DOI QR코드

DOI QR Code

Landmark Initialization for Unscented Kalman Filter Sensor Fusion in Monocular Camera Localization

  • Hartmann, Gabriel ;
  • Huang, Fay ;
  • Klette, Reinhard
  • Received : 2013.02.25
  • Accepted : 2013.03.15
  • Published : 2013.03.25

Abstract

The determination of the pose of the imaging camera is a fundamental problem in computer vision. In the monocular case, difficulties in determining the scene scale and the limitation to bearing-only measurements increase the difficulty in estimating camera pose accurately. Many mobile phones now contain inertial measurement devices, which may lend some aid to the task of determining camera pose. In this study, by means of simulation and real-world experimentation, we explore an approach to monocular camera localization that incorporates both observations of the environment and measurements from accelerometers and gyroscopes. The unscented Kalman filter was implemented for this task. Our main contribution is a novel approach to landmark initialization in a Kalman filter; we characterize the tolerance to noise that this approach allows.

Keywords

Unscented Kalman filter;Camera pose;Camera motion;Trajectory recovery

References

  1. P. Zhang, J. I. Gu, E. E. Milios, and P. Huynh, "Navigation with IMU/GPS/digital compass with unscented Kalman filter," in Proceedings of 2005 IEEE International Conference on Mechatronics and Automation, Niagara Falls, 2005, pp. 1497-1502. http://dx.doi.org/10.1109/ICMA.2005.1626777 https://doi.org/10.1109/ICMA.2005.1626777
  2. M. P. Parsley and S. J Julier, "Avoiding negative depth in inverse depth bearing-only SLAM," Nice, 2008, pp. 2066-2071. http://dx.doi.org/10.1109/IROS.2008.4651118 https://doi.org/10.1109/IROS.2008.4651118
  3. J. Kelly and G. Sukhatme, "Visual-inertial sensor fusion: localization, mapping and sensor-to-sensor self-calibration," The International Journal of Robotics Research, vol. 30, no. 1, pp. 56-79, Jan. 2011. http://dx.doi.org/10.1177/0278364910382802 https://doi.org/10.1177/0278364910382802
  4. J. M. M. Montiel, J. Civera, and A. J. Davison, "Unified inverse depth parametrization for monocular SLAM," in Proceedings of Robotics: Science and Systems 2006, Philadelphia, 2006.
  5. J. Civera, A. J. Davison, and J. M. M. Montiel, "Inverse depth parametrization for monocular SLAM," IEEE Transactions on Robotics, vol. 24, no. 5, pp. 932-945, Oct. 2008. http://dx.doi.org/10.1109/TRO.2008.2003276 https://doi.org/10.1109/TRO.2008.2003276
  6. T. Lemaire, S. Lacroix, and J. Sola, "A practical 3D bearing-only SLAM algorithm," in Proceedings of 2005 IEEE International Conference on Intelligent Robots and Systems, Edmonton, 2005, pp. 2449-2454. http://dx.doi.org/10.1109/IROS.2005.1545393 https://doi.org/10.1109/IROS.2005.1545393
  7. A. J. Davison, "Real-time simultaneous localisation and mapping with a single camera," in Proceedings of 2003 IEEE International Conference on Computer Vision, Nice, 2003, pp. 1403-1410. http://doi.ieeecomputersociety.org/10.1109/ICCV.2003.1238654 https://doi.org/10.1109/ICCV.2003.1238654
  8. R. Munguia and A. Grau, "Delayed features initialization for inverse depth monocular SLAM," in Proceedings of the 3rd European Conference on Mobile Robots 2007 (ECMR 2007), Freiburg, 2007.
  9. N. M. Kwok and G. M. W. M. Dissanayake, "An efficient multiple hypothesis filter for bearing-only SLAM," in Proceedings of 2004 IEEE International Conference on Intelligent Robots and Systems, Sendai, 2004, pp. 736-741. http://dx.doi.org/10.1109/IROS.2004.1389440 https://doi.org/10.1109/IROS.2004.1389440
  10. J. Sola, A. Monin, M. Devy, and T. Lemaire, "Undelayed initialization in bearing only SLAM," in Proceedings of 2005 IEEE International Conference on Intelligent Robots and Systems, Edmonton, 2005, pp. 2499-2504. http://dx.doi.org/10.1109/IROS.2005.1545392 https://doi.org/10.1109/IROS.2005.1545392
  11. S. J. Julier, "The scaled unscented transformation," in Proceedings of the 2002 American Control Conference, Anchorage, 2002, pp. 4555-4559. http://dx.doi.org/10.1109/ACC.2002.1025369 https://doi.org/10.1109/ACC.2002.1025369
  12. D. Chekhlov, M. Pupilli, W. Mayol-Cuevas, and A. Calway, "Real-time and robust monocular SLAM using predictive multi-resolution descriptors," in Proceedings of the Second International Conference on Advances in Visual Computing, Nevada, 2006, pp. 276-285. http://dx.doi.org/10.1007/11919629_29 https://doi.org/10.1007/11919629_29
  13. S. A. Holmes, G. Klein, and D. W. Murray, "A square root unscented Kalman filter for visual mono SLAM," in Proceedings of 2008 IEEE International Conference on Robotics and Automation, Pasadena, 2008, pp. 3710-3716. http://dx.doi.org/10.1109/ROBOT.2008.4543780 https://doi.org/10.1109/ROBOT.2008.4543780
  14. N. Sunderhauf, S. Lange, and P. Protzel, "Using the unscented Kalman filter in mono-SLAM with inverse depth parametrization for autonomous airship control," in Proceedings of 2007 IEEE International Workshop on Safety, Security and Rescue Robotics, Rome, 2007, pp. 1-6. http://dx.doi.org/10.1109/SSRR.2007.4381265 https://doi.org/10.1109/SSRR.2007.4381265

Cited by

  1. UKF Localization of a Mobile Robot in an Indoor Environment and Performance Evaluation vol.25, pp.4, 2015, https://doi.org/10.5391/JKIIS.2015.25.4.361
  2. An Optimization Approach for Localization of an Indoor Mobile Robot vol.26, pp.4, 2016, https://doi.org/10.5391/JKIIS.2016.26.4.253
  3. Sensor-Aware Recognition and Tracking for Wide-Area Augmented Reality on Mobile Phones vol.15, pp.12, 2015, https://doi.org/10.3390/s151229847
  4. Survey on Urban Warfare Augmented Reality vol.7, pp.2, 2018, https://doi.org/10.3390/ijgi7020046