基于偏微分方程的稠密视差图获取方法

Dense Disparity Map Estimation Approach Based on PDE

立体匹配是计算机视觉领域中的一个重要的热门研究课题,为了获得性能更优的稠密视差图,通过把偏微分方程理论运用于机器视觉中,提出了一种新的基于能量函数获取稠密视差图(disparity map)的方法,并首先分析了匹配点对在不同相对位置下对匹配项产生的影响;接着提出了适用于视差图的各向异性的热扩散方程,它不仅继承了Alvarez定义的正则项对初始视差图内部平滑和保持边缘不连续的特性,还通过引入图像的噪声屏蔽函数和二阶方向导数来分别控制对应视差图中不同区域的扩散速度和角点处的扩散方向;最后通过定义的正则项和匹配项来构造新的能量函数,并把基于区域匹配算法得到的视差图作为初始值,再利用最速下降法求解相应的最小能量泛函。实验结果表明,无论从视觉效果上,还是重构深度图的判别上,该新算法都取得了更优的性能。

Stereo matching is studied in the paper, which has been a very hot research topic at present. An energy based algorithm inspired by PDE and machine vision theory is proposed to estimate a dense disparity map between two images. Firstly, the effects of matching pairs at various relative positions to the attachment item are analyzed. Secondly, anisotropic heat diffusion equation adapts to disparity map is presented, which inherited from the ability of the Alvarez defining regularization item that keeping the discontinuities across the boundaries of the image and smoothing disparity inside the boundary. In addition image noise shielded function and second order directional derivative are introduced to separately control disparity diffusion velocity of different area and diffusion direction of edge position. At last, new energy function according to our approach is defined, adopting the output of the area stereo matching method as the initial value and steepest descent is exploited to solve the energy functional. Experiment results demonstrate the effectiveness of our approach, both in the visual effect and 3D depth retrieval.