摘要
使用视觉计算实现视频增强现实遮挡处理,用非线性误差扩散模型提高了对极几何的求解精度;将全局和局部高斯核相结合,提高并加快了物体前景轮廓线的提取精度和速度;仅用轮廓线上的点进行立体匹配的方法加快了真实物体深度反求的速度.与其他方法相比,文中方法速度快、精确度较高.实验结果证明了该方法的正确性和可行性.
A few techniques are applied for occlusion handling in video-based augmented reality, Epipolar geometry constraint is calculated by nonlinear error propagation at initial time to accelerate the speed of stereo matching; global and local methods are integrated to extract foreground objects precisely; and only pixe[s on objects' contour are reprojected into 3D space to fasten the depth calculation process. In comparison with other algorithms, our algorithm has advantages of efficient computation, high accuracy and easy implementation. Experimental results show the correctness and feasibility of the algorithm.
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2007年第12期1624-1628,共5页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金重点项目(60533080)
关键词
增强现实
误差扩散
对极几何
高斯核混合
augmented reality
error propagation
epipolar geometry
Gaussian kernel mixture