Segment-based stereo matching using graph cuts
Segment-based stereo matching using graph cuts
复制标题
DOI：
10.1109/cvpr.2004.220
复制
发表时间：
2004-07
期刊：
影响因子：
--
通讯作者：
L. Hong;George Q. Chen
中科院分区：
文献类型：
--
作者：
L. Hong;George Q. Chen
本文提出了一种新的基于图割的分段立体匹配算法。在我们的方法中，参考图像被划分成非重叠的同质段和场景结构表示为一组平面在视差空间。将立体匹配问题转化为图像分割域的能量最小化问题，而不是传统的像素域。图割技术用于快速逼近最优解，为每个分割段分配相应的视差平面。实验表明，我们的算法的性能是最先进的立体声算法在不同的数据集。此外，强大的性能，实现了在传统的困难领域，如：无纹理区域，视差不连续的边界和闭塞的部分。
In this paper we present a new segment-based stereo matching algorithm using graph cuts. In our approach, the reference image is divided into non-overlapping homogeneous segments and the scene structure is represented as a set of planes in the disparity space. The stereo matching problem is formulated as an energy minimization problem in the segment domain instead of the traditional pixel domain. Graph cuts technique is used to fast approximate the optimal solution, which assigns the corresponding disparity plane to each segment. Experiments demonstrate that the performance of our algorithm is comparable to the state-of-the-art stereo algorithms on various data sets. Furthermore, strong performance is achieved in the conventionally difficult areas such as: textureless regions, disparity discontinuous boundaries and occluded portions.