Adaptive disparity computation using local and non-local cost aggregations

Adaptive disparity computation using local and non-local cost aggregations
复制标题

使用本地和非本地成本聚合的自适应视差计算

DOI:
10.1007/s11042-018-6236-6
复制
发表时间:
2018-06
影响因子:
3.6
通讯作者:
Feng Jieqing
Feng Jieqing
中科院分区:
计算机科学4区
文献类型:
--
作者:
Dong Qicong;Feng Jieqing

文献摘要

参考文献

被引文献

相似文献

提出了一种新方法,通过从局部和非局部视差图中选择其中一个可选视差来自适应地计算立体匹配的视差。初始的两个视差图可从最先进的局部和非局部立体算法中获得。然后,选择更合理的视差。我们提出了两种选择视差的策略。一种基于左图像中的梯度幅值,这种方法简单且快速。另一种利用融合移动以理论上合理的方式结合两个提议的标记(视差图),这种方法更准确。最后,我们提出一种基于纹理的亚像素细化来细化视差图。使用Middlebury数据集的实验结果表明,所提出的两种选择策略都比单独的局部或非局部算法表现更好。此外,所提出的方法与许多在立体匹配中广泛使用的局部和非局部算法兼容。
A new method is proposed to adaptively compute the disparity of stereo matching by choosing one of the alternative disparities from local and non-local disparity maps. The initial two disparity maps can be obtained from state-of-the-art local and non-local stereo algorithms. Then, the more reasonable disparity is selected. We propose two strategies to select the disparity. One is based on the magnitude of the gradient in the left image, which is simple and fast. The other utilizes the fusion move to combine the two proposal labelings (disparity maps) in a theoretically sound manner, which is more accurate. Finally, we propose a texture-based sub-pixel refinement to refine the disparity map. Experimental results using Middlebury datasets demonstrate that the two proposed selection strategies both perform better than individual local or non-local algorithms. Moreover, the proposed method is compatible with many local and non-local algorithms that are widely used in stereo matching.
DOI: 10.1016/j.cviu.2019.02.001
发表时间: 2019-04
期刊: Comput. Vis. Image Underst.
影响因子: --
作者:
M. Park;Kuk-jin Yoon
通讯作者: M. Park;Kuk-jin Yoon
DOI: 10.1117/12.2083741
发表时间: 2015-03
期刊: --
影响因子: --
作者:
Yi-Jia Peng;Ge Li;Ronggang Wang;Wenmin Wang
通讯作者: Yi-Jia Peng;Ge Li;Ronggang Wang;Wenmin Wang
DOI: 10.1016/j.neucom.2014.12.081
发表时间: 2015-05
期刊: Neurocomputing
影响因子: 6
作者:
Yuan Tian-;Yan Long;Dan Xia;H. Yao;Jincheng Zhang
通讯作者: Yuan Tian-;Yan Long;Dan Xia;H. Yao;Jincheng Zhang
DOI: 10.1109/iccv.2017.174
发表时间: 2017-10
期刊: 2017 IEEE International Conference on Computer Vision (ICCV)
影响因子: --
作者:
Chao Zhou;Hong Zhang;Xiaoyong Shen;Jiaya Jia
通讯作者: Chao Zhou;Hong Zhang;Xiaoyong Shen;Jiaya Jia
DOI: 10.1109/icpr.2010.338
发表时间: 2010-08
期刊: 2010 20th International Conference on Pattern Recognition
影响因子: --
作者:
K. Ogawara
通讯作者: K. Ogawara