In this paper, we have proposed a novel method for stereo disparity estimation by combining the existing methods of block based and region based stereo matching. Our method can generate dense disparity maps from disparity measurements of only 18% pixels of either the left or the right image of a stereo image pair. It works by segmenting the lightness values of image pixels using a fast implementation of K-Means clustering. It then refines those segment boundaries by morphological filtering and connected components analysis, thus removing a lot of redundant boundary pixels. This is followed by determining the boundaries' disparities by the SAD cost function. Lastly, we reconstruct the entire disparity map of the scene from the boundaries' disparities through disparity propagation along the scan lines and disparity prediction of regions of uncertainty by considering disparities of the neighboring regions. Experimental results on the Middlebury stereo vision dataset demonstrate that the proposed method outperforms traditional disparity determination methods like SAD and NCC by up to 30% and achieves an improvement of 2.6% when compared to a recent approach based on absolute difference (AD) cost function for disparity calculations [1].

中文翻译：

---

基于立体视觉的稀疏视差估计的视差计算混合算法

在本文中，我们通过结合现有的基于块和基于区域的立体匹配方法，提出了一种新的立体视差估计方法。我们的方法可以从立体图像对的左侧或右侧图像的仅 18% 像素的视差测量中生成密集视差图。它的工作原理是使用 K-Means 聚类的快速实现来分割图像像素的亮度值。然后通过形态过滤和连通分量分析细化这些段边界，从而去除大量冗余边界像素。然后通过 SAD 成本函数确定边界的差异。最后，我们从边界重建整个场景的视差图 通过沿扫描线的视差传播和通过考虑相邻区域的视差对不确定区域进行视差预测。在 Middlebury 立体视觉数据集上的实验结果表明，与基于绝对差异 (AD) 成本函数的最新方法相比，所提出的方法比 SAD 和 NCC 等传统视差确定方法的性能提高了 30%，并实现了 2.6% 的改进。视差计算 [1]。