Advertisement

Multimedia Tools and Applications

, Volume 75, Issue 16, pp 9623–9640 | Cite as

Improving performance on object recognition for real-time on mobile devices

  • Jin-Chun Piao
  • Hyeon-Sub Jung
  • Chung-Pyo Hong
  • Shin-Dug KimEmail author
Article

Abstract

Augmented reality has been on the rise due to the proliferation of mobile devices. At the same time, object recognition has also come to the fore. In particular, many studies have focused on object recognition based on markerless matching. However, most of these studies have focused on desktop systems, which can have high performance in terms of CPU and memory, rather than investigating the use of mobile systems, which have been previously unable to provide high-performance object recognition based on markerless matching. In this paper, we propose a method that uses the OpenCV mobile library to improve real-time object recognition performance on mobile systems. First, we investigate the original object recognition algorithm to identify performance bottlenecks. Second, we optimize the algorithm by analyzing each module and applying appropriate code enhancements. Last, we change the operational structure of the algorithm to improve its performance, changing the execution frequency of the object recognition task from every frame to every four frames for real-time operation. During the three frames in which the original method is not executed, the object is instead recognized using the mobile devices accelerometer. We carry out experiments to reveal how much each aspect of our method improves the overall object recognition performance; overall, experimental performance improves by approximately 800 %, with a corresponding reduction of approximately 1 % in object recognition accuracy. Therefore, the proposed technique can be used to significantly improve the performance of object recognition based on markerless matching on mobile systems for real-time operation.

Keywords

Object recognition Marker-less Mobile device OpenCV Real-time 

Notes

Acknowledgments

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and Future Planning (2012R1A1A2043400), and the MSIP(Ministry of Science, ICT and Future Planning), Korea, under the Global IT Talent support program (NIPA-2014-H0905-14-1003) supervised by the NIPA(National IT Industry Promotion Agency).

References

  1. 1.
    ARM (2008) ARM NEON technology - ARM NEON support in the ARM compiler, white paper ed. ARM Corporation, Califonia CAGoogle Scholar
  2. 2.
    Bay H, Tuytelaars T, Gool LV (2006) Surf: Speeded up robust features. Computer Vision ECCV 2006 3951:404–417CrossRefGoogle Scholar
  3. 3.
    BeserraGomes R, da Silva BMF, de Medeiros Rochan LK, Aroca RV, Velho LCPR, Goncalves LMG (2013) Efficient 3d object recognition using foveated point clouds. Comput Graph 37(5):496–508CrossRefGoogle Scholar
  4. 4.
    Calonder M, Lepetit V, Strecha C, Fua P (2010) Brief: Binary robust independent elementary features. Computer Vision ECCV 2010 6314:778–792CrossRefGoogle Scholar
  5. 5.
    Fischler MA, Bolles RC (1981) Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395MathSciNetCrossRefGoogle Scholar
  6. 6.
    Kaehler A, Bradski G (2015) Learning OpenCV: computer vision in C++ with the OpenCV library, 2nd. O’REILLY, Califonia CAGoogle Scholar
  7. 7.
    Kim J-H, Kang B-D, Ahn S-H, Kim H-S, Kim S-K (2013) A real-time object detection system using selected principal components. Multimedia and Ubiquitous Engineering 240:367–376CrossRefGoogle Scholar
  8. 8.
    Lowe D G (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60:91–110CrossRefGoogle Scholar
  9. 9.
    OpenCV, OepnCV 2.4.6.0 API Reference - Common Interfaces of Descriptor Matchers. OpenCV Developer Team (2013)Google Scholar
  10. 10.
    Rosten E, Drummond T (2006) Machine learning for high-speed corner detection. Computer Vision ECCV 2006 3951:430–443CrossRefGoogle Scholar
  11. 11.
    SMPTE (1987) Smpte 240m-1988, television signal parameters 1 125/60 high definition production system, vol 69. SMPTE Journal, pp 1150–1152Google Scholar
  12. 12.
    Sugano H, Miyamoto R (2007) A real-time object recognition system on cell broadband engine. Advances in Image and Video Technology 4872:932–943CrossRefGoogle Scholar
  13. 13.
    Tuytelaars T, Mikolajczyk K (2007) Local invariant feature detectors: A survey. Computer Graphics and Vision 3(3):177–280CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  • Jin-Chun Piao
    • 1
  • Hyeon-Sub Jung
    • 2
  • Chung-Pyo Hong
    • 3
  • Shin-Dug Kim
    • 1
    Email author
  1. 1.Department of Computer ScienceYonsei UniversitySeoulSouth Korea
  2. 2.Home EntertainmentLG ElectronicsPyungtaekSouth Korea
  3. 3.Mobile CommunicationsLG ElectronicsSeoulSouth Korea

Personalised recommendations