Integration of Tracked and Recognized Features for Locally and Globally Robust Structure from Motion

Chris Engels, Friedrich Fraundorfer, David Nistér

2008

Abstract

We present a novel approach to structure from motion that integrates wide baseline local features with tracked features to rapidly and robustly reconstruct scenes from image sequences. Rather than assume that we can create and maintain a consistent and drift-free reconstructed map over an arbitrarily long sequence, we instead create small, independent submaps generated over short periods of time and attempt to link the submaps together via recognized features. The tracked features provide accurate pose estimates frame to frame, while the recognizable local features stabilize the estimate over larger baselines and provide a context for linking submaps together. As each frame in the submap is inserted, we apply real-time bundle adjustment to maintain a high accuracy for the submaps. Recent advances in feature-based object recognition enable us to efficiently localize and link new submaps into a reconstructed map within a localization and mapping context. Because our recognition system can operate efficiently on many more features than previous systems, our approach easily scales to larger maps. We provide results that show that accurate structure and motion estimates can be produced from a handheld camera under shaky camera motion

References

  1. Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60 (2004) 91-110
  2. Nistér, D., Stewénius, H.: Scalable recognition with a vocabulary tree. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, New York City, New York. (2006)
  3. Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: Proc. 9th IEEE International Conference on Computer Vision, Nice, France. (2003) 1470-1477
  4. Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. 13th British Machine Vision Conference, Cardiff, UK. (2002) 384-393
  5. Lowe, D.: Object recognition from local scale-invariant features. In: Proc. 7th International Conference on Computer Vision, Kerkyra, Greece. (1999) 1150-1157
  6. Kalman, R.: A new approach to linear filtering and prediction problems. Transactions of the ASME: Journal of Basic Engineering (1960) 35-45
  7. Triggs, B., McLauchlan, P., Hartley, R., Fitzgibbon, A.: Bundle adjustment: A modern synthesis. In: Vision Algorithms Workshop: Theory and Practice. (1999) 298-372
  8. Engels, C., Stewénius, H., Nistér, D.: Bundle adjustment rules. In: Photogrammetric Computer Vision. (2006)
  9. Bosse, M., Newman, P., Leonard, J., Teller, S.: An atlas framework for scalable mapping. In: IEEE International Conference on Robotics and Automation. (2003) 1234-1240
  10. Leonard, J.J., Newman, P.M.: Consistent, convergent, and constant-time slam. In: International Joint Conference on Artificial Intelligence. (2003) 1143-1150
  11. Davison, A., Reid, I., Molton, N., Stasse, O.: Monoslam: Real-time single camera slam. IEEE Transactions on Pattern Analysis and Machine Intelligence 29 (2007) 1052-1067
  12. Sim, R., Little, J.J.: Autonomous vision-based exploration and mapping using hybrid maps and Rao-Blackwellised particle filters. In: Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), Beijing, IEEE/RSJ, IEEE Press (2006) 2082-2089
  13. Montemerlo, M., Thrun, S., Koller, D., Wegbreit, B.: Fastslam: A factored solution to the simultaneous localization and mapping problem. In: Proc. of the AAAI National Conference on Artificial Intelligence. (2002) 593-598
  14. Nistér, D., Naroditsky, O., Bergen, J.: Visual odometry. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC. (2004) I: 652-659
  15. Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference. (1988)
  16. Tomasi, C., Kanade, T.: Detection and tracking of point features. Technical Report CMUCS-91-132, Carnegie Mellon University (1991)
  17. Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. International Journal of Computer Vision 65 (2005) 43-72
  18. Ni, K., Steedly, D., Dellaert, F.: Out-of-core bundle adjustment for large-scale 3d reconstruction. In: Proc. 11th IEEE International Conference on Computer Vision, Rio de Jeneiro, Brazil, IEEE (2007)
Download


Paper Citation


in Harvard Style

Engels C., Fraundorfer F. and Nistér D. (2008). Integration of Tracked and Recognized Features for Locally and Globally Robust Structure from Motion . In VISAPP-Robotic Perception - Volume 1: VISAPP-RoboPerc, (VISIGRAPP 2008) ISBN 978-989-8111-23-4, pages 13-22. DOI: 10.5220/0002341800130022


in Bibtex Style

@conference{visapp-roboperc08,
author={Chris Engels and Friedrich Fraundorfer and David Nistér},
title={Integration of Tracked and Recognized Features for Locally and Globally Robust Structure from Motion},
booktitle={VISAPP-Robotic Perception - Volume 1: VISAPP-RoboPerc, (VISIGRAPP 2008)},
year={2008},
pages={13-22},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002341800130022},
isbn={978-989-8111-23-4},
}


in EndNote Style

TY - CONF
JO - VISAPP-Robotic Perception - Volume 1: VISAPP-RoboPerc, (VISIGRAPP 2008)
TI - Integration of Tracked and Recognized Features for Locally and Globally Robust Structure from Motion
SN - 978-989-8111-23-4
AU - Engels C.
AU - Fraundorfer F.
AU - Nistér D.
PY - 2008
SP - 13
EP - 22
DO - 10.5220/0002341800130022