Advertisement

Real-Time GPU-Based Motion Detection and Tracking Using Full HD Videos

  • Sidi Ahmed Mahmoudi
  • Michal Kierzynka
  • Pierre Manneback
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 124)

Abstract

Video processing algorithms present a necessary tool for various domains related to computer vision such as motion tracking, videos indexation and event detection. However, the new video standards, especially those in high definitions, cause that current implementations, even running on modern hardware, no longer respect the needs of real-time processing. Several solutions have been proposed to overcome this constraint, by exploiting graphic processing units (GPUs). Although, they present a high potential of GPU, any is able to treat high definition videos efficiently. In this work, we propose a development scheme enabling an efficient exploitation of GPUs, in order to achieve real-time processing of Full HD videos. Based on this scheme, we developed GPU implementations of several methods related to motion tracking such as silhouette extraction, corners detection and tracking using optical flow estimation. These implementations are exploited for improving performances of an application of real-time motion detection using mobile camera.

Keywords

GPU CUDA video procesing motion tracking real-time 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    AMD Fusion, Family of APUs. The Future brought to you by AMD introducing the AMD APU Family, http://sites.amd.com/us/fusion/au/Pages/fusion.aspx
  2. 2.
    Fonseca, A., Mayron, L., Socek, D., Marques, O.: Design and im-plementation of an optical flow-based autonomous video surveillance system. In: Proceedings of the IASTED, p. 209 (2008)Google Scholar
  3. 3.
    Mahmoudi, S.A., Sharif, H., Ihaddadene, N., Djerabe, C.: Abnormal event detection in real time video. In: 1st International Workshop on Multimodal Interactions Analysis of Users in a Controlled Environment, ICMI (2008)Google Scholar
  4. 4.
    NVIDIA, NVIDIA CUDA: Compute Unified Device Architecture (2007), http://www.nvidia.com/cuda
  5. 5.
    Khronos-Group, The Open Standard for Parallel Programming of Heterogeneous Systems (2009), http://www.khronos.org/opencl
  6. 6.
    Bimbo, A.D., Nezi, P., Sanz, J.L.C.: Optical flow computation using extended constraints. IEEE Transaction on Image Processing, 720 (1996)Google Scholar
  7. 7.
    Kitt, B., Ranft, B., Lategahn, H.: Block-matching based optical flow estimation with reduced search space based on geometric constraints. In: 13th International Conference on Intelligent Transportation Systems, p. 1140 (2010)Google Scholar
  8. 8.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision (IJCV) 60(2), 91 (2004)CrossRefGoogle Scholar
  9. 9.
    Marzat, J., Dumortier, Y., Ducrot, A.: Real-time dense and accurate parallel optical flow using CUDA. In: In Proceedings of WSCG, p. 105 (2009)Google Scholar
  10. 10.
    Mizukami, Y., Tadamura, K.: Optical Flow Computation on Compute Unified Device Architecture. In: ICIAP’14, p. 179 (2007)Google Scholar
  11. 11.
    Mizukami, Y., Tadamura, K.: Optical Flow Computation on Compute Unified Device Architecture. In: ICIAP’14, p. 179 (2007)Google Scholar
  12. 12.
    Sinha, S.N., Fram, J.-M., Pollefeys, M., Genc, Y.: Gpu-based video feature tracking and matching. In: Edge Computing Using New Commodity Architectures (2006)Google Scholar
  13. 13.
    Tomasi, C., Kanade, T.: Detection and tracking of point features. Technical Report CMU-CS-91-132, CMU, p. 1 (1991)Google Scholar
  14. 14.
    OpenGL, OpenGL Architecture Review Board: ARB vertex program, Revision 45 (2004), http://oss.sgi.com/projects/ogl-sample/registry/
  15. 15.
    Lecron, F., Mahmoudi, S.A., Benjelloun, M., Mahmoudi, S., Manneback, P.: Heterogeneous Computing for Vertebra Detection and Segmentation in X-Ray Images. International Journal of Biomedical Imaging (2011)Google Scholar
  16. 16.
    OpenCV, OpenCV computer vision library, http://www.opencv.org
  17. 17.
    Bouguet, J.Y.: Pyramidal Implementation of the Lucas Kanade Feature Tracker, Description of the algorithm. Intel Corporation Microprocessor Research (2000)Google Scholar
  18. 18.
    Mahmoudi, S.A., et al.: Traitements d’images sur architectures parallèles et hétérogènes. Technique et Science Informatiques 31, 1183 (2012)CrossRefGoogle Scholar
  19. 19.
    Mahmoudi, S.A., Manneback, P., Augonnet, C., Thibault, S.: Détection optimale des coins et contours dans des bases d’images volumineuses sur architectures multicœurs hétérogènes. 20ème Rencontres Francophones du Parallélisme (2012)Google Scholar
  20. 20.
    Mahmoudi, S.A., Manneback, P.: Efficient Exploitation of Heterogeneous Platforms for Images Features Extraction. In: International Conference on Image Processing Theory, Tools and Applications, IPTA (2012)Google Scholar
  21. 21.
    Horn, B.K.P., Schunk, B.G.: Determining Optical Flow. Artificial Intelligence 2, 185 (1981)CrossRefGoogle Scholar
  22. 22.
    Mahmoudi, S.A., Lecron, F., Manneback, P., Benjelloun, M., Mahmoudi, S.: GPU-Based Segmentation of Cervical Vertebra in X-Ray Images. In: IEEE International Conference on Cluster Computing, p. 1 (2010)Google Scholar
  23. 23.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Imaging Understanding Workshop, p. 121 (1981)Google Scholar
  24. 24.
    Harris, C.: A combined corner and edge detector. In: Alvey Vision Conference, p. 147 (1988)Google Scholar
  25. 25.
    Mahmoudi, S.A., Lecron, F., Manneback, P., Benjelloun, M., Mahmoudi, S.: Efficient Exploitation of Heterogeneous Platforms for Vertebra Detection in X-Ray Images. In: Biomedical Engineering International Conference, Biomeic 2012, Tlemcen, Algeria, p. 1 (2012)Google Scholar

Copyright information

© ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering 2013

Authors and Affiliations

  • Sidi Ahmed Mahmoudi
    • 1
  • Michal Kierzynka
    • 2
  • Pierre Manneback
    • 1
  1. 1.Faculty of EngineeringUniversity of MonsMonsBelgium
  2. 2.Poznań Supercomputing and Networking CenterPoznańPoland

Personalised recommendations