Half-resolution semi-global stereo matching

Semi-global matching is a popular choice for applications where dense and robust stereo estimation is required and real-time performance is crucial. It therefore plays an important role in vision-based driver assistance systems. The strength of the algorithm comes from the integration of multiple 1D energy paths which are minimized along eight different directions across the image domain. The contribution of this paper is twofold. First, a thorough evaluation of stereo matching quality is performed when the number of accumulation paths is reduced. Second, an alteration of semi-global matching is proposed that operates only on half of the image domain without losing disparity resolution. The evaluation is performed on four real-world driving sequences of 400 frames each, as well as on 396 frames of a synthetic image sequence where sub-pixel accurate ground truth is available. Results indicate that a reduction of accumulation paths is a very good option to improve the run-time performance without losing significant quality, even on sub-pixel level. Furthermore, operating semiglobal matching only on half the image yields almost identical results to the corresponding full path integration. This approach yields the potential to further speed up the runtime and could also be exploited for other alterations of the algorithm.

[1]  T. Vaudrey,et al.  Differences between stereo and motion behaviour on synthetic and real-world stereo sequences , 2008, 2008 23rd International Conference Image and Vision Computing New Zealand.

[2]  Ines Ernst,et al.  Mutual Information Based Semi-Global Stereo Matching on the GPU , 2008, ISVC.

[3]  Stefan K. Gehrig,et al.  A Real-Time Low-Power Stereo Vision Engine Using Semi-Global Matching , 2009, ICVS.

[4]  Ramin Zabih,et al.  Non-parametric Local Transforms for Computing Visual Correspondence , 1994, ECCV.

[5]  H. Hirschmüller.  Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information , 2005, CVPR.

[6]  Masatoshi Okutomi,et al.  An analysis of sub-pixel estimation error on area-based image matching , 2002, 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628).

[7]  Heiko Hirschmüller,et al.  Evaluation of Stereo Matching Costs on Images with Radiometric Differences , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Jun-ichiro Toriwaki,et al.  New algorithms for euclidean distance transformation of an n-dimensional digitized picture with applications , 1994, Pattern Recognit..

[9]  Reinhard Klette,et al.  A Third Eye for Performance Evaluation in Stereo Sequence Analysis , 2009, CAIP.

[10]  Reinhard Klette,et al.  Inclusion of a Second-Order Prior into Semi-Global Matching , 2009, PSIVT.

[11]  Reinhard Klette,et al.  Illumination Invariant Cost Functions in Semi-Global Matching , 2010, ACCV Workshops.

[12]  Sergiu Nedevschi,et al.  Real-time semi-global dense stereo solution with improved sub-pixel accuracy , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[13]  Peter Wegner,et al.  A technique for counting ones in a binary computer , 1960, CACM.

[14]  Takeo Kanade,et al.  Stereo by Two-Level Dynamic Programming , 1985, IJCAI.

[15]  Reinhard Klette,et al.  Benchmarking Stereo Data (Not the Matching Algorithms) , 2010, DAGM-Symposium.