Autonomous Robots

, Volume 34, Issue 1–2, pp 47–71

How to localize humanoids with a single camera?

  • Pablo F. Alcantarilla
  • Olivier Stasse
  • Sebastien Druon
  • Luis M. Bergasa
  • Frank Dellaert
Article

Abstract

In this paper, we propose a real-time vision-based localization approach for humanoid robots using a single camera as the only sensor. In order to obtain an accurate localization of the robot, we first build an accurate 3D map of the environment. In the map computation process, we use stereo visual SLAM techniques based on non-linear least squares optimization methods (bundle adjustment). Once we have computed a 3D reconstruction of the environment, which comprises of a set of camera poses (keyframes) and a list of 3D points, we learn the visibility of the 3D points by exploiting all the geometric relationships between the camera poses and 3D map points involved in the reconstruction. Finally, we use the prior 3D map and the learned visibility prediction for monocular vision-based localization. Our algorithm is very efficient, easy to implement and more robust and accurate than existing approaches. By means of visibility prediction we predict for a query pose only the highly visible 3D points, thus, speeding up tremendously the data association between 3D map points and perceived 2D features in the image. In this way, we can solve very efficiently the Perspective-n-Point (PnP) problem providing robust and fast vision-based localization. We demonstrate the robustness and accuracy of our approach by showing several vision-based localization experiments with the HRP-2 humanoid robot.

Keywords

Vision-based localization Visibility prediction Humanoid robots Locally weighted learning Bundle adjustment 

Supplementary material

(MPG 35.3 MB)

(MPG 5.1 MB)

(MPG 10.0 MB)

(MPG 9.8 MB)

(MPG 37.2 MB)

(MPG 35.6 MB)

(MPG 18.9 MB)

(MPG 11.0 MB)

(MPG 21.1 MB)

(MPG 9.3 MB)

(MPG 4.7 MB)

10514_2012_9312_MOESM12_ESM.ppt (869 kb)
(PPT 869 kB)

