cvpr cvpr2013 cvpr2013-147 cvpr2013-147-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Ralf Haeusler, Rahul Nair, Daniel Kondermann
Abstract: With the aim to improve accuracy of stereo confidence measures, we apply the random decision forest framework to a large set of diverse stereo confidence measures. Learning and testing sets were drawnfrom the recently introduced KITTI dataset, which currently poses higher challenges to stereo solvers than other benchmarks with ground truth for stereo evaluation. We experiment with semi global matching stereo (SGM) and a census dataterm, which is the best performing realtime capable stereo method known to date. On KITTI images, SGM still produces a significant amount of error. We obtain consistently improved area under curve values of sparsification measures in comparison to best performing single stereo confidence measures where numbers of stereo errors are large. More specifically, our method performs best in all but one out of 194 frames of the KITTI dataset.
[1] IEEE International Conference on Computer Vision Workshops, ICCV 2011 Workshops, Barcelona, Spain, November 6-13, 2011. IEEE, 2011. 8
[2] O. M. Aodha, A. Humayun, M. Pollefeys, and G. J. Brostow. Learning a Confidence Measure for Optical Flow. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2012. 2, 6
[3] K. Archer and R. Kimes. Empirical characterization of random forest variable importance measures. Computational Statistics & Data Analysis, 52(4):2249–2260, 2008. 4
[4] Authors. Supplemental material to CVPR 2013. Supplied as additional material 16 8 5 -Haeu s le r- sup .pdf. 6
[5] J. Banks and P. I. Corke. Quantitative evaluation of matching methods and validity measures for stereo vision. I. J. Robotic Res., 20(7):512–532, 2001. 1, 2
[6] L. Breiman. Random Forests. Machine Learning, 45(1):5– 32, 2001. 2, 4
[7] S. Gehrig and C. Rabe. Real-time Semi-Global Matching on the CPU. In Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on, pages 85 –92, june 2010. 4
[8] S. K. Gehrig and T. Scharw¨ achter. A real-time multi-cue framework for determining optical flow confidence. In ICCV Workshops [1], pages 1978–1985. 2
[9] A. Geiger, P. Lenz, and R. Urtasun. Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In Computer Vision and Pattern Recognition (CVPR), Providence, USA, June 2012. 1, 4
[10] R. Haeusler and R. Klette. Analysis of KITTI Data for Stereo Analysis with Stereo Confidence Measures. In A. Fusiello, V. Murino, and R. Cucchiara, editors, ECCV Workshops (2), volume 7584 of Lecture Notes in Computer Science, pages 158–167. Springer, 2012. 8
[11] H. Hirschm u¨ller. Stereo processing by semiglobal matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell., 30(2):328–341, 2008. 3, 4
[12] H. Hirschm u¨ller and D. Scharstein. Evaluation of cost functions for stereo matching. In CVPR, 2007. 4
[13] X. Hu and P. Mordohai. A quantitative evaluation of confidence measures for stereo vision. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2012. 1, 2
[14] D. Kong and H. Tao. Stereo matching via learning multiple experts behaviors. In M. J. Chantler, R. B. Fisher, and
[15]
[16]
[17]
[18]
[19]
[20]
[21] E. Trucco, editors, BMVC, pages 97–106. British Machine Vision Association, 2006. 1 U. K ¨othe. The VIGRA Computer Vision Library, Version 1.9.0, 2012. http : / /hc i iwr .un i . -he ide lbe rg . de /vigra / . 5 P. Merrell, A. Akbarzadeh, L. Wang, P. Mordohai, J.-M. Frahm, R. Yang, D. Nist e´r, and M. Pollefeys. Real-time visibility-based fusion of depth maps. In ICCV, pages 1–8, 2007. 1, 3 A. Motten, L. Claesen, and Y. Pan. Binary confidence evaluation for a stereo vision based depth field processor SoC. In Pattern Recognition (ACPR), 2011 First Asian Conference on, pages 456–460, 2011. 1 M. Okutomi, Y. Katayama, and S. Oka. A simple stereo algorithm to recover precise object boundaries and smooth surfaces. International Journal of Computer Vision, 47(13):261–273, 2002. 3 D. Pfeiffer, S. Gehrig, and N. Schneider. Exploiting the Power of Stereo Confidences. In CVPR. IEEE, 2013. 1 D. Scharstein and R. Szeliski. Stereo matching with nonlinear diffusion. International Journal of Computer Vision, 28(2): 155–174, 1998. 3 P. Steingrube, S. K. Gehrig, and U. Franke. Performance Evaluation of Stereo Algorithms for Automotive Applications. In M. Fritz, B. Schiele, and J. H. Piater, editors, ICVS, volume 5815 of Lecture Notes in Computer Science, pages 285–294. Springer, 2009. 4 333 111222