Grid-based Spatial Keypoint Selection for Real Time Visual Odometry

Volker Nannen, Gabriel Oliver

Abstract

Robotic systems can achieve real-time visual odometry by extracting a fixed number of invariant keypoints from the current camera frame, matching them against keypoints from a previous frame, and calculating camera motion from matching pairs. If keypoints are selected by response only they can become concentrated in a small image region. This decreases the chance for keypoints to match between images and increases the chance for a degenerate set of matching keypoints. Here we present and evaluate a simple grid-based method that forces extracted keypoints to follow an even spatial distribution. The benefits of this approach depend on image quality. Real world trials with low quality images show that the method can extend the length of a correctly estimated path by an order of magnitude. In laboratory trials with images of higher quality we observe that the quality of motion estimates can degrade significantly, in particular if the number of extracted keypoints is low. This negative effect can be minimized by using a large number of grid cells.

References

  1. Bay, H., Ess, A., Tuytelaars, T., and van Gool, L. (2008). Speeded-Up Robust Features (SURF). Computer Vis. Image Underst., 110(3):346-359.
  2. Brown, M., Szeliski, R., and Winder, S. (2005). Multiimage matching using multi-scale oriented patches. In IEEE Conf. Comput. Vision Pattern Recogn., CVPR'05, pages 510-517. IEEE.
  3. Caballero, F., Merino, L., Ferruz, J., and Ollero, A. (2009). Vision-Based Odometry and SLAM for Medium and High Altitude Flying UAVs. J. Intell. Robotic Syst., 54(1-3):137-161.
  4. Cheng, Z., Devarajan, D., and Radke, R. J. (2007). Determining Vision Graphs for Distributed Camera Networks Using Feature Digests. EURASIP J. Adv. Signal Process., 2007(1):057034.
  5. Evans, C. (2009). Notes on the OpenSURF Library. Technical Report CSTR-09-001, University of Bristol.
  6. Fischler, M. A. and Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Comm. ACM, 24(6):381-395.
  7. Gauglitz, S., Foschini, L., Turk, M., and Hollerer, T. (2011). Efficiently selecting spatially distributed keypoints for visual tracking. In IEEE Int. Conf. Image Process., ICIP'11, pages 1869-1872. IEEE.
  8. Nannen, V. and Oliver, G. (2012). Optimal Number of Image Keypoints for Real Time Visual Odometry. In IFAC Worksh. Navig. Guid. Control Underw. Veh. (NGCUV), pages 1-6, Porto.
  9. Prats, M., Ribas, D., Palomeras, N., García, J. C., Nannen, V., Wirth, S., Fernández, J. J., Beltrán, J. P., Campos, R., Ridao, P., Sanz, P. J., Oliver, G., Carreras, M., Gracias, N., Marín, R., and Ortiz, A. (2012). Reconfigurable AUV for intervention missions: a case study on underwater object recovery. Intel. Serv. Robot., 5(1):19-31.
Download


Paper Citation


in Harvard Style

Nannen V. and Oliver G. (2013). Grid-based Spatial Keypoint Selection for Real Time Visual Odometry . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 586-589. DOI: 10.5220/0004270005860589


in Bibtex Style

@conference{icpram13,
author={Volker Nannen and Gabriel Oliver},
title={Grid-based Spatial Keypoint Selection for Real Time Visual Odometry},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={586-589},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004270005860589},
isbn={978-989-8565-41-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Grid-based Spatial Keypoint Selection for Real Time Visual Odometry
SN - 978-989-8565-41-9
AU - Nannen V.
AU - Oliver G.
PY - 2013
SP - 586
EP - 589
DO - 10.5220/0004270005860589