References

  1. Agarwal, S., Snavely, N., Simon, I., Seitz, S. M., & Szeliski, R. (2009). Building Rome in a day. In Intl. conf. on computer vision (ICCV). Google Scholar
  2. Alcantarilla, P. F., Oh, S., Mariottini, G., Bergasa, L. M., & Dellaert, F. (2010). Learning visibility of landmarks for vision-based localization. In IEEE intl. conf. on robotics and automation (ICRA), Anchorage, AK, USA (pp. 4881–4888). Google Scholar
  3. Alcantarilla, P. F., Ni, K., Bergasa, L. M., & Dellaert, F. (2011). Visibility learning in large-scale urban environment. In IEEE intl. conf. on robotics and automation (ICRA), Shanghai, China. Google Scholar
  4. Angeli, A., Filliat, D., Doncieux, S., & Meyer, J. A. (2008). Fast and incremental method for loop-closure detection using bags of visual words. IEEE Transactions on Robotics, 24, 1027–1037. CrossRefGoogle Scholar
  5. Ansar, A., & Danilidis, K. (2003). Linear pose estimation from points or lines. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(4), 1–12. Google Scholar
  6. Atkeson, C., Moore, A., & Schaal, S. (1997). Locally weighted learning. AI Review, 11, 11–73. Google Scholar
  7. Bay, H., Ess, A., Tuytelaars, T., & Gool, L. V. (2008). SURF: speeded up robust features. Computer Vision and Image Understanding, 110(3), 346–359. CrossRefGoogle Scholar
  8. Blösch, M., Weiss, S., Scaramuzza, D., & Siegwart, R. (2010). Vision based MAV navigation in unknown and unstructured environments. In IEEE intl. conf. on robotics and automation (ICRA), Anchorage, AK, USA. Google Scholar
  9. Bohg, J., Holst, C., Huebner, K., Ralph, M., Rasolzadeh, B., Song, D., & Kragic, D. (2009). Towards grasp-oriented visual perception for humanoid robots. International Journal of Humanoid Robotics, 6(3), 387–434. CrossRefGoogle Scholar
  10. Bolles, R., & Fischler, M. (1981). A RANSAC-based approach to model fitting and its application to finding cylinders in range data. In Intl. joint conf. on AI (IJCAI), Vancouver, Canada (pp. 637–643). Google Scholar
  11. Bouguet, J. (2008a). The calibration toolbox for Matlab. example 5: Stereo rectification algorithm (code and instructions only). Google Scholar
  12. Bouguet, J. (2008b). Documentation: camera calibration toolbox for Matlab. www.vision.caltech.edu/bouguetj/calib_doc/.
  13. Byröd, M., & Åström, K. (2010). Conjugate gradient bundle adjustment. In Eur. conf. on computer vision (ECCV). Google Scholar
  14. Checklov, D., Mayol-Cuevas, W., & Calway, A. (2008). Appearance based indexing for relocalisation in real-time visual SLAM. In British machine vision conf (BMVC), Leeds, UK. Google Scholar
  15. Cummins, M., & Newman, P. (2008). FAB-MAP: probabilistic localization and mapping in the space of appearance. International Journal of Robotics Research, 27(6), 647–665. CrossRefGoogle Scholar
  16. Davison, A. J., Reid, I. D., Molton, N. D., & Stasse, O. (2007). MonoSLAM: Real-time single camera SLAM. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(6), 1052–1067. CrossRefGoogle Scholar
  17. Dellaert, F., & Kaess, M. (2006). Square root SAM: simultaneous localization and mapping via square root information smoothing. International Journal of Robotics Research, 25(12), 1181–1203. MATHCrossRefGoogle Scholar
  18. Dominey, P., Mallet, A., & Yoshida, E. (2007). Progress in programming the HRP-2 humanoid using spoken language. In IEEE intl. conf. on robotics and automation (ICRA), Rome, Italy. Google Scholar
  19. Durrant-White, H., & Bailey, T. (2006). Simultaneous localization and mapping SLAM: part 1. IEEE Robotics and Automation Magazine, 13(3), 99–110. CrossRefGoogle Scholar
  20. Foissote, T., Stasse, O., Wieber, P., Escande, A., & Kheddar, A. (2010). Autonomous 3D object modeling by a humanoid using an optimization-driven next-best-view formulation. International Journal of Humanoid Robotics, 7(3), 407–428. CrossRefGoogle Scholar
  21. Geiger, A., Roser, M., & Urtasun, R. (2010). Efficient large-scale stereo matching. In Asian conf. on computer vision (ACCV), Queenstown, New Zealand. Google Scholar
  22. Gil, A., Mozos, O., Ballesta, M., & Reinoso, O. (2010). A comparative evaluation of interest point detectors and local descriptors for visual SLAM. Machine Vision and Applications, 21(6), 905–920. CrossRefGoogle Scholar
