We apologize for a recent technical issue with our email system, which temporarily affected account activations. Accounts have now been activated. Authors may proceed with paper submissions. PhDFocusTM
CFP last date
20 December 2024
Reseach Article

Stereo Matching using Multi-resolution Images on CUDA

by Sudhakar Sah, Nikhil Jotwani
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 56 - Number 12
Year of Publication: 2012
Authors: Sudhakar Sah, Nikhil Jotwani
10.5120/8947-3119

Sudhakar Sah, Nikhil Jotwani . Stereo Matching using Multi-resolution Images on CUDA. International Journal of Computer Applications. 56, 12 ( October 2012), 47-55. DOI=10.5120/8947-3119

@article{ 10.5120/8947-3119,
author = { Sudhakar Sah, Nikhil Jotwani },
title = { Stereo Matching using Multi-resolution Images on CUDA },
journal = { International Journal of Computer Applications },
issue_date = { October 2012 },
volume = { 56 },
number = { 12 },
month = { October },
year = { 2012 },
issn = { 0975-8887 },
pages = { 47-55 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume56/number12/8947-3119/ },
doi = { 10.5120/8947-3119 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T20:58:41.570954+05:30
%A Sudhakar Sah
%A Nikhil Jotwani
%T Stereo Matching using Multi-resolution Images on CUDA
%J International Journal of Computer Applications
%@ 0975-8887
%V 56
%N 12
%P 47-55
%D 2012
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Stereo matching technique is used to estimate the depth of objects in an image acquired from real time scenes. The basic algorithm is not very complex but is computationally exhaustive and hinders its usage for real time applications. However, this algorithm is highly data parallel and it highly suitable for execution on GPGPU (General-purpose graphical processing units). In this paper, we are proposing the parallel implementation of the fast stereo matching algorithm based on correlation of multi-resolution images using CUDA (Compute Unified Device Architecture). The performance of this implementation is faster than most of the software implementations of this method and comparable with FPGA implementation and few other optimized methods mentioned in the references. This enables the real time usage of stereo matching method. We have also provided performance comparison and results for different methods of stereo matching on CUDA. The paper concludes with analysis of results and the reasons of the performance variations. We have also given qualitative image data for comparison of accuracy of different stereo correspondence methods.

References
  1. Sunil Kumar, K. , Desai, B. , U. 1994. "New Algorithm for 3D Surface Description and Binocular Stereo Using Integration",journal of Franklin Institute, Volume 331, Issue 5, September 1994, Pages 531–554.
  2. Sun, Changming. 1997. Fast Stereo Matching Method. In Digital Image Computing: Techniques and Applications.
  3. Satorre,Rossana. ,Compan, Patricia. , Botia, Antonio. , Rizo, Ramon. Multi Resolution Scheme for Stereo Correspondence using Correlation Techniques. University of Alicante.
  4. Zhu, Ke. ,Butenuth, Matthias. , D'Angelo, Pablo. 2010. Comparison of Dense Stereo Using CUDA. ECCV, Workshop `Computer Vision on GPUs´.
  5. Congote, John. ,Barandiaran, Javier. , Barandiaran, Inigo. , Ruiz, Oscar. 2009. Real Time Dense Stereo Matching with Dynamic Programming in CUDA. CEIG'09, San Sebastián.
  6. Geiger, Andreas. ,Roser, Martin. , Urtasun, Raquel. 2010. Efficient Large Scale Stereo Matching. In ProceedingACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I, Pages 25-38.
  7. Zhao, Yong. ,Taubin, Gabriel. "Real Time High Definition Stereo on GPGPU using Progressive Multi Resolution Adaptive Windows", Journal Image and Vision Computing, Volume 29 Issue 6, May, 2011, Pages 420-432.
  8. NVIDIA Corporation. , 2008. NVIDIA CUDA Programming Guide. Technical Report. California. USA.
  9. Middlebury Stereo Website (05. 2010). (http://vision. middlebury. edu/stereo/).
  10. Kimura, Yoshikatsu. , A Stereo Matching Method using Multi Resolution Images. R&D Review of Toyota CRDL Vol. 36 NO. 1 (2001. 3).
  11. Sun, Jian. , Li, Yin. , Bing Kang, Sing. , Shum, Heung-Yeung. 2005. Symmetric Stereo Matching for Occlusion Handling in proceedings CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02, Pages 399 – 406.
  12. Forstmann, Sven. ,Kanou, Yutuka. , Ohya, Jun. , Thuering, Sven. , Schmitt, Alfred. 2004. Real Time Stereo by Dynamic Programming, in Computer Vision and Pattern Recognition Workshop, 2004. CVPRW '04.
  13. Sabihuddin, Siraj. , Islam, Jamin. , MacLean, James. W. 2008. Dynamic Programming Approach to High Frame Rate Stereo Correspondence: APipelined Architecture Implemented on a Field Programmable Gate Array, in Electrical and Computer Engineering,CCECE'08.
  14. Kalraot, Ratheesh. , Morris, John. 2010. Comparison of FPGA and GPU Implementation of Real Time Stereo Vision, in Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE Computer Society.
Index Terms

Computer Science
Information Sciences

Keywords

Correlation Multi-Resolution images CUDA Stereo matching