A New Stereo Matching Algorithm based on Variable Windows using Frequency Information in DWT Domain

In this paper we propose a new stereo matching algorithm which is suitable for application to obtain depth information with high-speed in stereoscopic camera environment. For satisfying these condition we propose a new adaptive stereo matching technique using frequency information in discrete wavelet (DWT) domain and variable matching window. The size of the matching window is selected by analysis of the local property of the image in spatial domain and the feature and scaling factor of the matching window is selected by the frequency property in the frequency domain. For using frequency information we use local DWT and global DWT. We identified that the proposed technique has better peak noise to signal ratio (PSNR) than the fixed matching techniques with similar complexity.

[1]  Ignazio Gallo,et al.  Neural disparity computation for dense two-frame stereo correspondence , 2008, Pattern Recognit. Lett..

[2]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[3]  Aggelos K. Katsaggelos,et al.  Dense Disparity Estimation with a Divide-and-Conquer Disparity Space Image Technique , 1999, IEEE Trans. Multim..

[4]  Darius Burschka,et al.  Advances in Computational Stereo , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Takeo Kanade,et al.  Stereo by Intra- and Inter-Scanline Search Using Dynamic Programming , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Georgios Ch. Sirakoulis,et al.  Real-time disparity map computation module , 2008, Microprocess. Microsystems.

[7]  Dongil Han,et al.  Real-time object segmentation using disparity map of stereo matching , 2008, Appl. Math. Comput..

[8]  Kim Bong-Gyum,et al.  Stereo Matching using Belief Propagation with Line Grouping , 2005 .

[9]  Peter N. Belhumeur,et al.  A Bayesian approach to binocular steropsis , 1996, International Journal of Computer Vision.