摘要
提出一种使用图形硬件用于复杂模型间的快速的碰撞检测算法。算法是基于CULLIDE的执行GPU可见性查询来减少物体模型间没有邻近特征的子集,描述了一个分类方案计算物体潜在碰撞集和碰撞自由子集,提高了裁减的性能。为了减少CPU的负载,利用GPU的可编程性,在GPU上进行精确的物体相交计算。
A fast collision detection algorithm is presented between complex models using graphics hardware. The algorithm is based on CULLIDE which using GPU to eliminate a subset of geometric primitives that are not in close proximity. A novel visibility-based classification scheme is described to compute potentially-colliding and collision-free subsets of objects and primitives, which considerably improves the culling performance. For balancing the load between CPU and GPU, precise intersection is calculated on GPU.
出处
《计算机工程与设计》
CSCD
北大核心
2007年第15期3675-3677,3681,共4页
Computer Engineering and Design
