Advanced search
1 file | 3.77 MB Add to list

Robust monocular visual odometry for road vehicles using uncertain perspective projection

David Van Hamme (UGent) , Werner Goeman (UGent) , Peter Veelaert (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
Many emerging applications in the field of assisted and autonomous driving rely on accurate position information. Satellite-based positioning is not always sufficiently reliable and accurate for these tasks. Visual odometry can provide a solution to some of these shortcomings. Current systems mainly focus on the use of stereo cameras, which are impractical for large-scale application in consumer vehicles due to their reliance on accurate calibration. Existing monocular solutions on the other hand have significantly lower accuracy. In this paper, we present a novel monocular visual odometry method based on the robust tracking of features in the ground plane. The key concepts behind the method are the modeling of the uncertainty associated with the inverse perspective projection of image features and a parameter space voting scheme to find a consensus on the vehicle state among tracked features. Our approach differs from traditional visual odometry methods by applying 2D scene and motion constraints at the lowest level instead of solving for the 3D pose change. Evaluation both on the public KITTI benchmark and our own dataset show that this is a viable approach for visual odometry which outperforms basic 3D pose estimation due to the exploitation of the largely planar structure of road environments.
Keywords
SLAM, Computer vision, Localization, Visual odometry

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 3.77 MB

Citation

Please use this url to cite or link to this publication:

MLA
Van Hamme, David et al. “Robust Monocular Visual Odometry for Road Vehicles Using Uncertain Perspective Projection.” Ed. Jean-Luc Dugelay. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING (2015): 1–18. Print.
APA
Van Hamme, D., Goeman, W., Veelaert, P., & Philips, W. (2015). Robust monocular visual odometry for road vehicles using uncertain perspective projection. (J.-L. Dugelay, Ed.)EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 1–18.
Chicago author-date
Van Hamme, David, Werner Goeman, Peter Veelaert, and Wilfried Philips. 2015. “Robust Monocular Visual Odometry for Road Vehicles Using Uncertain Perspective Projection.” Ed. Jean-Luc Dugelay. Eurasip Journal on Image and Video Processing: 1–18.
Chicago author-date (all authors)
Van Hamme, David, Werner Goeman, Peter Veelaert, and Wilfried Philips. 2015. “Robust Monocular Visual Odometry for Road Vehicles Using Uncertain Perspective Projection.” Ed. Jean-Luc Dugelay. Eurasip Journal on Image and Video Processing: 1–18.
Vancouver
1.
Van Hamme D, Goeman W, Veelaert P, Philips W. Robust monocular visual odometry for road vehicles using uncertain perspective projection. Dugelay J-L, editor. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING. SpringerOpen; 2015;1–18.
IEEE
[1]
D. Van Hamme, W. Goeman, P. Veelaert, and W. Philips, “Robust monocular visual odometry for road vehicles using uncertain perspective projection,” EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, pp. 1–18, 2015.
@article{6895776,
  abstract     = {Many emerging applications in the field of assisted and autonomous driving rely on accurate position information. Satellite-based positioning is not always sufficiently reliable and accurate for these tasks. Visual odometry can provide a solution to some of these shortcomings. Current systems mainly focus on the use of stereo cameras, which are impractical for large-scale application in consumer vehicles due to their reliance on accurate calibration. Existing monocular solutions on the other hand have significantly lower accuracy. In this paper, we present a novel monocular visual odometry method based on the robust tracking of features in the ground plane. The key concepts behind the method are the modeling of the uncertainty associated with the inverse perspective projection of image features and a parameter space voting scheme to find a consensus on the vehicle state among tracked features. Our approach differs from traditional visual odometry methods by applying 2D scene and motion constraints at the lowest level instead of solving for the 3D pose change. Evaluation both on the public KITTI benchmark and our own dataset show that this is a viable approach for visual odometry which outperforms basic 3D pose estimation due to the exploitation of the largely planar structure of road environments.},
  articleno    = {10},
  author       = {Van Hamme, David and Goeman, Werner and Veelaert, Peter and Philips, Wilfried},
  editor       = {Dugelay, Jean-Luc},
  issn         = {1687-5281},
  journal      = {EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING},
  keywords     = {SLAM,Computer vision,Localization,Visual odometry},
  language     = {eng},
  pages        = {10:1--10:18},
  publisher    = {SpringerOpen},
  title        = {Robust monocular visual odometry for road vehicles using uncertain perspective projection},
  url          = {http://dx.doi.org/10.1186/s13640-015-0065-6},
  year         = {2015},
}

Altmetric
View in Altmetric
Web of Science
Times cited: