Browse > Article
http://dx.doi.org/10.3745/KIPSTB.2011.18B.4.173

Real-Time Object Segmentation in Image Sequences  

Kang, Eui-Seon (숭실대학교 베어드학부)
Yoo, Seung-Hun (삼성전자)
Publication Information
The KIPS Transactions:PartB / v.18B, no.4, 2011 , pp. 173-180 More about this Journal
Abstract
This paper shows an approach for real-time object segmentation on GPU (Graphics Processing Unit) using CUDA (Compute Unified Device Architecture). Recently, many applications that is monitoring system, motion analysis, object tracking or etc require real-time processing. It is not suitable for object segmentation to procedure real-time in CPU. NVIDIA provide CUDA platform for Parallel Processing for General Computation to upgrade limit of Hardware Graphic. In this paper, we use adaptive Gaussian Mixture Background Modeling in the step of object extraction and CCL(Connected Component Labeling) for classification. The speed of GPU and CPU is compared and evaluated with implementation in Core2 Quad processor with 2.4GHz.The GPU version achieved a speedup of 3x-4x over the CPU version.
Keywords
GPU(Graphics Processing Unit); CUDA(Compute Unified Device Architecture); Object Segmentation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 M.Harville, G.Gordon, and J. Woodfill"Adaptive Video Background Modeling Using Color and Depth," Proc. IEEE. Published in the 2001 International Conference on Image Processing (ICIP-2001), October, 7-10, 2001   DOI
2 D. S. Lee"Effective Gaussian Mixture Learning for Video Background Subtraction," IEEE Transactions on Pattern Analysis and Machine Inteeligence, Vol.27, No.5, May, 2005.   DOI   ScienceOn
3 P. W.Power and J. A.Schoonees. "Understanding backgroundmixture models for foreground segmentation," IVCNZ, Nov., 2002.
4 K. Suzuki, I. Horiba and N. Sugie, "Linear-time connected component labeling based on sequential local operations," Comput. Vis. Image Underst. 89(1), pp.1-23, 2003.   DOI   ScienceOn
5 L. He, Y. Chao, K. Suzuki and K. Wu, "Fast connected-component labeling," Pattern Recognition.42, pp.1977-1987, 2009.   DOI   ScienceOn
6 K. Wu, E. Otoo, K. Suzuki, "Optimizing two-pass connected-component labeling algorithms," Pattern Anal. Applic.12, pp.117-135, 2009.   DOI
7 J. D. Owens, D. Luebke, N. Govindaraju, M. Harris, J. Kruger, A. E. Lefohn, and T. J. Purcell, "A Survey of General-Purpose Computation on Graphics Hardware," Comput. Graph.Forum 26, pp.80-113, 2007.   DOI   ScienceOn
8 M. Pharr and R. Fernando, "GPU Gems 2: Programming Techniques for High-Performance Graphics and General-Purpose Computation", Addison Wesley, Messachusetts, 2005.
9 NVIDIA, 2007, CUDA Technology. Available from: http://www.nvidia.com/CUDA.
10 Nickolls, J. Buck, I. Garland, M. Skadron. K,"Scalable Parallel Programming with CUDA", ACM6(2), pp.40-53, 2008
11 P. Kaew, T. Pong and R. Bowden, "An Improved Adaptive Background Mixture Model for Real-Time Tracking with Shadow Detection," Proc. European Workshop Advanced Video Based Surveillance Systems, Sep., 2001
12 C.Stauffer, W.E.L. Grimson. "Adaptive Backgroud Mixture Models for Real-Time Tracking," Proc. CVPR, Vol.2, pp. 246-252, 1999.   DOI
13 G. Wel, S. C. Romano R. Lee L. "Using adaptive tracking to classify and monitor activities in a site," in Proceedings.1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998.   DOI
14 Stauffer C, Grimson W. E. L, "Learning patterns of activity using real-time tracking," IEEE Transactions on Pattern Analysis &Machine Intelligence, vol.22(8), pp.747-57, 2000.   DOI   ScienceOn
15 G. M. Harville and J. Woodfill."Foreground Segmentation Usingadaptive Mixture Models in Color and Depth," Workshopon Detection and Recognition of Events in Video, 2001.
16 Halfhill, T.R.,2008, "Parallel Processing With CUDA", Microprocessor Report [Online] Available from: http://www.MPRonline.com
17 P. Kumar, K. Palaniappan, A. Mittal, and G. Seetharaman, "Parallel Blob Extraction Using the Multi-core Cell Processor", ACIVS 2009, LNCS 5807, pp.320-332, 2009.