  23. Harris, C., & Stephens, M. (1988). A combined corner and edge detector. In Proc. fourth alvey vision conference (pp. 147–151). Google Scholar
  24. Hartley, R. (1999). Theory and practice of projective rectification. International Journal of Computer Vision, 35, 115–127. CrossRefGoogle Scholar
  25. Hartley, R., & Zisserman, A. (2000). Multiple view geometry in computer vision. Cambridge: Cambridge University Press. MATHGoogle Scholar
  26. Hirschmüller, H. (2008). Stereo processing by semiglobal matching and mutual information. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2), 328–341. CrossRefGoogle Scholar
  27. Hornung, A., Wurm, K., & Bennewitz, M. (2010). Humanoid robot localization in complex indoor environments. In IEEE/RSJ intl. Conf. on intelligent robots and systems (IROS), Taipei, Taiwan. Google Scholar
  28. Jian, Y. D., Balcan, D., & Dellaert, F. (2011). Generalized subgraph preconditioners for large-scale bundle adjustment. In Intl. conf. on computer vision (ICCV), Barcelona, Spain. Google Scholar
  29. Kaess, M., Ni, K., & Dellaert, F. (2009). Flow separation for fast and robust stereo odometry. In IEEE intl. conf. on robotics and automation (ICRA), Kobe, Japan. Google Scholar
  30. Kagami, S., Nishiwaki, K., Kuffner, J., Thompson, S., Chestnutt, J., Stilman, M., & Michel, P. (2005). Humanoid HRP2-DHRC for autonomous and interactive behavior. In Proc. of the intl. symp. of robotics research (ISRR) (pp. 103–117). Google Scholar
  31. Kaneko, K., Kanehiro, F., Kajita, S., Hirukawa, H., Kawasaki, T., Hirata, M., Akachi, K., & Isozumi, T. (2004). Humanoid robot HRP-2. In IEEE intl. conf. on robotics and automation (ICRA), New Orleans, USA (pp. 1083–1090). Google Scholar
  32. Klein, G., & Murray, D. W. (2007). Parallel tracking and mapping for small AR workspaces. In IEEE and ACM intl. sym. on mixed and augmented reality (ISMAR), Nara, Japan. Google Scholar
  33. Konolige, K. (1997). Small vision system: hardware and implementation. In Proc. of the intl. symp. of robotics research (ISRR) (pp. 111–116). Google Scholar
  34. Konolige, K., & Agrawal, M. (2008). FrameSLAM: from bundle adjustment to real-time visual mapping. IEEE Transactions on Robotics, 24(5), 1066–1077. CrossRefGoogle Scholar
  35. Kwak, N., Stasse, O., Foissotte, T., & Yokoi, K. (2009). 3D grid and particle based SLAM for a humanoid robot. In IEEE-RAS intl. conference on humanoid robots, Paris, France (pp. 62–67). Google Scholar
  36. Li, L., Socher, R., & Fei-Fei, L. (2009). Towards total scene understanding: classification, annotation and segmentation in an automatic framework. In IEEE conf. on computer vision and pattern recognition (CVPR), Miami, FL, USA. Google Scholar
  37. Lourakis, M. A. (2004). levmar: Levenberg-Marquardt nonlinear least squares algorithms in C/C++. [web page] http://www.ics.forth.gr/~lourakis/levmar/.
  38. Lourakis, M. A., & Argyros, A. (2009). SBA: A software package for generic sparse bundle adjustment. ACM Transactions on Mathematical Software, 36(1), 1–30. MathSciNetCrossRefGoogle Scholar
  39. Lu, C., Hager, G., & Mjolsness, E. (2000). Fast and globally convergent pose estimation from video images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(6), 610–622. CrossRefGoogle Scholar
  40. Marquardt, D. (1963). An algorithm for least-squares estimation of nonlinear parameters. SIAM Journal on Applied Mathematics (SIAP), 11(2), 431–441. MathSciNetMATHCrossRefGoogle Scholar
  41. Mei, C., Sibley, G., Cummins, M., Newman, P., & REAL, R. I. (2010). A system for large-scale mapping in constant-time using stereo. International Journal of Computer Vision, 94(2), 198–214. CrossRefGoogle Scholar
  42. Michel, P., Chestnutt, J., Kagami, S., Nishiwaki, K., Kuffner, J., & Kanade, T. (2007). GPU-accelerated real-time 3D tracking for humanoid locomotion and stair climbing. In IEEE/RSJ intl. conf. on intelligent robots and systems (IROS), San Diego, CA, USA (pp. 463–469). Google Scholar
  43. Mikolajczyk, K., & Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(10), 1615–1630. CrossRefGoogle Scholar
