Monocular Structure from Motion Based on Angular BA

Xiu Zhi Li; Ai Lin Yang; Huan Qiu; Song Min Jia

doi:10.4028/www.scientific.net/AMM.742.290

Paper Titles

New Segmentation Scheme for Low Quality Fingerprint Images
p.272

Research on Image Restoration Methods
p.277

Translation Compensation Based on Cycle Subtracting of Micro-Doppler Curve
p.281

An Object Tracking Method Based on Illumination Compensation
p.286

Monocular Structure from Motion Based on Angular BA
p.290

A Genenral Feistal Structure Based Color Image Encryption Algorithm
p.294

Face Recognition Algorithm Based on Haar-Like Features and Gentle Adaboost Feature Selection via Sparse Representation
p.299

Real-Time Image Shift Detection with Cross Correlation Coefficient Algorithm for Correlating Shack-Hartmann Wavefront Sensors Based on FPGA and DSP
p.303

An Improved Method for Power Harmonic Analysis Based on Blackman Window and Phase Difference Correction
p.312

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 742Monocular Structure from Motion Based on Angular...

Monocular Structure from Motion Based on Angular BA

Abstract:

This paper presents a technique for monocular Structure from Motion (SFM) that reconstructs 3D world shape. The technique proposed uses optical flow for 2D pixel pair matching and Angular Bundle Ajustment (ABA) for 3D structure refinement. The proposed strategy has two main advantages. Firstly, optical flow fields provide sufficient dense correspondence of image point pairs and secondly, ABA outperforms classic BA variants, especially for the points relatively far from camera. The reconstruction results obtained in realistic scenario demonstrate the effectiveness and accuracy of the proposed algorithm.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 742)

Pages:

290-293

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.742.290

Citation:

Cite this paper

Online since:

March 2015

Authors:

Xiu Zhi Li, Ai Lin Yang*, Huan Qiu, Song Min Jia

Keywords:

Angular Bundle Adjustment, Feature Match, Optical Flow, SFM

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] G. Klein and D. W. Murray: Parallel Tracking and Mapping for Small AR Workspaces, in Proceedings of the International Symposium on Mixed and Augmented Reality (IS-MAR), Nara, (2007), p.225.

DOI: 10.1109/ismar.2007.4538852

Google Scholar

[2] Zhao Liang, Huang Shoudong, Sun Yanbiao, Yan Lei and Gamini Dissanayake: ParallaxBA: Bundle Adjustment using Parallax Angle Feature Parametrization, Submitted to International Journal of Robotics Research (IJRR), (2013).

DOI: 10.1177/0278364914551583

Google Scholar

[3] M. I. A Lourakis and A. A Argyros: SBA: A Software Package for Generic Sparse Bundle Adjustment. ACM Transactions on Mathematical Software, 36(1): (2009), p.1.

DOI: 10.1145/1486525.1486527

Google Scholar

[4] K Konolige: Sparse Bundle Adjustment. British Machine Vision Conference (BMVC), (2010), p.1.

DOI: 10.5244/c.24.102

Google Scholar

[5] Zhao Liang, Huang Shoudong, Yan Lei and Gamini Dissanayake: Parallax Angle Parametrization for Monocular SLAM, In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), (2011), p.3117.

DOI: 10.1109/icra.2011.5979934

Google Scholar

[6] C. Zach, T. Pock, and H. Bischof: A Duality Based Approach for Real-time TV-L1 Optical Flow, in Proceedings of the DAGM Symposium on Pattern Recognition, Heidelberg, (2007), p.214.

DOI: 10.1007/978-3-540-74936-3_22

Google Scholar

[7] D Nister: An Efficient Solution to the Five-Point Relative Pose Problem, IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(6), (2004), p.756.

DOI: 10.1109/tpami.2004.17

Google Scholar