论文:2013,Vol:31,Issue(2):311-316
引用本文:
肖照林, 杨恒, 周果清, 王庆. 一种视差法与变焦法融合的深度估计方法[J]. 西北工业大学
Xiao Zhaolin, Yang Heng, Zhou Guoqing, Wang Qing. A Fused Estimation Method of Depth Based on Depth from Stereo and Depth from Focus[J]. Northwestern polytechnical university

一种视差法与变焦法融合的深度估计方法
肖照林, 杨恒, 周果清, 王庆
西北工业大学 计算机学院, 陕西 西安 710072
摘要:
视差法与变焦法是两种基于图像的三维重建方法,由于它们在所需数据集与深度计算方法上的差异,故具有不同的优势和应用场合。通过利用摄像机阵列,在获取多视点数据集的基础上,提出了一种视差法与变焦法融合的深度估计方法。先利用视差法选取候选深度集,然后利用视差法与变焦法结果的带权线性混合函数选取最终深度,从而解决了视差法与变焦法数据集的获取及单一方法对深度不连续区域鲁棒性较低的问题。实验结果表明该方法的可行性与优越性。
关键词:    深度估计    视差法    变焦法    摄像机阵列   
A Fused Estimation Method of Depth Based on Depth from Stereo and Depth from Focus
Xiao Zhaolin, Yang Heng, Zhou Guoqing, Wang Qing
Department of Computer Science and Engineering,Northwestern Polytechnical University,Xi'an 710072,China
Abstract:
Depth from stereo and depth from focus are two classical image-based 3D reconstruction methods,whichhave distinct advantages in different applications respectively. In this paper,we propose a fused depth recoverymethod based on depth from stereo and depth from focus. First,we choose some depth candidates using depth fromstereo method. Then,a weighted linear cost function is employed to determine the final depth. As we know,depthfrom stereo and depth from focus need different kinds of input images,which can not be acquired at the same timeby using traditional imaging system. We have preliminary tackled this issue by using a camera array system and synthetic aperture photography. Experiment results have verified the validity and advantages of proposed method.
Key words:    fused depth estimation    depth perception    depth from stereo    depth from focus    camera array   
收稿日期: 2012-04-19     修回日期:
DOI:
基金项目: 国家自然科学基金(61103060、61272287);教育部博士点基金(20116102110031)资助
通讯作者:     Email:
作者简介: 肖照林(1984-),西北工业大学博士研究生,主要从事计算机视觉、图像处理等研究。
相关功能
PDF(625KB) Free
打印本文
把本文推荐给朋友
作者相关文章
肖照林  在本刊中的所有文章
杨恒  在本刊中的所有文章
周果清  在本刊中的所有文章
王庆  在本刊中的所有文章

参考文献:
[1] Szeliski Richard. Computer Vision: Algorithms and Applications. Springer, 2010
[2] Steffen Herbort,Christian Wohler. An Introduction to Image-Based 3D Surface Reconstruction and a Survey of Photometric Ster-eo Methods. 3D Research, 2011, 2(3): 1-17
[3] Yoon K J,Kweon I S. Adaptive Support-Weight Approach for Correspondence Search. IEEE Trans on Pattern Analysis and Ma-chine Intelligence, 2006, 28(4): 650-656
[4] Boykov Y,Veksler O,Zabih R. Fast Approximate Energy Minimization via Graph Cuts. IEEE Trans on Pattern Analysis andMachine Intelligence, 2001, 23(11): 1222-1239
[5] Sun J,Zheng N N,Shum H Y. Stereo Matching Using Belief Propagation. IEEE Trans on Pattern Analysis and Machine Intelli-gence, 2003, 25(7): 787-800
[6] Zeng G,Paris S,Quan L,Sillion F. Progressive Surface Reconstruction from Images Using a Local Prior. Proc of ICCV, 2005,1230-1237
[7] Slabaugh G,Culbertson B,Malzbender T,Stevens M. Methods for Volumetric Reconstruction of Visual Scenes. Int'l J. Com-puter Vision, 2004, 57(3):179-199
[8] Kutulakos K,Seitz S. A Theory of Shape by Space Carving. Int'l J. Computer Vision, 2000, 38(3):199-218
[9] Eric Krotkov. Focusing. International Journal of Computer Vision, 1987, 1(3): 223-237
[10] Alex Pentland. A New Sense for Depth of Field. IEEE Trans on Pattern Analysis and Machine Intelligence, 1987, 9(4): 523-531
[11] Paolo Favaro. Recovering Thin Structures via Nonlocal-Means Regularization with Application to Depth from Defocus. IEEEComputer Society Conference on Computer Vision and Pattern Recognition, 2010, 1133-1140
[12] Shim Seong O,Choi Taesun. Depth from Focus Based on Combinatorial Optimization. Optics Letters,2010,35 (12):1956-1958
[13] Samuel W Hasinoff,Kiriakos N Kutulakos. Confocal Stereo. International Journal of Computer Vision, 2009, 81(1): 82-104
[14] Ashutosh Saxena,Sung H Chung,Andrew Y Ng. 3-D Depth Reconstruction from a Single Still Image. International Journal ofComputer Vision, 2008, 76(1): 53-69
[15] Johannes Burge, Wilson Geisler. Optimal Defocus Estimation in Individual Natural Images. Proceedings of the National Academyof Sciences of the United States of America, 2011, 108(40): 16849-16854
[16] Robert Held,Emily Cooper,Martin Banks. Blur and Disparity are Complementary Cues to Depth. Current Biology,2012,22(5): 1-6
[17] Schechner Y Y,Kiryati N. Depth from Defocus vs. Stereo: How Different Really Are They? Proc of ICPR, 1998, 1784-1786
[18] Levoy M,Hanrahan P. Light Field Rendering. Proc of ACM SIGGRAPH, 1996, 31-42
[19] Wilburn B,Joshi N,Vaish V,Talvala et al. High Performance Imaging Using Large Camera Arrays. ACM Trans on Graphics,2005, 24(3): 765-776
[20] Vaish V. Synthetic Aperture Imaging Using Dense Camera Arrays. Ph. D. Thesis, Dept of Computer Science, University of Stan-ford, 2007
[21] Ng Ren. Fourier Slice Photography. ACM Trans on Graphics, 2005, 24(3): 735-744
[22] Nayar S,Watanabe M,Noguchi M. Real-Time Focus Range Sensor. IEEE Trans on PAMI, 1996, 18(12): 1186-1198