  44. Mouragnon, E., Lhuillier, M., Dhome, M., Dekeyser, F., & Sayd, P. (2009). Generic and real-time structure from motion using Local bundle adjustment. Image and Vision Computing, 27, 1178–1193. CrossRefGoogle Scholar
  45. Nistér, D., Naroditsky, O., & Bergen, J. (2004). Visual odometry. In IEEE conf. on computer vision and pattern recognition (CVPR). Google Scholar
  46. Ozawa, R., Takaoka, Y., Kida, Y., Nishiwaki, K., Chestnutt, J., & Kuffner, J. (2007). Using visual odometry to create 3D maps for online footstep planning. In IEEE intl. conference on systems, man and cybernetics, Hawaii, USA (pp. 2643–2648). Google Scholar
  47. Perrin, N., Stasse, O., Lamiraux, F., & Yoshida, E. (2010). Approximation of feasibility tests for reactive walk on HRP-2. In IEEE intl. conf. on robotics and automation (ICRA), Anchorage, AK (pp. 4243–4248). Google Scholar
  48. Pretto, A., Menegatti, E., Bennewitz, M., Burgard, W., & Pagello, E. (2009). A visual odometry framework robust to motion blur. In IEEE intl. conf. on robotics and automation (ICRA), Kobe, Japan. Google Scholar
  49. Scharstein, D., & Szeliski, R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47, 7–42. MATHCrossRefGoogle Scholar
  50. Schweighofer, G., & Pinz, A. (2006). Fast and globally convergent structure and motion estimation for general camera models. In British machine vision conf. (BMVC). Google Scholar
  51. Schweighofer, G., & Pinz, A. (2008). Globally optimal O(n) solution to the PnP problem for general camera models. In British machine vision conf. (BMVC). Google Scholar
  52. Snavely, N., Seitz, S. M., & Szeliski, R. (2006). Photo tourism: exploring image collections in 3D. In SIGGRAPH. Google Scholar
  53. Stachniss, C., Bennewitz, M., Grisetti, G., Behnke, S., & Burgard, W. (2008). How to learn accurate grid maps with a humanoid. In IEEE intl. conf. on robotics and automation (ICRA), Pasadena, CA, USA. Google Scholar
  54. Stasse, O., Davison, A., Sellaouti, R., & Yokoi, K. (2006). Real-time 3D SLAM for a humanoid robot considering pattern generator information. In IEEE/RSJ intl. conf. on intelligent robots and systems (IROS), Beijing, China (pp. 348–355). Google Scholar
  55. Stasse, O., Larlus, D., Lagarde, B., Escande, A., Saidi, F., Kheddar, A., Yokoi, K., & Jurie, F. (2007). Towards autonomous object reconstruction for visual search by the humanoid robot HRP-2. In IEEE-RAS intl. conference on humanoid robots, Pittsburg, USA (pp. 151–158). Google Scholar
  56. Stasse, O., Verrelst, B., Wieber, P., Vanderborght, B., Evrard, P., Kheddar, A., & Yokoi, K. (2008). Modular architecture for humanoid walking pattern prototyping and experiments. Advanced Robotics, Special Issue on Middleware for Robotics–Software and Hardware Module in Robotics System, 22(6), 589–611. Google Scholar
  57. Strasdat, H., Montiel, J. M. M., & Davison, A. (2010). Real-time monocular SLAM: why filter? In IEEE intl. conf. on robotics and automation (ICRA), Anchorage, USA. Google Scholar
  58. Strelow, D., & Singh, S. (2004). Motion estimation from image and inertial measurements. International Journal of Robotics Research, 23(12), 1157–1195. CrossRefGoogle Scholar
  59. Triggs, B., McLauchlan, P., Hartley, R., & Fitzgibbon, A. (1999). Bundle adjustment—a modern synthesis. In W. Triggs, A. Zisserman, & R. Szeliski (Eds.), Vision algorithms: theory and practice, LNCS (pp. 298–375). Berlin: Springer. Google Scholar
  60. Wendel, A., Irschara, A., & Bischof, H. (2011). Natural landmark-based monocular localization for MAVs. In IEEE intl. conf. on robotics and automation (ICRA), Shanghai, China (pp. 5792–5799). Google Scholar
  61. Williams, B., Klein, G., & Reid, I. (2007). Real-time SLAM relocalisation. In Intl. conf. on computer vision (ICCV). Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Pablo F. Alcantarilla
    • 1
  • Olivier Stasse
    • 2
  • Sebastien Druon
    • 3
  • Luis M. Bergasa
    • 4
  • Frank Dellaert
    • 5
  1. 1.ISIT-UMR 6284 CNRSUniversité d’AuvergneClermont FerrandFrance
  2. 2.LAASCNRSToulouseFrance
  3. 3.LIRMMUniversity Montpellier IIMontpellierFrance
  4. 4.Department of ElectronicsUniversity of AlcaláMadridSpain
  5. 5.School of Interactive ComputingGeorgia Institute of TechnologyAtlantaUSA

Personalised recommendations