[1]唐望平 袁 华.基于前景检测的视差优化算法[J].大众科技,,():25.
点击复制

基于前景检测的视差优化算法
分享到:

《大众科技》[ISSN:1008-1151/CN:45-1235/N]

卷:
期数:
201403期
页码:
25
栏目:
信息技术与通信
出版日期:

文章信息/Info

Title:
Parallax optimization algorithm based on foreground detection
文章编号:
1008-1151(2014)03-0025-03
作者:
唐望平 袁 华
(桂林电子科技大学信息与通信学院,广西 桂林 541004)
关键词:
立体视觉视差优化立体匹配前景检测最小二乘法
Keywords:
Stereo vision parallax optimization stereo matching foreground detection least square method
分类号:
TN911.73
文献标志码:
A
摘要:
目前立体匹配算法分两类,传统的匹配算法通过计算两幅图的像素点相似程度,采用的是一种局部优先的方法。 而当前的策略主要将问题转化为求解能量方程,进而对全局空间进行优化,提高匹配精度,获得更好的视差图。但是在实际应 用过程中,由于光学失真和噪声,平滑表面的镜面反射,投影缩减,透视失真,低纹理和重复纹理等影响,导致误匹配或者找 不到匹配点,从而得不到有效视差。然而在特定的场合,可以利用有限的有效视差,基于前景检测以及最小二乘法,优化得到 较为完整的前景视差图
Abstract:
Currently, there are two types of stereo matching algorithms, the traditional stereo matching algorithm use a local optimum method by calculating the similarity of the pixels in two images. The current strategy is to create its energy equation, and then to optimize the global space, improve matching accuracy and obtain better disparity map. However, in practical application process, the photometric distortions and noise, specular surfaces, foreshortening, transparent objects and repetitive or ambiguous patterns will lead to false match or no match point, which lead to noneffective parallax. However, in certain situations, you can optimize the limited effective parallax to get a more complete disparity map, based on foreground detection and least square method.

参考文献/References:

[1] 章毓晋.图像工程[M].北京:清华大学出版社, 2006. [2] 伊传历,刘冬梅,宋建中.改进的基于图像分割的立体匹配 算法[J].计算机工程. 2008.[3] Daniel Scharstein, Richard Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J].International Journal of Computer Vision, 2002, 47(1/2/3): 7-42. [4] Boykow Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision [J].IEEE Transaction on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1124-1137. [5] Bleyer M, Gelautz M. A layered stereo algorithm using segmentation and global visibility constraions[J].ISPRS Journal of Photogrammetry and Remote Sensing,2005, 59(3): 128-150. [6] Bleyer M, Gelautz M. Graph-cut-based stereo matching using image segmentation with symmetrical treatment of occlusions[J].Signal Processing Image Communication. 2007, 22(2): 127-143. [7] Asmaa Hosni, Michael Bleyer, Margrit Gelautz, Christoph Rhemann. Local stereo matching using geodesic support weights-In international conference on image processing[J] 2009. TR-188-2-2009-08. [8] Qingxiong Yang, Liang Wang, Ruigang Yang, Henrik Stewenius,and David Nister, Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation, and Occlusion Handling, In IEEE Transactions on Pattern Analysis and Machine Intelligence[J].2009Vol.31, No.3, 492-504. [9] Xiaoyong Lin, Yu Liu and Wenzhan Dai. Study of Occlusions Problem in Stereo Vision. In IEEE Proceedings of the 7th World Congress on Intelligent Control and Automation. [C].2008, 5062-5067.

相似文献/References:

[1]曾日金 袁 华.双目立体视觉的障碍物检测方法综述[J].大众科技,,():37.
[2]曾日金 袁 华.双目立体视觉的障碍物检测方法综述[J].大众科技,2014,16(03):37.
[3]唐望平 袁 华.基于前景检测的视差优化算法[J].大众科技,2014,16(03):25.

备注/Memo

备注/Memo:
【收稿日期】2014-02-11 【基金项目】广西自然科学基金(No.2013GXNSFDA019030,2013GXNSFAA019331,2012GXNSFBA053014,2012GXNSFAA053231), 广西科技开发项目(桂科攻 1348020-6,桂科能 1298025-7),广西教育厅项目(No.201202ZD040, 201202ZD044,2013YB091)。 【作者简介】唐望平(1988-),男,湖南邵阳人,桂林电子科技大学信息与通信学院硕士研究生,研究方向为立体视觉、 双目立体测量。 【通讯作者】袁华(1975-),男,湖北宜昌人,桂林电子科技大学信息与通信学院讲师,研究方向为图像处理、智能信号 处理。
更新日期/Last Update: 1900-01-01