Efficient Implementation of Stereovision Algorithms for Graphics Processing Unit in DirectShow Technology

• Autorzy: Szajerman D. , Pelczynski P.
• Języki publikacji: EN

Abstrakty

EN

Stereovision is a passive technique for estimation of depth in 3D scenes. Unfortunately, depth estimation in this imaging technique is computationally demanding. We show that stereovision matching algorithms can be efficiently mapped onto the present-day graphics processing units (GPUs). A number of modifications to the original image disparity estimation algorithm have been proposed that make running its computation on GPU platforms particularly efficient. A complete depth estimation system was implemented in GPU, covering correction of camera distortions, image rectification and disparity estimation. To obtain modularity of developed software, the DirectShow multimedia technology was used. Examples, computed depth maps are shown, and time performances of the proposed algorithms are outlined. The developed system has proved the usefulness of both GPU implementation and the DirectShow technology in scene depth estimation.

Słowa kluczowe

EN

stereovision; depth estimation; graphics processing unit; DirectShow technology

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2011
• Tom: Vol. 20, No. 2
• Strony: 139--156
• Opis fizyczny: Bibliogr. 21 poz., il., tab., wykr.

Twórcy

autor

Szajerman D.

autor

Pelczynski P.

• Institute of Information Technology, Technical University of Lodz, Pologne,

Bibliografia

• [1] Scharstein D., and Szeliski R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision Volume 47 Issue 1-3, April-June 2002, pp.7-42.
• [2] Brown M. Z., Burschka D., Hager G. D.: Advances in computational stereo, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.25, no. 8, 2003, pp. 993-1008.
• [3] Pesce, Mark D.: Programming Microsoft DirectShow for Digital Video and Television, Microsoft Press. April 16, 2003.
• [4] Mao Y., Soatto S., Kosecka J., Sastry S. S.: An invitation to 3-D vision: from images to geometric transformations. Springer-Verlag, New York, inc., 2004.
• [5] Stefano L. D., Marchionni M., Mattoccia S.: A PC-based real-time stereo vision system, Machine Graphics &: Vision International Journal, Vol. 13 Issue 3, January 2004.
• [6] Andrysiak T., Chora M.: Algorithm for stereovision disparity calculation in the moment space, Machine Graphics & Vision International Journal, Vol. 15 Issue 3, February 2006.
• [7] Brunton A., Shu C., Roth G.: Belief propagation on the GPU for Stereo Vision, Third Canadian Conference on Computer and Robot Vision, Quebec, Canada, June 7-9, 2006.
• [8] Blythe D.: Rise of the Graphics Processor, Proceedings of the IEEE, Vol. 96, No. 5, pp.761-778, 2007.
• [9] Meuth R. J.: GPUs surpass computers at repetitive calculations, IEEE Potentials, pp. 12-15, 2007.
• [10] Skulimowski P., Strumiłło P.: Refinement of depth from stereo camera ego-motion parameters, Electronics Letters, vol. 44, no. 12, 2008, pp. 729-730.
• [11] Rozen T., Boryczko K., Aida W.: A GPU-based method for approximate real-time fluid flow simulation. MGV vol. 17, no. 3, 2008, pp. 267-278.
• [12] Cyganek B.: An Introduction to 3D Computer Vision Techniques and Algorithms, John Wiley, 2009.
• [13] Grauer-Gray S. and Kambhamettu C.: Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009.
• [14] Strumiłło P., Szajerman D., Pelczyski P., Materka A.: Implementation of Stereo Matching Algorithms on Graphics Processing Units, Image Processing & Communications Challenges (R. S. Chora, A. Zabudowski, Eds.), Academy Publishing House EXIT, Warsaw 2009, pp 286-293.
• [15] NVIDIA CUDA Programming Guide ver.3.2: http://developer.download.nvidia.com/compute/cuda/3-2_prod/toolkit/docs/CUDA-C_Programming_Guide.pdf. ; 2010.
• [16] Szczypiński P., Pelczynski P., Szajerman D., Strumiłło P.: Implementation of Computer Vision Algorithms in Direct Show Technology, IP&C 2010, Oct. 20, 2010, Bydgoszcz, Poland.
• [17] Yu W., Chen T., Franchetti F., and Hoe J.: High performance stereo vision designed for massively data parallel platforms. IEEE Transactions on Circuits and Systems for Video Technology, vol. 20, no. 11, November 2010, pp. 1509-1519.
• [18] GeForce GTX590 specification: http://www.geforce.eom/#/Hardware/GPUs/geforce-gtX"590/specifications ; 2011.
• [19] Mei X., Sun X., Zhou M., Jiao S., Wang H., and Zhang X.: On building an accurate stereo matching system on graphics hardware. GPUCV 2011.
• [20] Microsoft MSDN DirectShow documentation, http://msdn.microsoft.com/en-us/library. 2011.
• [21] Polańczyk M., Owczarek A., Strzelecki M., Slot K.: Stereovision-Based Obstacle Avoidance Procedure for Autonomous Mobile Platforms. HAIS 1, Vol. 6678 Springer (2011) , p. 206-213.