Efficient Stereo Matching Using Histogram Aggregation with Multiple Slant Hypotheses
作者： Michel Antunes , João P. Barreto
DOI: 10.1007/978-3-642-38628-2_1
关键词:
摘要: This paper presents an enhancement to the recent framework of histogram aggregation [1], that enables improve matching accuracy while preserving a low computational complexity. The original algorithm uses fronto-parallel support window for cost aggregation, which leads inaccurate results in presence significant surface slant. We address problem by considering pre-defined set discrete orientation hypotheses window. It is shown single hypothesis Disparity Space Image usually representative large interval possible 3D slants, and handling slant disparity space has advantage avoiding visibility issues. also propose fast recognition scheme volume selecting most likely aggregation. experiments clearly prove effectiveness approach.
springer.com
sci-hub.st 参考文章(13)
Yi Ma, Stefano Soatto, Jana Košecká, S. Shankar Sastry, An Invitation to 3-D Vision Springer New York. ,(2004) , 10.1007/978-0-387-21779-6
Michael Bleyer, Christoph Rhemann, Carsten Rother, PatchMatch Stereo - Stereo Matching with Slanted Support Windows. british machine vision conference. pp. 1- 11 ,(2011) , 10.5244/C.25.14
Stefano Soatto, Yi Ma, S. Shankar Sastry, Jana Koseck, An Invitation to 3-D Vision: From Images to Geometric Models ,(2003)
Michael Ble, Carsten Rother, Pushmeet Kohli, Surface stereo with soft segmentation computer vision and pattern recognition. pp. 1570- 1577 ,(2010) , 10.1109/CVPR.2010.5539783
Yilei Zhang, Minglun Gong, Yee-Hong Yang, Local stereo matching with 3D adaptive cost aggregation for slanted surface modeling and sub-pixel accuracy international conference on pattern recognition. pp. 1- 4 ,(2008) , 10.1109/ICPR.2008.4761101
Dongbo Min, Jiangbo Lu, Minh N. Do, A revisit to cost aggregation in stereo matching: How far can we reduce its computational redundancy? international conference on computer vision. pp. 1567- 1574 ,(2011) , 10.1109/ICCV.2011.6126416
Daniel Scharstein, Chris Pal, Learning Conditional Random Fields for Stereo computer vision and pattern recognition. pp. 1- 8 ,(2007) , 10.1109/CVPR.2007.383191
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
A. Klaus, M. Sormann, K. Karner, Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure international conference on pattern recognition. ,vol. 3, pp. 15- 18 ,(2006) , 10.1109/ICPR.2006.1033
Kuk-Jin Yoon, In So Kweon, Adaptive support-weight approach for correspondence search IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 28, pp. 650- 656 ,(2006) , 10.1109/TPAMI.2006.70