Article

Article title STEREO PAIR SAD CALCULATION OPTIMIZATION FOR DEPTH MAP RECONSTRUCTION IN REAL-TIME STEREO VISION SYSTEMS
Authors A.V. Chumachenko
Section SECTION II. NAVIGATION AND PROMPTING
Month, Year 03, 2013 @en
Index UDC 004.923
DOI
Abstract This paper presents SAD calculation optimization method for local stereo correspondence algorithms. The key point of the optimization is pre calculation of auxiliary two-dimensional sumsarray, which allows getting results of SAD-queries in constant time. Method allows to decrease the computational complexity of the main step of some local stereocorrespondence algorithm by two orders of magnitude for rectangular support windows and by one order for adaptive windows. Method is applicable to rectangular and adaptive support windows, can be implemented for systems with universal CPUs and does not assume any kind of vector operations to be used.

Download PDF

Keywords Stereo pair; pixel correspondence; correlation; support window; optimization; real-time stereo vision system; adaptive support window.
References 1. Sharstein D., Szeliski R. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms // International Journal of Computer Vision. – 2002. – Vol. 47, 1/3. – P. 7-42.
2. Xing Mei, Xun Sun, Mingcai Zhou, Shaohui Jiao, Haitao Wang, Xiaopeng Zhang. On building an accurate stereo matching system on graphics hardware // Computer Vision Workshops, 2011 IEEE
International Conference on Stereo Vision, date of Conference: 6-13 Nov. 2011. – P. 467-474.
3. Гузик В.Ф., Чумаченко А.В. Статистический метод оптимизации локальных алгоритмов установления пиксельных соответствий на стереопарах // Известия высших учебных заведений Северо-Кавказский регион. Технические науки. – 2011 – № 4. – С. 20-25.
4. Boykov Y., Veksler O. and Zabih R. Fast approximate energy minimization via graph cuts // International Conference of Computer Vision (ICCV). – 1999. – P. 377-384.
5. Lei C., Selzer J., and Yang Y. Region-tree based stereo using dynamic programming optimization // Computer Vision and Pattern Recognition. – 2006. – № 2. – Р. 2378-2385.
6. HajerFradi, Jean-Luc Dugelay. Improved depth map estimation in Stereo Vision. Conference of Stereoscopic Displays and Applications XXII, San Francisco, Vol. 7863, January 2011.
7. URL: http://www.eurecom.fr/fr/publication/3341/download/mm-publi-3341.pdf (дата обращения 02.12.2012).
8. Konstantin Kramer. Real-Time Stereo Vision System. Tel-Aviv academic college of Engineering, 2006.
9. URL: http://highlearn.afeka.ac.il/users/www/9357/files/projects/StereoVision.pdf, дата обращения 02.12.2012).
10. Heiko Hirschmuller, Peter R. Innocent, Jon Garibaldi. Real-Time Correlation-Based Stereo Vision with Reduced Border Errors // International Journal of Computer Vision. – 2002. – Vol. 47, 1/3. – P. 229-246.
11. Wannes van der Mark, Dariu M. Gavrila. Real-Time Dense Stereo for Intelligent Vehicles // IEEE Transactions on Intelligent Transportation Systems. – March 2006. – Vol. 7, №. 1. – Р. 38-50.
12. Yong Zhao, Gabriel Taubin. Real-time stereo on GPGPU using progressive multi-resolution adaptive windows // Image and Vision Computing. – 2011. – № 29. – Р. 420-432.
13. Форсайт Девид А., Понс Жан. Компьютерное зрение, Современный подход: Пер. с англ. – М.: Изд. дом "Вильямс", 2004. – 928 с.

Comments are closed.