基于图像空间的复杂模型碰撞检测算法

Image-space collision detection algorithm between complex models

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.