基于GPU的实时球面化算法  

A graphics processing unit(GPU)-based real-time spherizing algorithm

作　　者：黄建彪[1] 陈国华[1] 张爱军[1] 周厉颖[1] 

机构地区：[1]北京化工大学机电工程学院,北京100029

出　　处：《北京化工大学学报（自然科学版）》2013年第1期109-114,共6页Journal of Beijing University of Chemical Technology(Natural Science Edition)

摘　　要：分析了球面映射算法速度过慢的原因,针对传统插值计算中普遍存在的速度与精度相互制约的问题,改进了现有的基于立体投影的半球面纹理映射模型,提出了基于GPU的球面化算法,使用CUDA并行编程实现双线性插值的并行计算。球面化实验表明该算法在保证输出精度的前提下,可获得10倍左右的加速比,显著提高了计算速度,可用于实时性较高的应用场合。The cause of the low speed of a sphere mapping algorithm has been analyzed. In order to reduce the in- teraction between speed and accuracy, which is common in traditional interpolation methods with existing sphere mapping algorithms, an improved hemisphere texture mapping model based on stereoscopic projection has been pro- posed, and a graphics processing unit （GPU）-based spherizing algorithm has been put forward, in which CUDA parallel programming was utilized to complete the parallel computing of bilinear interpolation. The experiments showed that the computing speed could be significantly increased with the new method, whilst ensuring output accu- racy. The method gave a speedup factor of almost 10, and it could be employed in fast real-time applications.

关 键 词：实时球面化 半球面纹理映射 立体投影 并行计算 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]