Skip to main content
SpringerLink
Log in

An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation

  • Published:
Autonomous Robots Aims and scope Submit manuscript

Abstract

Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. http://opencv.org/.

  2. http://www.csse.monash.edu.au/~karun/superpose3D/.

References

  • Bachrach, A., Prentice, S., He, R., & Roy, N. (2011). Range-robust autonomous navigation in GPS-denied environments. Journal of Field Robotics, 28(5), 644–666.

    Article  Google Scholar 

  • Bachrach, A., Prentice, S., He, R., Henry, P., Huang, A. S., Krainin, M., et al. (2012). Estimation, planning, and mapping for autonomous flight using an RGB-D camera in GPS-denied environments. The International Journal of Robotics Research, 31(11), 1320–1343.

    Article  Google Scholar 

  • Besl, P., & McKay, N. D. (1992). A method for registration of 3-d shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2), 239–256. https://doi.org/10.1109/34.121791.

    Article  Google Scholar 

  • Bouguet, J. Y. (2000). Pyramidal implementation of the lucas kanade feature tracker. Tech. rep., Intel Corporation, Microprocessor Research Labs.

  • Bry, A., Bachrach, A., & Roy, N. (2012). State estimation for aggressive flight in GPS-denied environments using onboard sensing. In: 2012 IEEE international conference on robotics and automation (ICRA) (pp. 1–8)

  • Chowdhary, G., Sobers, D. M., Pravitra, C., Christmann, C., Wu, A., Hashimoto, H., et al. (2012). Self-contained autonomous indoor flight with ranging sensor navigation. Journal of Guidance, Control, and Dynamics, 35(6), 1843–1854.

    Article  Google Scholar 

  • Endres, F., Hess, J., Sturm, J., Cremers, D., & Burgard, W. (2014). 3-d mapping with an RGB-D camera. IEEE Transactions on Robotics, 30(1), 177–187.

    Article  Google Scholar 

  • Fang, Z., & Scherer, S. (2014). Experimental study of odometry estimation methods using RGB-d cameras. In 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

  • Firman, M. (2016). RGBD datasets: past, present and future. In CVPR workshop on large scale 3D data: acquisition, modelling and analysis.

  • Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6), 381–395.

    Article  MathSciNet  Google Scholar 

  • García Carrillo, L., Dzul López, A., Lozano, R., & Pégard, C. (2012). Combining stereo vision and inertial navigation system for a quad-rotor UAV. Journal of Intelligent and Robotic Systems, 65(1–4), 373–387.

    Article  Google Scholar 

  • Geiger, A., Ziegler, J., & Stiller, C. (2011). Stereoscan: Dense 3d reconstruction in real-time. In Intelligent Vehicles Symposium (IV), 2011 (pp. 963–968). IEEE

  • Glocker, B., Izadi, S., Shotton, J., & Criminisi, A. (2013). Real-time RGB-d camera relocalization. In IEEE international symposium on mixed and augmented reality (ISMAR) (pp. 173–179).

  • Heredia, M., Endres, F., Burgard, W., & Sanz, R. (2015). Fast and robust feature matching for RGB-D based localization. CoRR abs/1502.00500

  • Hogg, R. V., & Craig, A. (1994). Introduction to mathematical statistics (Vol. 5). Upper Saddle River: Prentice Hall.

    MATH  Google Scholar 

  • Horn, B. K. P. (1987). Closed-form solution of absolute orientation using unit quaternions. Journal of the Optical Society of America A, 4(4), 629–642.

    Article  Google Scholar 

  • Kearsley, S. K. (1989). On the orthogonal transformation used for structural comparisons. Acta Crystallographica Section A, 45(2), 208–210.

    Google Scholar 

  • Kerl, C., Sturm, J., & Cremers, D. (2013). Robust odometry estimation for RGB-d cameras. In 2013 IEEE international conference on robotics and automation (ICRA) (pp. 3748–3754).

  • Khoshelham, K., & Elberink, S. O. (2012). Accuracy and resolution of kinect depth data for indoor mapping applications. Sensors, 12(2), 1437–1454.

    Article  Google Scholar 

  • Konagurthu, A., Kasarapu, P., Allison, L., Collier, J., & Lesk, A. (2014). On sufficient statistics of least-squares superposition of vector sets. In R. Sharan (Ed.), Research in computational molecular biology. Lecture notes in computer science, Vol. 8394 (pp. 144–159). Berlin: Springer.

    Google Scholar 

  • Li, D., Li, Q., Cheng, N., Wu, Q., Song, J., & Tang, L. (2013). Combined RGBD-inertial based state estimation for mav in GPS-denied indoor environments. In 9th Asian control conference (ASCC) (pp. 1–8).

  • Li, D., Li, Q., Tang, L., Yang, S., Cheng, N., & Song, J. (2015). Invariant observer-based state estimation for micro-aerial vehicles in gps-denied indoor environments using an RGB-D camera and MEMS inertial sensors. Micromachines, 6(4), 487–522.

