A pixel dissimilarity measure that is insensitive to image sampling, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.20, issue.4, pp.401-406, 1998. ,
Simple but effective tree structures for dynamic programming-based stereo matching, International Conference on Computer Vision Theory and Applications (VISAPP), pp.415-422, 2008. ,
Efficient belief propagation for early vision, International journal of computer vision, vol.70, issue.1, pp.41-54, 2006. ,
Are we ready for autonomous driving? the kitti vision benchmark suite, Computer Vision and Pattern Recognition (CVPR), 2012. ,
Stereo processing by semiglobal matching and mutual information, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.30, issue.2, pp.328-341, 2008. ,
Realtime correlation-based stereo vision with reduced border errors, International Journal of Computer Vision, vol.47, issue.1-3, pp.229-246, 2002. ,
Evaluation of cost functions for stereo matching, IEEE Computer Vision and Pattern Recognition (CVPR), pp.1-8, 2007. ,
Evaluation of stereo matching costs on images with radiometric differences, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.31, issue.9, pp.1582-1599, 2009. ,
Segmentbased stereo matching using belief propagation and a selfadapting dissimilarity measure, IEEE International Conference on Pattern Recognition, vol.3, pp.15-18, 2006. ,
Comparison of energy minimization algorithms for highly connected graphs, ECCV, pp.1-15, 2006. ,
Computing visual correspondence with occlusions using graph cuts, IEEE International Conference on Computer Vision, vol.2, pp.508-515, 2001. ,
Joint optimization for object class segmentation and dense stereo reconstruction, International Journal of Computer Vision, pp.1-12, 2012. ,
Anisotropic local high-confidence voting for accurate stereo correspondence, Proc. SPIE-IS&T Electronic Imaging, vol.6812, pp.605822-605823, 2008. ,
On building an accurate stereo matching system on graphics hardware, IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp.467-474, 2011. ,
Outdoor stereo camera system for the generation of real-world benchmark data sets, Optical Engineering, vol.51, issue.02, p.21107, 2012. ,
Crosscomparison census for colour stereo matching applied to intelligent vehicle, Electronics Letters, vol.48, issue.24, pp.1530-1532, 2012. ,
Ground truth evaluation of stereo algorithms for real world applications, Computer Vision-ACCV 2010 Workshops, pp.152-162, 2011. ,
Depth estimation using monocular and stereo cues, IJCAI, 2007. ,
A taxonomy and evaluation of dense two-frame stereo correspondence algorithms, International journal of computer vision, vol.47, issue.1, pp.7-42, 2002. ,
A local adaptive approach for dense stereo matching in architectural scene reconstruction, 2013. ,
A comparative study of energy minimization methods for markov random fields with smoothness-based priors, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.30, issue.6, pp.1068-1080, 2008. ,
Real-time dense stereo for intelligent vehicles, IEEE Transactions on Intelligent Transportation Systems, vol.7, issue.1, pp.38-50, 2006. ,
Non-parametric local transforms for computing visual correspondence, pp.151-158, 1994. ,
Cross-based local stereo matching using orthogonal integral images, IEEE Transactions on Circuits and Systems for Video Technology, vol.19, pp.1073-1079, 2009. ,
, Ground truth for image a1)
, Visible left image nr. 2 (d1) Groud truth for image c1)
, CZA : C ADCensus : 8.81% (b5) GC : C ADCensus : 9.20% (c5) CZA : C ADCensus : 11.27% (d5) GC : C ADCensus, p.20
, CZA : C klaus : 11.99% (b6) GC : C klaus : 22.09% (c6) CZA : C klaus : 14.96% (d6) GC : C klaus, p.82
, CZA : C Dif f CCC : 8.65% (b7) GC : C Dif f CCC : 7.22% (c7) CZA : C Dif
, CZA : C Dif f CT : 7.89% (b8) GC : C Dif f CT : 8.05% (c8) CZA : C Dif f CT : 11.56% (d8) GC : C Dif f CT : 14.22%
, On the following lines are the output disparity maps corresponding to different functions: on the first ( a2-a10) and third column ( b2-b10) the output obtained with the cross zone aggregation (CZA) algorithm, while on columns two (b2-b10) and fourth (d2-d10) the output of the graph cuts algorithm, Comparison between cost functions. On first row there are presented two left visible images ( a1 and c1) from the KITTI dataset with the corresponding ground truth disparity images ( b1 and d1 ), vol.4