Skip to main content
SpringerLink
Log in

Real-time multi-camera video analytics system on GPU

  • Original Research Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

In this article, parallel implementation of a real-time intelligent video surveillance system on Graphics Processing Unit (GPU) is described. The system is based on background subtraction and composed of motion detection, camera sabotage detection (moved camera, out-of-focus camera and covered camera detection), abandoned object detection, and object-tracking algorithms. As the algorithms have different characteristics, their GPU implementations have different speed-up rates. Test results show that when all the algorithms run concurrently, parallelization in GPU makes the system up to 21.88 times faster than the central processing unit counterpart, enabling real-time analysis of higher number of cameras.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Abbreviations

CPU:

Central processing unit

GPU:

Graphics processing unit

CCD:

Covered camera detection

MCD:

Moved camera detection

OOFCD:

Out-of-focus camera detection

VMD:

Video motion detection

GMM:

Gaussian mixture model

IAGMM:

Improved adaptive Gaussian mixture model

VSAM:

Video surveillance and monitoring

AOD:

Abandoned object detection

OT:

Object tracking

References

  1. Auvinet, E., Grossmann, E., Rougier, C., Dahmane, M., Meunier, J.: Left-luggage detection using homographies and simple heuristics. In: Proceedings of IEEE Int. Workshop on Performance Evaluation of Tracking and Surveillance, 51–58 (2006)

  2. Babenko, P., Shah, M.: MinGPU: a minimum GPU library for computer vision. J. Real-Time Image Proc. 3(4), 255–268 (2008)

    Article  Google Scholar 

  3. Benezeth, Y., Jodoin, P.-M., Emile, B., Laurent, H., Rosenberger C.: Comparative study of background subtraction algorithms. J. Electron. Imaging 19(3) (2010)

  4. Beyan, C., Temizel, A.: Adaptive mean-shift for automated multi object tracking. IET Comput. Vis. 6(1), 1–12 (2012). doi:10.1049/iet-cvi.2011.0054

  5. Camera sabotage discovery test video database of Graduate School of Informatics, Middle East Technical University (2009): ftp://ftp.vrcv.ii.metu.edu.tr/Datasets/Camera%20Covered, ftp://ftp.vrcv.ii.metu.edu.tr/Datasets/Camera%20Moved, ftp://ftp.vrcv.ii.metu.edu.tr/Datasets/Camera%20Out%20of%20Focus

  6. Chen, Y.-T., Chen, C.-S., Huang, C.-R., Hung, Y.-P.: Efficient hierarchical method for background subtraction. Pattern Recogn. 40(10), 2706–2715 (2007)

    Article  MATH  Google Scholar 

  7. Collins, R.T., Lipton, A., Kanade, T., Fujiyoshi, H., Duggins, D., Tsin, Y., et al.: A system for video surveillance and monitoring: VSAM Final Report. Carnegie Mellon University, Pittsburgh (2000)

  8. Cucchiara, R., Grana, C., Piccardi, M., Prati, A.: Detecting objects, shadows and ghosts in video streams by exploiting colour and motion information. Proceedings of ICIAP 25(10), 360–365 (2001)

    Google Scholar 

  9. Emeksiz, D., Temizel A.: A continuous object tracking system with stationary and moving camera modes, Proceedings of SPIE Security+Defense, Electro-Optical and Infrared Systems: Technology and Applications (2012)

  10. Ferrando, S., Gera, G., Massa, M., Regazzoni, C.: A new method for real time abandoned object detection and owner tracking. Proceedings of IEEE International Conference on Image Processing, pp. 3329–3332 (2006)

  11. Gil- Jiménez, P., López-Sastre, R., Siegmann, P., Acevedo-Rodríguez, J., Maldonado-Bascón, S.: Automatic control of video surveillance camera sabotage. IWINAC ‘07 Proceedings of the 2nd international work-conference on Nature Inspired Problem-Solving Methods in Knowledge Engineering: interplay between natural and artificial computation, Part II. (2007)

  12. Guler, S., Farrow, MK.: Abandoned object detection in crowded places. In: Proceedings of IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, pp. 99–106 (2006)

  13. Harris, M.: Optimizing parallel reduction in CUDA (2008). http://developer.download.nvidia.com/compute/cuda/1_1/Website/projects/reduction/doc/reduction.pdf

  14. Hosseini, F., Fijany, A., Safari, S., Fontaine, J.-G.: Fast implementation of dense stereo vision algorithms on a highly parallel SIMD architecture. J. Real-Time Image Process. (2011). doi:10.1007/s11554-011-0211-z

