改进的边界距离变换算法在虚拟内窥镜中应用

Application of Improved Boundary Distance Transform Algorithm In Virtual Endoscope

为提高虚拟内窥镜实现中提取中心路径的时间效率,改善虚拟内窥镜的实时漫游,边界距离变换算法是提取中心路径的常用算法。上述算法在建立边界距离场和源距离场时非常耗时,故实时性很差。针对建立两个场非常耗时的缺点,提出定义超大数组,建立体素点ID值和体素点在体素点集中位置的一一对应关系,减少在确定体素点位置时对体素集的扫描次数,从而提高算法的效率。实验结果表明,改进后的算法时间效率高,实时漫游效果好,速度快,提取的中心路径漫游效果好,实现了虚拟漫游效果,具有一定的实际应用与理论研究价值。

To improve the time efficiency of extraction of centerline in the realization of virtual endoscope, and improve the real-time roaming, border distance transform algorithm is a common algorithm. However, the above algorithm in establishing border distance and the source distance field is very time consuming, so the real-time performance is very poor. To overcome the shortcoming in establishing the two fields, a super big array is defined, correspondence between vixel points＇ ID and its position in voxel points set is established, and numbers of scan in establishing the voxel points position is reduced, so it can improve time efficiency of the algorithm. Experimental results show that the improved algorithm has high time efficiency, good effect of real-time roaming.