基于边缘检测的深度图与单视图配准算法

Registration of Depth and Video Data Based on Edge Detection

为解决由单视点图像和相关深度数据所创建的立体图像部分存在的重影问题,提出基于边缘检测的深度图与单视图配准算法。对单视图和深度图进行边缘检测得到各自的边界后,以单视图的边界为基准,配准深度图的边界及其邻域的深度数据。实验结果表明,该算法与已有的算法相比,匹配质量明显提高,使在立体图像中的重影现象得到了缓解。

Stereoscopic images created from video images and their associated depth data partly contain artifacts due to misalignment between depth and video data. To solve this problem, we present an algorithm of registration of depth and video data based on edge detection. First we use edge detection method to get the edge of the video image and the depth image respectively. Then we set the edge of the video image as the baseline to register the edge of the depth image. Experimental results show that by using the proposed algorithm the spatial alignment of depth and video data can be improved, leading to an alleviation of the observed artifacts in stereoscopic images.