  15. Ishii, I., Ichida, T., Gu, Q., Takaki, T.: 500-fps face tracking system. J. Real-Time Image Process. (2012). doi:10.1007/s11554-012-0255-8

  16. Lee, D.-S.: Effective Gaussian mixture learning for video background subtraction. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(5), 827–832 (2005)

    Article  Google Scholar 

  17. Liu, K-Y., Li, Y.-H., Li, S., Tang, L., Wang, L.: A new parallel particle filter face tracking method based on heterogeneous system. J. Real-Time Image Process. 7(3), 153–163 (2011). doi:10.1007/s11554-011-0225-6

    Article  Google Scholar 

  18. Maddalena, L., Petrosino, A.: A self-organizing approach to background subtraction for visual surveillance applications. IEEE Trans. Image Process. 17(7), 1168–1177 (2008)

    Article  MathSciNet  Google Scholar 

  19. NVIDIA Corporation: Fermi compatibility guide for CUDA applications. http://developer.download.nvidia.com/compute/cuda/3_2/toolkit/docs/Fermi_Compatibility_Guide.pdf

  20. Obukhov, A., Kharlamov, A.: Discrete cosine transform for 8 × 8 blocks with CUDA (2008). http://developer.download.nvidia.com/compute/DevZone/C/html/C/src/dct8x8/doc/dct8x8.pdf

  21. Performance evaluation of tracking and surveillance (PETS) Benchmark Data: http://pets2006.net/ (2006)

  22. Podlozhnyuk, V.: FFT-based 2D convolution (2007). http://developer.download.nvidia.com/compute/cuda/2_2/sdk/website/projects/convolutionFFT2D/doc/convolutionFFT2D.pdf

  23. Porikli, F., Ivanov, Y., Haga, T.: Robust abandoned object detection using dual foregrounds. EURASIP J. Adv. Signal Process. (2008). doi:10.1155/2008/197875

    MATH  Google Scholar 

  24. Ribnick, E., Atev, S., Masoud, O., Papanikolopoulos, N., Volyes, R.: Real-time detection of camera tampering. AVSS ‘06 Proceedings of the IEEE International Conference on Video and Signal Based Surveillance (2006)

  25. Saglam, A., Temizel, A.: Real-time adaptive camera tamper detection for video surveillance. 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance AVSS ‘09, pp. 430–435 (2009)

  26. SanMiguel, J. C., Martinez, J. M.: Robust unattended and stolen object detection by fusing simple algorithms. Proceedings of IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 18–25 (2008)

  27. Temizel, A., Halıcı, T., Loğoğlu, B., Taşkaya Temizel, T., Ömrüuzun, F., Karaman, E.: Experiences on image and video processing with CUDA and OpenCL. GPU Computing Gems 1, NVIDIA. Elsevier (2011)

  28. Vu, P., Phong, V, Vu, T. H., Le Hoai, B.: GPU implementation of extended gaussian mixture model for background subtraction. International Conference on Computing and Communication Technologies, Research, Innovation, and Vision for the Future (RIVF), 2010 IEEE RIVF, pp. 1–4 (2010)

  29. Stava O., Benes B.: Connected component labeling in CUDA. Chapter in GPU Computing Gems (2010)

  30. Yigit, A.: Thermal and visible band image fusion for abandoned object detection, Middle East Technical University, Ankara (2010)

  31. Zivkovic, Z.: Improved adaptive Gaussian mixture model for background subtraction. Proceedings of the 17th International Conference on Pattern Recognition. ICPR, 2, pp. 28–31 (2004)

Download references

Acknowledgments

This research was funded by Ministry of Science, Industry and Technology SAN-TEZ program grant number 00542.STZ.2010-1. We also would like to thank NVIDIA for their donation of Tesla C2075 GPU boards.

Author information

Authors and Affiliations

  1. Graduate School of Informatics, Middle East Technical University, Ankara, Turkey

    Puren Guler, Deniz Emeksiz, Alptekin Temizel, Mustafa Teke & Tugba Taskaya Temizel

Authors
  1. Puren Guler
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Deniz Emeksiz
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alptekin Temizel
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mustafa Teke
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Tugba Taskaya Temizel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alptekin Temizel.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Guler, P., Emeksiz, D., Temizel, A. et al. Real-time multi-camera video analytics system on GPU. J Real-Time Image Proc 11, 457–472 (2016). https://doi.org/10.1007/s11554-013-0337-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-013-0337-2

Keywords

Search

Navigation