    Article  Google Scholar 

  • Matas, J., & Chum, O. (2004). Randomized RANSAC with td,d test. Image and Vision Computing, 22(10), 837–842. (british Machine Vision Computing, 2002).

    Article  Google Scholar 

  • Nister, D. (2003). Preemptive RANSAC for live structure and motion estimation. In Proceedings of the ninth IEEE international conference on computer vision (vol. 1, pp. 199–206).

  • Pomerleau, F., Colas, F., Siegwart, R., & Magnenat, S. (2013). Comparing ICP variants on real-world data sets. Autonomous Robots, 34(3), 133–148.

    Article  Google Scholar 

  • Scherer, S., & Zell, A. (2013). Efficient onboard RGBD-slam for autonomous MAVS. In 2013 IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 1062–1068).

  • Senthooran, I., Barca, J. C., Kamruzzaman, J., Murshed, M. M., & Chung, H. (2015). An efficient pose estimation for limited-resourced MAVS using sufficient statistics. In 2015 IEEE/RSJ international conference on intelligent robots and systems, IROS 2015 (pp. 3735–3740). Hamburg, Germany, September 28-October 2, 2015.

  • Shen, S., Michael, N., & Kumar, V. (2011). Autonomous multi-floor indoor navigation with a computationally constrained MAV. In 2011 IEEE international conference on robotics and automation (ICRA) (pp. 20–25).

  • Shi, J., & Tomasi, C. (1994). Good features to track. In Proceedings of the 1994 IEEE computer society conference on computer vision and pattern recognition, CVPR ’94 (pp. 593–600).

  • Stowers, J., Hayes, M., & Bainbridge-Smith, A. (2011). Altitude control of a quadrotor helicopter using depth map from microsoft kinect sensor. In 2011 IEEE international conference on mechatronics (ICM) (pp. 358–362).

  • Sturm, J., Engelhard, N., Endres, F., Burgard, W., & Cremers, D. (2012). A benchmark for the evaluation of RGB-d slam systems. In Proceedings of the international conference on intelligent robot systems (IROS).

  • Szeliski, R. (2011). Computer vision-algorithms and applications. Texts in computer science. London: Springer.

    MATH  Google Scholar 

  • Valenti, R. G., Dryanovski, I., Jaramillo, C., Perea Strom, D., & Xiao, J. (2014a). Autonomous quadrotor flight using onboard RGB-d visual odometry. In 2014 IEEE international conference on robotics and automation (ICRA) (pp. 5233–5238).

  • Valenti, R. G., Dryanovski, I., Jaramillo, C., Strom, D. P., & Xiao, J. (2014b). Autonomous quadrotor flight using onboard RGB-D visual odometry. In 2014 IEEE international conference on robotics and automation, ICRA 2014 (pp. 5233–5238). Hong Kong, China, May 31-June 7, 2014.

  • Voigt. R., Nikolic, J., Hurzeler, C., Weiss, S., Kneip, L., & Siegwart, R. (2011). Robust embedded egomotion estimation. In 2011 IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 2694–2699).

  • Wang, C., Wang, T., Liang, J., Chen, Y., & Wu, Y. (2012). Monocular vision and IMU based navigation for a small unmanned helicopter. In 2012 7th IEEE conference on industrial electronics and applications (ICIEA) (pp. 1694–1699).

  • Wasenmüller, O., Meyer, M., & Stricker, D. (2016). CoRBS: Comprehensive RGB-d benchmark for slam using kinect v2. In IEEE winter conference on applications of computer vision (WACV). IEEE.

  • Weiss, S., Achtelik, M., Lynen, S., Chli, M., & Siegwart, R. (2012). Real-time onboard visual-inertial state estimation and self-calibration of MAVS in unknown environments. In 2012 IEEE international conference on robotics and automation (ICRA) (pp. 957–964).

Download references

Author information

Authors and Affiliations

  1. Faculty of Information Technology, Monash University, Caulfield East, VIC, 3145, Australia

    Ilankaikone Senthooran

  2. Faculty of Science and Technology, Federation University Australia, Churchill, VIC, 3842, Australia

    Manzur Murshed & Joarder Kamruzzaman

  3. School of Information Technology, Deakin University, Burwood, VIC, 3125, Australia

    Jan Carlo Barca

  4. Department of Mechanical and Aerospace Engineering, Monash University, Clayton, VIC, 3800, Australia

    Hoam Chung

Authors
  1. Ilankaikone Senthooran
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Manzur Murshed
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jan Carlo Barca
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Joarder Kamruzzaman
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hoam Chung
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ilankaikone Senthooran.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Senthooran, I., Murshed, M., Barca, J.C. et al. An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation. Auton Robot 43, 1257–1270 (2019). https://doi.org/10.1007/s10514-018-9801-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10514-018-9801-y

Keywords

Search

Navigation