%0 Journal Article
%T Research of 3D reconstruction and filtering algorithm based on depth information of Kinect<br>基于Kinect深度信息的实时三维重建和滤波算法研究
%A CHEN Xiao-ming
%A JIANG Le-tian
%A YING Ren-dong
%A <br>陈晓明
%A 蒋乐天
%A 应忍冬
%J 计算机应用研究
%D 2013
%I 
%X This paper analyzed and improved 3D reconstruction algorithm using the depth information from Kinect. To reduce noise, it proposed an improved bilateral filtering algorithm based on the signal structure. This new algorithm used a two-valued function to compute the weights of the filter, because the range of depth image data was already known. It also combined the RGB values and depth information of surrounding pixels to complement some missing depth information. The results show that the proposed algorithm has much better performance and efficiency, namely 6 times as fast as the original algorithm.
%K real-time 3D reconstruction
%K Kinect
%K 3D point cloud
%K noise analysis
%K depth image
%K bilateral filter
%K joint bilateral filter<br>实时三维重建
%K Kinect
%K 三维点云
%K 噪声分析
%K 深度图像
%K 双边滤波
%K 联合双边滤波
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=DD8ECC43358E540DE05488CE4B5B46A3&yid=FF7AA908D58E97FA&vid=340AC2BF8E7AB4FD&iid=E158A972A605785F&sid=DB29DCDE63A11F6A&eid=E2F55FDAFC844F27&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=0&reference_num=10