Texture discrimination-enforced matching cost computation and smoothness-weighted cost regularization for stereo matching
Texture discrimination-enforced matching cost computation and smoothness-weighted cost regularization for stereo matching
复制标题
用于立体匹配的纹理辨别强制匹配成本计算和平滑度加权成本正则化
DOI：
10.1117/1.jei.28.5.053025
复制
发表时间：
2019-10
影响因子：
1.1
通讯作者：
Luo Ying
中科院分区：
文献类型：
--
作者：
Xu Jinxin;Li Qingwu;Zhou Yan;Liu Yan;Luo Ying
抽象的。在立体匹配中，动态规划（DP）等能量最小化优化器可以实现有效的视差估计。然而，由于过多的人工惩罚参数和复杂的能量函数，基于DP的优化器仍然面临着相对较高的能量，不可避免地导致深度不连续、遮挡和低纹理区域的匹配失败。为了实现密集的高精度视差估计，我们提出了一种使用纹理辨别强制匹配成本计算和平滑度加权成本正则化的有效立体匹配方法。首先，将像素调整引入梯度差计算中，从而可以提高初始匹配精度，尤其是低纹理区域的精度。为了确定像素调整的程度，采用灰度梯度共生矩阵和模糊c均值方法来根据纹理属性区分两种参考图像。其次，利用局部方法中的支持权重和全局优化中的平滑约束。将输入图像的颜色信息和置信图组合起来形成支持权重。通过改进加权水平DP通道期间的平滑度约束函数，可以减少过度惩罚的不利影响。第三，提出了一种后处理方法，用于细化遮挡区域和低纹理区域的结果。所提出的方法考虑了来自 Middlebury v.2 和 v.3 数据集的测试用例，并且可以超越最先进的立体匹配算法。
Abstract. In stereo matching, energy-minimization optimizers such as dynamic programming (DP) could achieve efficient disparity estimation. However, DP-based optimizers still suffer from relatively high energy due to too many artificial penalty parameters and a complex energy function, inevitably leading to matching failure in depth discontinuities, occlusions, and low-textured regions. To reach dense high-accuracy disparity estimation, we propose an effective stereo-matching method using texture discrimination-enforced matching cost computation and smoothness-weighted cost regularization. First, pixel adjustment is introduced to the gradient difference calculation so that initial matching accuracy, especially in low-textured regions, can be improved. For determining the degree of pixel adjustment, a gray-gradient co-occurrence matrix and the fuzzy c-means method are adopted to differentiate between two varieties of reference images based on textural property. Second, the support weight in local methods and the smoothness constraints in global optimizations are leveraged. Color information and the confidence map of the input image are combined to form the support weight. By ameliorating the smoothness constraint function during weighted horizontal DP passes, the adverse effects of excessive penalty can be reduced. Third, a postprocessing method is proposed for refining results in both occluded and low-textured regions. The proposed method considers test cases from the Middlebury v.2 and v.3 datasets and can outperform the state-of-the-art stereo-matching algorithms.
登录
查看更多内容
DOI：
10.1186/s41074-016-0013-0
发表时间：
2017-12
影响因子：
--
作者：
S. Nahar;M. Joshi
通讯作者：
S. Nahar;M. Joshi
用于立体匹配的基于跨树、边缘和超像素先验的成本聚合
影响因子：
8
作者：
Cheng, Feiyang;Zhang, Hong;Sun, Mingui;Yuan, Ding
通讯作者：
Yuan, Ding
局部平滑强制成本量正则化以实现快速立体声对应
影响因子：
3.9
作者：
Yang Qingqing
通讯作者：
Yang Qingqing
DOI：
10.1109/tcsvt.2015.2513663
发表时间：
2017-05
影响因子：
8.4
作者：
Kang Zhang;Yuqiang Fang;Dongbo Min;Lifeng Sun;Shiqiang Yang;Shuicheng Yan
通讯作者：
Kang Zhang;Yuqiang Fang;Dongbo Min;Lifeng Sun;Shiqiang Yang;Shuicheng Yan
DOI：
10.1007/978-3-319-16808-1_22
发表时间：
2014-11
期刊：
--
影响因子：
--
作者：
M. Helala;F. Qureshi
通讯作者：
M. Helala;F. Qureshi