Registration review

Software and hardware limitations in model-surface registration
David Rix
2015

Abstract

We introduce model-surface registration and iterative closest point (ICP), a popular solution to this problem, with reference to surveys by Rusinkiewicz and Levoy [2001] and Salvi et al. [2006]. Implementations of ICP using the Kinect for Xbox 360 are reviewed. Hardware characteristics for the Kinect and other commercial sensors (Leap Motion, Kinect for Xbox One) are summarised. Finally, limitations and requirements for academic reference material are discussed.

References

  1. Vamsi Kiran Adhikarla, Jaka Sodnik, Peter Szolgay, and Grega Jakus. 2015. Exploring direct 3D interaction for full horizontal parallax light field displays using Leap Motion controller. Sensors 15, 4 (2015), 8642-8663.
  2. Clemens Amon and Ferdinand Fuhrmann. 2014. Evaluation of the spatial resolution accuracy of the face tracking system for Kinect for Windows v1 and v2. Proceedings of the 6th Congress of the Alps Adria Acoustics Association (16-17 October 2014).
  3. Kai Berger, Stephan Meister, Rahul Nair, and Daniel Kondermann. 2013. A state of the art report on Kinect sensor setups in computer vision. Time-of-Flight and Depth Imaging. Sensors, Algorithms, and Applications (2013), Springer Berlin Heidelberg, 257-272.
  4. Paul J. Besl and Neil D. McKay. 1992. A Method for Registration of 3-D Shapes. IEEE Trans. Pattern Analysis Mach. Intell. 14, 2 (February 1992), 239-256.
  5. Joshua Blake, Florian Echtler, and Christian Kerl. 2015. libfreenect2/README.md (April 2015). Retrieved April 24, 2015 from https://github.com/OpenKinect/libfreenect2/blob/master/README.md
  6. Michael Buckwald. 2015. Leap Motion + VR 2015: A Look at the Year Ahead. Leap Motion Blog (January 8, 2015) Retrieved April 24, 2015 from http://blog.leapmotion.com/leap-motion-vr-2015-look-year-ahead/
  7. Thomas Butkiewicz. 2014. Low-cost coastal mapping using Kinect v2 time-of-flight cameras. Oceans – St. John's (14-19 September 2014), 1-9.
  8. Yang Chen and Gérard Medioni. 1991. Object modeling by registration of multiple range images. Proceedings of the IEEE International Conference on Robotics and Automation 3, 9-11 (April 1991), 2724-2729.
  9. Derivative. 2014. Image Changes Resolution. Leap Motion Community (September 17, 2014) Retrieved April 24, 2015 from https://community.leapmotion.com/t/image-changes-resolution/1765
  10. Jimmy He. 2015. Image API Now Available for v2 Tracking Beta. Leap Motion Blog (August 15, 2014) Retrieved April 24, 2015 from http://blog.leapmotion.com/image-api-now-available-v2-tracking-beta/
  11. Jože Guna, Grega Jakus, Matevž Pogačnik, Sašo Tomažič, and Jaka Sodnik. 2014. An analysis of the precision and reliability of the Leap Motion sensor and its suitability for static and dynamic tracking. Sensors 14, 2 (2014), 3702-3720.
  12. Peter Henry, Michael Krainin, Evan Herbst, Xiaofeng Ren, and Dieter Fox. 2012. RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments. Int. J. Rob. Res. 31, 5 (April 2012), 647-663.
  13. Gibson Hu, Shoudong Huang, Liang Zhao, Alen Alempijevic, and Gamini Dissanayake. A robust RGB-D SLAM algorithm. 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '12). IEEE, 1714-1719.
  14. Shahram Izadi, David Kim, Otmar Hilliges, David Molyneaux, Richard Newcombe, Pushmeet Kohli, Jamie Shotton, Steve Hodges, Dustin Freeman, Andrew Davison, and Andrew Fitzgibbon. 2011. KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera. Proceedings of the 24th annual ACM symposium on User interface software and technology (UIST '11). ACM, New York, NY, USA, 559-568.
  15. Benoît Lahoz. 2014. Use of Distortion() to get an OpenCV usable calibration map (post #9). Leap Motion Community (August 22, 2014). Retrieved April 24, 2015 from https://community.leapmotion.com/t/use-of-distortion-to-get-an-opencv-usable-calibration-map/1605/9
  16. Leap Motion. 2015a. Leap Motion (product page). Retrieved April 24, 2015 from https://www.leapmotion.com/product
  17. Leap Motion. 2015b. Camera Images. Leap Motion C# SDK v2.2 documentation (2015). Retrieved April 24, 2015 from https://developer.leapmotion.com/documentation/csharp/devguide/Leap_Images.html
  18. Leap Motion. 2015c. Is it possible to get raw point cloud data? Leap Motion Support (2015). Retrieved April 24, 2015 from https://support.leapmotion.com/entries/40337273-Is-it-possible-to-get-raw-point-cloud-data
  19. Leap Motion. 2015d. Using the Leap Motion Control Panel (robust tracking mode). Leap Motion C# SDK v2.2 documentation (2015). Retrieved April 24, 2015 from https://developer.leapmotion.com/documentation/csharp/supplements/Leap_Application.html#robust-tracking-mode
  20. Xiaoguang Lu, Anil K. Jain, and Dirk Colbry. 2006. Matching 2.5D Face Scans to 3D Models. IEEE Trans. Pattern Analysis Mach. Intell. 28, 1 (January 2006), 31-43.
  21. Sam Machkovech. 2014. Kinect v2 PC devs receive official SDK, $50 USB 3.0 adapter. Ars Technica (October 25 2014). Retrieved April 24, 2015 from http://arstechnica.com/gaming/2014/10/25/kinect-v2-pc-devs-receive-official-sdk-50-usb-3-0-adapter/
  22. Giulio Marin, Fabio Dominio, and Pietro Zanuttigh. 2014. Hand gesture recognition with Leap Motion and Kinect devices. IEEE International Conference on Image Processing (ICIP '14), IEEE, 1565-1569.
  23. Kyle Orland. 2014. Standalone Kinect for Xbox One coming October 7. Ars Technica (August 27 2014). Retrieved April 24, 2015 from http://arstechnica.com/gaming/2014/08/27/standalone-kinect-for-xbox-one-coming-october-7/
  24. Leigh Ellen Potter, Jake Araullo, and Lewis Carter. 2013. The Leap Motion controller: a view on sign language. Proceedings of the 25th Australian Computer-Human Interaction Conference: Augmentation, Application, Innovation, Collaboration (OzCHI '13), Haifeng Shen, Ross Smith, Jeni Paay, Paul Calder, and Theodor Wyeld (Eds.). ACM, New York, NY, USA, 175-178.
  25. Szymon Rusinkiewicz and Marc Levoy. 2001. Efficient variants of the ICP algorithm. Proceedings of the Third International Conference on 3-D Digital Imaging and Modeling (2001), 145-152.
  26. Joaquim Salvi, Carles Matabosch, David Fofi, and Josep Forest. 2007. A review of recent range image registration methods with accuracy evaluation. Image Vision Comput. 25, 5 (May 2007), 578-596.
  27. Gregory C. Sharp, Sang W. Lee, and David K. Wehe. 2002. ICP registration using invariant features. IEEE Trans. Pattern Analysis Mach. Intell. 24, 1 (January 2002), 90-102.
  28. Jan Smisek, Michal Jancosek, and Tomas Pajdla. 2011. 3D with Kinect. IEEE Workshop on Consumer Depth Cameras for Computer Vision (2011), 1154-1160.