基于稀疏测量的稠密视差图重构研究

关于视差图的估计方法有很多,本文提出了一种基于传感压缩理论只需少量测试就可以估计视差图的方法。这种方法只需使用整个图像的大约5%的信息就可以精确地重构视差图。为此我们提出了一个共轭梯度法用于解决优化问题,该方法对恢复大型系统的视差图是有效地。实验证明在噪声环境下我们所提出的方法有效并具有鲁棒性。

Research on Reconstruction of Dense Disparities Map Using Sparse Measurement

There are many methods to estimate the disparity maps.We propose a algorithm,which based on comprehensive sensing and can estimate the disparity maps with few measurements.Only about five percent information of the entire map can be used to accurately reconstruct the disparity map.In view of this,we propose a method of conjugate gradient to solve the problem met in the process of optimization.This method is of high efficiency when reconstructing a disparity map of large system.Experiments show that our method is effective and robust in the noise environment.