditsky O., Bergen J., Visual odometry. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Vol. 1, 1–8. IEEE, 2004.
  24. Pomerleau F., Colas F., Siegwart R., A review of point cloud registration algorithms for mobile robotics. Foundations and Trends in Robotics, 4(1):1–104, 2015, DOI: 10.1561/2300000035.
  25. Pomerleau F., Colas F., Siegwart R., Magnenat S., Comparing ICP variants on real-world data sets. “Autonomous Robots”, 34(3):133–148, 2013, DOI: 10.1007/s10514-013-9327-2.
  26. Raguram R., Chum O., Pollefeys M., Matas J., Frahm J.-M., USAC: a universal framework for random sample consensus. IEEE transactions on pattern analysis and machine intelligence, 35(8):2022–2038, 2013, DOI: 10.1109/TPAMI.2012.257.
  27. Rusinkiewicz S., Levoy M., Efficient variants of the ICP algorithm. Third International Conference on 3-D Digital Imaging and Modeling, Proceedings, 145–152, IEEE, 2001, DOI: 10.1109/IM.2001.924423.
  28. Rusu R.B., Blodow N., Beetz M., Fast point feature histograms (FPFH) for 3D registration. IEEE International Conference on Robotics and Automation, ICRA ’09, 3212–3217. IEEE, 2009, 10.1109/ROBOT.2009.5152473.
  29. Scaramuzza D., Fraundorfer F., Visual odometry: Part I: The first 30 years and fundamentals. IEEE Robotics & Automation Magazine, 18(4):80–92, 2011.
  30. Steder B., Rusu R.B., Konolige K., Burgard W., Point feature extraction on 3D range scans taking into account object boundaries. 2011 IEEE International Conference on Robotics and Automation (ICRA), 2601–2608. IEEE, 2011,  DOI: 10.1109/ICRA.2011.5980187.
  31. Stefanczyk M., Kornuta T., Akwizycja obrazów RGB-D: metody. „Pomiary Automatyka Robotyka”, 18(1):82–90, 2014.
  32. Thrun S., Leonard J.J., The Handbook of Robotics, rozdział Simultaneous Localization and Mapping, 871–890. Springer, June 2008.
  33. Tombari F., Salti S., Di Stefano L., Unique signatures of histograms for local surface description. Proceedings of the 11th European Conference on Computer Vision Conference on Computer Vision: Part III, ECCV ’10, 356–369, Berlin, Heidelberg, 2010. Springer-Verlag.
  34. Zhang Z., Iterative point matching for registration of freeform curves and surfaces. “International Journal of Computer Vision”, 13(2):119–152, 1994.