Research on SIFT Matching Algorithm Based on GPU

Zheng Feng Zhan; Ge Li; Xue He Zhang

doi:10.4028/www.scientific.net/AMM.599-601.1652

Paper Titles

Research on Flight Altitude Information Fusion Method for ADS/INS/GPS Integrated Systems Based on Federated Filter
p.1636

Research on Information Exchange Platform Based-Web Services for Tourist
p.1640

Research on Information Interactive Model of Automated Demand Response
p.1644

Research on Limit-Trajectory Over-Modulation Strategy of Two Stage Matrix Converter
p.1648

Research on SIFT Matching Algorithm Based on GPU
p.1652

Research on Switch Power Module Parallel Operation System
p.1657

Research on the Application of Cloud Computing in the Field of Archives Informatization
p.1661

Research on the Performance Test of Wired/Wireless Heterogeneous Industrial Control Network
p.1665

Research on Vague Set of Target Threat Information Fusion Algorithm
p.1671

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 599-601Research on SIFT Matching Algorithm Based on GPU

Research on SIFT Matching Algorithm Based on GPU

Abstract:

Aiming at the shortage of SIFT algorithm in time comsumption and getting less matching points. On the one hand, the paper improves the original SIFT algorithm, it proposes regional growth algorithm based on SIFT, so you can get many matching points which are good for generating the disparity map; on the other hand, the paper uses the CPU and GPU heterogeneous platforms and analyses the CUDA programming model and memory model. This paper analyses the algorithm in detail, so the algorithm can be carried out on CUDA. Experimental results show that, compared with the original algorithm, the algorithm is about 10 times faster, and generate good disparity map.

You might also be interested in these eBooks

Frontiers of Manufacturing Science and Measuring Technology IV

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 599-601)

Pages:

1652-1656

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.599-601.1652

Citation:

Cite this paper

Online since:

August 2014

Authors:

Zheng Feng Zhan*, Ge Li, Xue He Zhang

Keywords:

CUDA, Parallel Computing, Regional Growth, SIFT

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Grimson W E L. Computational experiments with a feature based stereo algorithm[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, (2010)17-34.

DOI: 10.1109/tpami.1985.4767615

Google Scholar

[2] Medioni G, Nevatia R. Segment-based stereo matching[J]. Computer Vision, Graphics, and Image Processing, (2011) 2-18.

DOI: 10.1016/s0734-189x(85)80073-6

Google Scholar

[3] Sanders J, Kandrot E. CUDA by example: an introduction to general-purpose GPU programming[M]. Addison-Wesley Professional, (2010).

Google Scholar

[4] Cheng L, Caelli T. Bayesian stereo matching[J]. Computer Vision and Image Understanding, (2007)85-96.

DOI: 10.1016/j.cviu.2005.09.009

Google Scholar

[5] Information on http: /vision. middlebury. edu/stereo/eval.

Google Scholar

[6] Cheng L, Caelli T. Bayesian stereo matching[J]. Computer Vision and Image Understanding, (2007)85-96.

DOI: 10.1016/j.cviu.2005.09.009

Google Scholar