3D camera pose estimation using line correspondences and 1D homographies
Pages 41 - 52
Abstract
This paper describes a new method for matching line segments between two images in order to compute the relative camera pose. This approach improves the camera pose for images lacking stable point features but where straight line segments are available. The line matching algorithm is divided into two stages: At first, scale-invariant feature points along the lines are matched incorporating a one-dimensional homography. Then, corresponding line segments are selected based on the quality of the estimated homography and epipolar constraints. Based on two line segment correspondences the relative orientation between two images can be calculated.
References
[1]
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 27, 1615-1630 (2005)
[2]
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91-110 (2004)
[3]
Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: British Machine Vision Conference, pp. 384-393 (2002)
[4]
Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: Exploring photo collections in 3d. In: SIGGRAPH Conference Proceedings, pp. 835-846 (2006)
[5]
Fischler, M.A., Bolles, R.C.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM 24, 381-395 (1981)
[6]
Nistér, D.: An efficient solution to the five-point relative pose problem. IEEE Pattern Analysis and Machine Intelligence 26, 756-770 (2004)
[7]
Schmid, C., Zisserman, A.: Automatic line matching across views. In: Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition, pp. 666-672 (1997)
[8]
Bay, H., Ferrari, V., Van Gool, L.: Wide-baseline stereo matching with line segments. In: Proceedings of the 2005 Conference on Computer Vision and Pattern Recognition, pp. 329-336 (2005)
[9]
Meltzer, J., Soatto, S.: Edge descriptors for robust wide-baseline correspondence. In: Proceedings of the 2008 Conference on Computer Vision and Pattern Recognition, pp. 1-8 (2008)
[10]
Briggs, A.J., Detweiler, C., Li, Y., Mullen, P.C., Scharstein, D.: Matching scalespace features in 1d panoramas. Computer Vision and Image Understanding 103, 184-195 (2006)
[11]
Xie, J., Beigi, M.S.: A scale-invariant local descriptor for event recognition in 1d sensor signals. In: Proceedings of the 2009 IEEE International Conference on Multimedia and Expo, Piscataway, NJ, USA, pp. 1226-1229. IEEE Press, Los Alamitos (2009)
[12]
Thormählen, T., Broszio, H., Wassermann, I.: Robust line-based calibration of lens distortion from a single view. In: Proceedings of MIRAGE 2003, pp. 105-112 (2003)
[13]
Brown, M., Lowe, D.: Invariant features from interest point groups. In: British Machine Vision Conference, pp. 656-665 (2002)
[14]
Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004) ISBN: 0521540518
- 3D camera pose estimation using line correspondences and 1D homographies
Recommendations
Pose Estimation using Point and Line Correspondences
The problem of a real-time pose estimation between a 3D scene and a single camera is a fundamental task in most 3D computer vision and robotics applications such as object tracking, visual servoing, and virtual reality. In this paper we present two fast ...
Real-time camera pose estimation via line tracking
Real-time camera calibration has been intensively studied in augmented reality. However, for texture-less and texture-repeated scenes as well as poorly illuminated scenes, obtaining a stable calibration is still an open problem. In the paper, we propose ...
Absolute pose estimation from line correspondences using direct linear transformation
We propose a novel method for camera pose estimation from large sets of lines.The method exploits linear formulation of the Perspective-n-Line problem.It achieves state-of-the-art accuracy in estimating camera position.The method is highly ...
Comments
Information & Contributors
Information
Published In
November 2010
756 pages
ISBN:3642172733
Sponsors
- NASA: National Aeronatics and Space Administration
- DigitalPersona
- Intel: Intel
- Equinox Corporation
- HP invent
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 29 November 2010
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 25 Feb 2025