快速检索:      
引用本文:
【打印本页】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
过刊浏览    高级检索
本文已被:浏览 156次   下载 15  
分享到: 微信 更多
基于结构相似性的高准确度深度获取及其应用
郭文凤,张倩,王斌,黄继风,郑鑫
作者单位E-mail
郭文凤 上海师范大学 1032234903@qq.com 
张倩 上海师范大学 qianzhang@shnu.edu.cn 
王斌 上海师范大学  
黄继风 上海师范大学  
郑鑫 上海师范大学  
摘要:
在3D视频中,深度是核心关键信息。Kinect深度图在采集的过程中由于受到设备自身及采集环境的影响,使得采集到的图像中存在大量的空洞,以致很难提取到高准确度的深度信息。针对以上问题,本文提出一种基于Kinect的高准确度深度获取算法,先对背景深度图做基于形态学滤波的填充,再分离深度图的前景和背景,针对空洞出现的区域做不同的处理,背景空洞进行基于背景深度值的填充,前景空洞采用颜色匹配和结构相似性结合的算法填充,得到最终的深度图,实验证明该算法在背景复杂的场景中能有效地填充深度图中的空洞,而且能保持物体的边缘细节,取得较好的虚拟视点质量。
关键词:  深度图  深度获取  空洞填充  深度图像绘制
DOI:
分类号:
基金项目:
The Acquisition of High Accuracy Depth Image and Its Application Based on Structural?Similarity
guowenfeng,zhangqian,wangbin,huang jifeng,zheng xin
Abstract:
In 3D video, depth is the core of key information. Because of the influence of the equipment itself and the acquisition environment, the depth map of Kinect has a large number of holes in the depth image, so it is difficult to extract the depth information with high accuracy. To solve the above problems, an algorithm based on Kinect for high accuracy depth image acquisition is proposed, which uses morphological filtering to fill the hole of the background texture map from Kinect. Then the foreground and background of the depth image obtained from the Kinect were separated . Making different treatment for the area in the hole. The background hole is filled with the corresponding background value, and the foreground hole is filled with the algorithm of color matching and structural similarity to obtain the reliable depth image. The experimental results show that this algorithm not only can effectively fill the void depth in complex background environment, but also can keep the edge of the object details, which can get better virtual viewpoint quality image.
Key words:  depth map  depth acquisition  The filling of hole  Depth image based on rendering