Abstract
Modern imaging sensors with higher megapixel resolution and frame rates are being increasingly used for wide-area video surveillance (VS). This has produced an accelerated demand for high-performance implementation of VS algorithms for real-time processing of high-resolution videos. The emergence of multi-core architectures and graphics processing units (GPUs) provides energy and cost-efficient platform to meet the real-time processing needs by extracting data level parallelism in such algorithms. However, the potential benefits of these architectures can only be realized by developing fine-grained parallelization strategies and algorithm innovation. This paper describes parallel implementation of video object detection algorithms like Gaussians mixture model (GMM) for background modelling, morphological operations for post-processing and connected component labelling (CCL) for blob labelling. Novel parallelization strategies and fine-grained optimization techniques are described for fully exploiting the computational capacity of CUDA cores on GPUs. Experimental results show parallel GPU implementation achieves significant speedups of ~250× for binary morphology, ~15× for GMM and ~2× for CCL when compared to sequential implementation running on Intel Xeon processor, resulting in processing of 22.3 frames per second for HD videos.
Similar content being viewed by others
References
Kumar, P., Roy, S., Mittal, A., Kumar, P.: OS-Guard: a novel framework for multimedia surveillance data management. J Multimed Technol Appl 59(2), 363–382 (2012)
Jefferson, K., Lee, C.: Computer vision workload analysis—case study of video surveillance systems. Intel Technol. J. 9(2), 109–118 (2005)
Manohar, M., Ramapriyan, H.K.: Connected component labeling of binary images on a mesh connected massively parallel processor. Comput. Vis. Graph. Image Process. 45(2), 133–149 (1989)
Boyer, M., Tarjan, D., Acton, S.T., Skadron, K.: Accelerating leukocyte tracking using CUDA: a case study in leveraging manycore coprocessors (2009)
Pavlidis, I., Morellas, V., Tsiamyrtzis, P., Harp, S.: Urban surveillance systems: from the laboratory to the commercial world. Proc IEEE 89(10), 1478–1497 (2001)
Collins, R.T., Lipton, A. J., Kanade, T., Fujiyoshi, H., Duggins, D., Tsin, Y., Tolliver, D., Enomoto, N., Hasegawa, O., Burt, P., Wixson, L.: VSAM: a system for video surveillance and monitoring. Technical Report CMU-RI-TR-00-12, Carnegie Mellon University, Pittsburgh, PA (2000)
Sankaranarayanan, A.C., Veeraraghavan, A., Chellappa, R.: Object detection, tracking and recognition for multiple smart cameras. Proc. IEEE 96(10), 1606–1624 (2008)
Kolekar, M.H., Palaniappan, K., Sengupta, S., Seetharaman, G.: Semantic concept mining based on hierarchical event detection for soccer video indexing. J. Multimed. 4(5), 298–312 (2009)
Bibby, C., Reid, I.D.: Robust real-time visual tracking using pixelwise posteriors. In: European Conference on Computer Vision, pp. II:831–II:844 (2008)
Shyu, C.R., Klaric, M., Scott, G., Barb, A., Davis, C., Palaniappan, K.: GeoIRIS: geospatial information retrieval and indexing system—content mining, semantics, modeling, and complex queries. IEEE Trans. Geosci. Remote Sens. 45(5), 839–852 (2007)
Bunyak, F., Palaniappan, K., Nath, S.K., Baskin, T.I., Dong, G.: Quantitative cell motility for in vitro wound healing using level set-based active contour tracking. In: Proceedings of the 3rd IEEE International Symposium on Biomedical Imaging, pp. 1040–1043
Hidemasa, M., Munehiro, D., Hiroki, N., Yumi, M.: Multilevel parallelization on the Cell/B.E. for a motion JPEG 2000 encoding server. In: Proceedings of the 15th International Conference Multimedia, pp. 942–951 (2007)
Liu, L., Kesavarapu, S., Connell, J., Jagmohan, A., Leem, A., Paulovicks, L., Sheinin, B. , Tang, V.L., Yeo, H.: Video analysis and compression on the STI cell broadband engine processor. In: IEEE International Conference on Multimedia and Expo (2006)
Momcilovic, S., Sousa, L.: A parallel algorithm for advanced video motion estimation on multi-core architectures. In: International Conference on Complex, Intelligent and Software Intensive Systems, pp. 831–836 (2008)
Kumar, P., Palaniappan, K., Mittal, A., Seetharaman, G.: Parallel blob extraction using multicore cell processor. In: Advanced Concepts for Intelligent Vision Systems (ACIVS) 2009. LNCS, vol. 5807, pp. 320–332 (2009)
Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. In: Proceedings CVPR, pp. 246–252 (1999)
Zivkovic, Z.: Improved adaptive Gaussian mixture model for background subtraction. In: Proceedings of the ICPR, vol. 2, pp. 28–31 (2004)
Toyama, K., Krumm, J., Brumitt, B., Meyers, B.: Wallflower: principles and practice of background maintenance. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 1, pp. 255–261, Kerkyra, Corfu, Greece, 20–25 September 1999
Sugano, H., Miyamoto, R.: Parallel implementation of morphological processing on CELL BE with OpenCV interface. In: Communications, Control and Signal Processing, 2008. ISCCSP 2008, pp. 578–583 (2008)
Park, J.-M., Looney, C.G., Chen, H.-C.: Fast connected component labeling algorithm using a divide and conquer technique. Computer Science Dept University of Alabama and University of Nevada, Reno (2004)
Chang, F., Chen, C.-J., Lu, C.-J.: A linear-time component-labeling algorithm using contour tracing technique. Comput. Vis. Underst. 93(I2), 206–220 (2004)
Wu, K., Otoo, E., Shoshani, A.: Optimizing connected component labeling algorithms. In: Proceedings of SPIE Medical Imaging Conference 2005, San Diego, CA (2005). LBNL report LBNL-56864
Fiorio, C., Gustedt, J.: Two linear time union-find strategies for image processing. Theor. Comput. Sci. 154(2), 165–181 (1996)
Davis, J., Sharma, V.: Fusion-based background subtraction using contour saliency. IEEE Conf. Comput. Vis. Pattern Recognit. 3, 11–11 (2005). OTCBVS Benchmark Dataset Collection (http://www.cse.ohio-state.edu/otcbvs-bench/)
Acknowledgments
This research was supported by DRDO under Extramural Research Project Grant Number ERIP/ER/1004552/M/01/1307 in cooperation with the Government of India. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of DRDO or the Government of India. The DRDO or Government of India is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation thereon. The authors would like to acknowledge the help of Prof. K. Palaniappan, University of Missouri-Columbia, USA, for his valuable discussions and insights on sequential algorithms of morphology and CCL and their parallelization on CELL BE architecture for an earlier work. Also we would like to heartily thank K. Phani Sunil, B.tech student at GRIET for assisting us to carry out the experiments.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kumar, P., Singhal, A., Mehta, S. et al. Real-time moving object detection algorithm on high-resolution videos using GPUs. J Real-Time Image Proc 11, 93–109 (2016). https://doi.org/10.1007/s11554-012-0309-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-012-0309-y