Analysis of KITTI data for stereo analysis with stereo confidence measures
作者： Ralf Haeusler , Reinhard Klette
DOI: 10.1007/978-3-642-33868-7_16
关键词:
摘要: The recently published KITTI stereo dataset provides a new quality of imagery with partial ground truth for benchmarking matchers. Our aim is to test the value confidence measures (e.g. left-right consistency check disparity maps, or an analysis slope local interpolation cost function at taken minimum) when applied recorded datasets, such as KITTI. We choose popular available in stereo-analysis literature, and discuss naive combination these. Evaluations are carried out using sparsification strategy. While best single measure proved be right-left high map densities, overall performance achieved proposed combination. argue that there still demand more challenging datasets comprehensive truth.
springer.com
acm.org 
sci-hub.se 参考文章(16)
Geoffrey Egnal, Mutual Information as a Stereo Correspondence Measure ,(2000)
Jasmine Banks, Peter Corke, Quantitative Evaluation of Matching Methods and Validity Measures for Stereo Vision The International Journal of Robotics Research. ,vol. 20, pp. 512- 532 ,(2001) , 10.1177/02783640122067525
Stefan K. Gehrig, Timo Scharwachter, A real-time multi-cue framework for determining optical flow confidence international conference on computer vision. pp. 1978- 1985 ,(2011) , 10.1109/ICCVW.2011.6130491
Ahmad Humayun, Oisin Mac Aodha, Gabriel J. Brostow, Learning to find occlusion regions CVPR 2011. pp. 2161- 2168 ,(2011) , 10.1109/CVPR.2011.5995517
Andreas Wedel, Thomas Brox, Tobi Vaudrey, Clemens Rabe, Uwe Franke, Daniel Cremers, None, Stereoscopic Scene Flow Computation for 3D Motion Understanding International Journal of Computer Vision. ,vol. 95, pp. 29- 51 ,(2011) , 10.1007/S11263-010-0404-0
O Mac Aodha, G J Brostow, M Pollefeys, Segmenting video into classes of algorithm-suitability computer vision and pattern recognition. pp. 1054- 1061 ,(2010) , 10.1109/CVPR.2010.5540099
Masatoshi Okutomi, Yasuhiro Katayama, Setsuko Oka, A simple stereo algorithm to recover precise object boundaries and smooth surfaces International Journal of Computer Vision. ,vol. 47, pp. 261- 273 ,(2001) , 10.1023/A:1014510328154
Xiaoyan Hu, Philippos Mordohai, Evaluation of stereo confidence indoors and outdoors computer vision and pattern recognition. pp. 1466- 1473 ,(2010) , 10.1109/CVPR.2010.5539798
Daniel Scharstein, Richard Szeliski, A taxonomy and evaluation of dense two-frame stereo correspondence algorithms International Journal of Computer Vision. ,vol. 47, pp. 7- 42 ,(2001) , 10.1023/A:1014573219977
Daniel Scharstein, Richard Szeliski, Stereo Matching with Nonlinear Diffusion International Journal of Computer Vision. ,vol. 28, pp. 155- 174 ,(1998) , 10.1023/A:1008015117424