Optimizing Census-based Semi Global Matching by genetic algorithms

Recent years have shown a great progress in self-driving vehicles and stereovision has proven to be a key aspect towards this goal. Semi-Global Matching (SGM) algorithm is among the best stereo solutions, capable of producing reliable results at reasonable cost. Census transform is generally preferred as a cost metric due to its robustness and invariance to lighting conditions. This paper proposes an original methodology for finding both the optimal Census mask and the best values for the penalties P1 and P2 in SGM by using genetic algorithms (GA). The obtained census masks are thoroughly analyzed and the best ones can be combined in a weighted center-symmetric census to increase the performance of SGM. Kitti test cases show that our GA-based censuses as well as our novel weighted center-symmetric census outperform dense, sparse and center-symmetric counterparts for Census only and SGM.

[1]  Sergiu Nedevschi,et al.  Statistical method for sub-pixel interpolation function estimation , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

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

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

[4]  Peter Pirsch,et al.  Evaluation of Penalty Functions for Semi-Global Matching Cost Aggregation , 2012 .

[5]  Raúl Rojas,et al.  Weighted Semi-Global Matching and Center-Symmetric Census Transform for Robust Driver Assistance , 2013, CAIP.

[6]  Carlo Tomasi,et al.  Depth Discontinuities by Pixel-to-Pixel Stereo , 1999, International Journal of Computer Vision.

[7]  Heiko Hirschmüller,et al.  Stereo Processing by Semiglobal Matching and Mutual Information , 2008, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Sergiu Nedevschi,et al.  SORT-SGM: Subpixel Optimized Real-Time Semiglobal Matching for Intelligent Vehicles , 2012, IEEE Transactions on Vehicular Technology.

[9]  Maziar Loghman,et al.  SGM-based dense disparity estimation using adaptive Census transform , 2013, 2013 International Conference on Connected Vehicles and Expo (ICCVE).

[10]  Thomas Greiner,et al.  Matching cost computation algorithm and high speed FPGA architecture for high quality real-time Semi Global Matching stereo vision for road scenes , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[11]  Sergiu Nedevschi,et al.  GPU optimization of the SGM stereo algorithm , 2010, Proceedings of the 2010 IEEE 6th International Conference on Intelligent Computer Communication and Processing.

[12]  Markus Vincze,et al.  A fast stereo matching algorithm suitable for embedded real-time systems , 2010, Comput. Vis. Image Underst..

[13]  Sergiu Nedevschi,et al.  New sub-pixel interpolation functions for accurate real-time stereo-matching algorithms , 2015, 2015 IEEE International Conference on Intelligent Computer Communication and Processing (ICCP).

[14]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Raúl Rojas,et al.  Large scale Semi-Global Matching on the CPU , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[16]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[17]  James K. Archibald,et al.  Improved Census Transforms for Resource-Optimized Stereo Vision , 2013, IEEE Transactions on Circuits and Systems for Video Technology.