Feature Extraction Method Based on Content-Aware Tiling on Mobile Devices

Li Zhu; Wen Mao Li

doi:10.4028/www.scientific.net/AMR.926-930.3509

Paper Titles

Automatic Detection Algorithm for Chest Compressions Signal with Classification Algorithm
p.3493

Design and Research of Hardware-in-the Loop Platform of Infrared Seeker Based on Lab-VIEW
p.3497

Design of the Oil Well Gets Remote Monitoring System Based on GoAhead
p.3501

Fault Diagnosis of some TV Seeker Based on General Grey Relation Analysis
p.3505

Feature Extraction Method Based on Content-Aware Tiling on Mobile Devices
p.3509

Kinematic Transmission Analysis of a Novel Spherical 3-RRR Parallel Manipulator
p.3513

Multi-Sensor Data Fusion Algorithm in the Belt of Coal Dust Spray Application
p.3517

Numerical Simulation of the Extrusion Process with Feeder Plate Die
p.3521

Numerical Simulation of Ventilation Characteristics in a Hydropower Station Spillway Tunnel with High Head and Large Discharge
p.3527

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 926-930Feature Extraction Method Based on Content-Aware...

Feature Extraction Method Based on Content-Aware Tiling on Mobile Devices

Abstract:

The computing power of mobile devices makes it possible to transplant the applications which run on PCs to mobile devices. However, the power is still too weak to meet the requirements for some kinds of applications which are highly in real-time. In augmented reality applications, feature extraction, as well as feature matching is critical. In this paper .we focus on the part of feature extraction, and modify SURF as an example to fit the hardware characteristics of mobile devices. To solve the mismatch between the small cache size and the data access pattern. We proposed the content-aware tiling based SURF according to the small cache capacity. Experiments show that the accelerated SURF achieves a 1.5x-1.7x speedup without sacrificing recognition accuracy.

You might also be interested in these eBooks

Progress in Applied Sciences, Engineering and Technology

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 926-930)

Pages:

3509-3512

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.926-930.3509

Citation:

Cite this paper

Online since:

May 2014

Authors:

Li Zhu*, Wen Mao Li

Keywords:

Augmented Reality, Feature Extraction, SURF, Tiling

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Shi Jiaoying. Virtual reality basis and practical algorithm. Beijing: Science Press, (2002).

Google Scholar

[2] H.B. Yang: Virtual reality constructed language VRML. Beijing: Beihang University Press, (2000).

Google Scholar

[3] Wang Chengwei. Spiritual environment (virtual reality) technology, theory, implementation and applications Beijing: Tsinghua University Press, (1996).

Google Scholar

[4] Zhu Miaoliang, Yao Yuan, Jiang Yunliang: Journal of Image and Graphics, 2004(9): 767-774.

Google Scholar

[5] Su Hui, AR Zombie Invasion, http: /mobile. 51cto. com/hot-305941. htm.

Google Scholar

[6] E. Rublee, V. Rabaud, K. Konolige, et al: An Efficient Alternative to SIFT or SURF. In Proc. ICCV, 2011, pp.510-514.

DOI: 10.1109/iccv.2011.6126544

Google Scholar

[7] Rosten, E. and Drummond, T. Machine Learning for High Speed Corner Detection. In Proc. ECCV, 2006, pp.931-934.

Google Scholar

[8] Rosten, E., Porter, R., and Drummond, T: In IEEE Trans. PAMI, 2010, 32: 105–119.

Google Scholar

[9] D.N. Ta, W.C. Chen, N. Gelfand, et al: Local Feature Descriptors. In Proc. CVPR, 2009, 104-107.

Google Scholar

[10] Terriberry, T. B., French, L. M., and HelmsenL: In Proc. 3DPVT, 2008, pp.410-414.

Google Scholar

[11] Coleman, S. and McKinley, K. S.: In Proc. SIGPLAN, 1995, pp.2391-2394.

Google Scholar