Handling occlusions in augmented reality based on 3D reconstruction method
Handling occlusions in augmented reality based on 3D reconstruction method
复制标题
DOI：
10.1016/j.neucom.2014.12.081
复制
发表时间：
2015-05
期刊：
影响因子：
6
通讯作者：
Yuan Tian-;Yan Long;Dan Xia;H. Yao;Jincheng Zhang
中科院分区：
文献类型：
--
作者：
Yuan Tian-;Yan Long;Dan Xia;H. Yao;Jincheng Zhang
真实的物体和虚拟物体之间的正确关系对于真实感增强现实系统至关重要，其中遮挡处理方法应该能够估计真实的物体和虚拟物体之间的空间关系，以及实时自动处理相互遮挡。为了同时完成上述任务，我们提出了一种新的基于三维重建的遮挡处理方法，该方法包括离线阶段和在线阶段。在离线阶段，我们使用低成本的RGB-D相机获得真实的场景的深度图。然后，获得每个点在全局坐标系中的3D坐标，并将其用于在线遮挡处理阶段。在在线阶段，我们设计了一种基于GPU的三维点云对齐方法，以点到切平面的距离作为误差度量，以加快收敛速度，减少迭代次数。然后通过比较真实的物体和较小区域内虚拟物体的每个像素的Z坐标值，自动获得真实的物体和虚拟物体之间的正确关系，以达到实时性。更具体地说，我们可以判断和处理相互遮挡没有人的交互在真实的时间，实验结果证明了它的有效性。
The correct relationships between real and virtual objects are of utmost importance to a realistic augmented reality system, in which the occlusion handling method should be able to estimate the spatial relationships between real and virtual objects, as well as handle the mutual occlusion automatically in real-time. To accomplish the above tasks simultaneously, we propose a novel occlusion handling method based on 3D reconstruction, which consists of offline stage and online stage. In the offline stage, we get the depth map of the real scene using a low cost RGB-D camera. Then the 3D coordinate of each point in the global coordinate system are obtained and will be used in the online occlusion handling stage. In the online stage, we design a GPU based 3D point clouds alignment method by using point to tangent plane distance as error metric to accelerate the convergence speed and reduce the iterations. The correct relationships between real and virtual objects are then obtained automatically by comparing each pixel’sZcoordinate value of real objects with that of virtual objects in a smaller region to achieve real-time performance. More specifically, we can judge and handle the mutual occlusion without human interactivity in real time, and experimental results prove its effectiveness.