GPU Optimized Stereo Image Matching Technique for Computer Vision Applications

Full Text (PDF, 836KB), PP.37-42

Views: 0 Downloads: 0


Kajal Sharma 1,*

1. Chosun University, Korea

* Corresponding author.


Received: 23 Jan. 2015 / Revised: 6 Mar. 2015 / Accepted: 1 Apr. 2015 / Published: 8 May 2015

Index Terms

Feature matching, stereo vision, self-organizing map, graphics processing unit


In this paper, we propose a graphics processing unit (GPU) based matching technique to perform fast feature matching between different images. Lowe proposed a scale invariant feature transform algorithm that has been successfully used in various feature matching applications such as stereo vision, object recognition, and many others, but this algorithm is computationally intensive. In order to solve this problem, we propose a matching technique optimized for graphics processing units to perform computation with less time. We have applied GPU optimization for the fast computation of keypoints to make our system fast and efficient. The proposed method used self-organizing map feature matching technique to perform efficient matching between different images. The experiments are performed on various images to examine the performance of the system in diverse conditions such as image rotation, scaling, and blurring conditions. The experimental results reveal that the proposed algorithm outperforms the existing feature matching methods resulting into fast feature matching with the optimization of graphics processing unit.

Cite This Paper

Kajal Sharma, "GPU Optimized Stereo Image Matching Technique for Computer Vision Applications", International Journal of Modern Education and Computer Science (IJMECS), vol.7, no.5, pp.37-42, 2015. DOI:10.5815/ijmecs.2015.05.05


[1]M. Z. Brown, D. Burschka, and G. D. Hager, “Advances in computational stereo,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25 issue. 8, pp. 993–1008, 2003.
[2]T. Pribanic, N. Obradovic and J. Salvi, “Stereo computation combining structured light and passive stereo matching,” Optics Communications, vol. 285 issue 6, pp. 1017-1022, 2012.
[3]C. H. Lee, Y. C. Lim, S. Kwon and J. H. Lee, “Stereo vision–based vehicle detection using a road feature and disparity histogram”, Opt. Eng. vol. 50 issue 2, 027004, 2011.
[4]S. Belongie, J. Malik, and J. Puzicha., “Shape matching and object recognition using shape contexts,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 509-522, vol. 24 issue 4, 2002.
[5]H. A. Alnabriss, I. S. I. Abuhaiba, “Improved Image Retrieval with Color and Angle Representation,” I. J. Information Technology and Computer Science, pp. 68-81, vol. 6 issue 6, 2014.
[6]M. Z. Uddin, “A Two-Level Hidden Markov Model-based Approach for Human Activity Recognition,” I. J. Information Technology and Computer Science, pp. 21-29, vol. 17 issue 1, 2014.
[7]J. Shi and C. Tomasi, “Good Features to Track,” Proc. of the 9th IEEE Conference on Computer Vision and Pattern Recognition, pp. 593-600, 1994.
[8]K. Mikolajczyk and C. Schmid, “Scale & affine invariant interest point detectors,” Int. J. of Computer Vision, pp. 63-86, vol. 60 issue 1 , 2004.
[9]C. Schmid and R. Mohr, “Local gray value invariants for image retrieval,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 19 no. 5, pp. 530-534, 1997.
[10]D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” Int. J. of Computer Vision, vol. 60, no. 2 pp. 91-110, 2004.
[11]K. Sharma, S. G. Kim, and M. P. Singh, “An improved feature matching technique for stereo vision applications with the use of self-organizing map,” International Journal of Precision Engineering and Manufacturing, vol.13 issue 8, pp. 1359-1368, 2012.
[12]S. N Sinha, J. M. Frahm, M. Pollefeys and Y. Genc, “Feature Tracking and Matching in Video Using Programmable Graphics Hardware,” Machine Vision and Applications vol. 22 issue 1, pp. 207-217, 2011.
[13]K. Bjorke, “Image processing on parallel GPU pixel units”, Proceedings of SPIE, vol. 6065 (2006).
[14]J. Fung, S. Mann, and C. Aimone, “OpenVIDIA: parallel GPU computer vision,” Proc. of the 13th annual ACM international conference on Multimedia pp. 849-852, 2005.
[15]R. Yang and M. Pollefeys, “Multi-resolution real-time stereo on commodity graphics hardware,” Proc. of IEEE computer society conference on Computer vision and pattern recognition, pp. 211-217, 2003.
[16]C. Zach, H. Bischof, and K. Karner, “Hierarchical Disparity Estimation with Programmable 3D Hardware,” International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, pp. 275-288, 2004.
[17]M. Bramberger, B. Rinner, and H. Schwabach, “An embedded smart camera on a scalable heterogeneous multi-dsp system,” Proc. of the European DSP Education and Research Symposium, 2004.
[18]S. Klupsch et al., “Real Time Image Processing based on Reconfigurable Hardware Acceleration,” Proc. of IEEE Workshop on Heterogeneous Reconfigurable Systems on Chip, 2002.
[19]M. T. Jones and P. E. Plassmann, “Scalable iterative solution of sparse linear systems,” Parallel Computing vol. 20 issue 5, pp. 753-773, 1994.
[20]Y. Saad, “ILUM: A Multi-Elimination ILU Preconditioner for General Sparse Matrices,” SIAM Journal on Scientific Computing vol. 17 issue 4, pp. 830-847, 1996.
[21]T. Kohonen, “The self-organizing map,” Proc. IEEE vol. 78 issue 19, pp. 1464-1480, 1990.
[22]G. Toulminet et al., “Vehicle Detection by Means of Stereo Vision-Based Obstacles Features Extraction and Monocular Pattern Analysis,” IEEE Transactions on Image Processing, vol .15 issue 8, pp. 2364-2375, 2006.
[23]D. B. Kirk and W. W. Hwu, “Programming Massively Parallel Processors,” 1st edition, Morgan Kaufmann, Burlington, MA, USA, 2010.