Using the GPU for fast symmetry-based dense stereo matching in high resolution images

SymStereo is a new algorithm used for stereo estimation. Instead of measuring photo-similarity, it proposes novel cost functions that measure symmetry for evaluating the likelihood of two pixels being a match. In this work we propose a parallel approach of the LogN matching cost variant of SymStereo capable of processing pairs of images in real-time for depth estimation. The power of the graphics processing units utilized allows exploring more efficiently the bank of log-Gabor wavelets developed to analyze symmetry, in the spectral domain. We analyze tradeoffs and propose different parameter-izations of the signal processing algorithm to accommodate image size, dimension of the filter bank, number of wavelets and also the number of disparities that controls the space density of the estimation, and still process up to 53 frames per second (fps) for images with size 288 × 384 and up to 3 fps for 768 × 1024 images.

[1]  Cristiano Premebida,et al.  Can stereo vision replace a Laser Rangefinder? , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  David Berry,et al.  Analysis of Real-Time Stereo Vision Algorithms On GPU , 2012 .

[3]  Gabriel Taubin,et al.  Real-time stereo on GPGPU using progressive multi-resolution adaptive windows , 2011, Image Vis. Comput..

[4]  John Morris,et al.  Comparison of FPGA and GPU implementations of real-time stereo vision , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[5]  Koichi Ito,et al.  GPU implementation of phase-based stereo correspondence and its application , 2012, 2012 19th IEEE International Conference on Image Processing.

[6]  Michel Antunes,et al.  Stereo estimation of depth along virtual cut planes , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[7]  Ruigang Yang,et al.  Multi-resolution real-time stereo on commodity graphics hardware , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[8]  Ruigang Yang,et al.  Gain Adaptive Real-Time Stereo Streaming , 2007 .