基于决策树分类的体绘制加速技术  

Decision trees for accelerating rendering model

作　　者：马素静[1] 刘旭敏[1] 

机构地区：[1]首都师范大学信息工程学院,北京100037

出　　处：《计算机应用》2007年第11期2770-2772,2792,共4页journal of Computer Applications

基　　金：北京市教育委员会科技发展计划基金面上项目(KM200410028013);北京市教育委员会科技发展计划重点项目(KZ200710028014)

摘　　要：为了提高体绘制速度,提出一种新的算法。该算法通过决策树对体素分类,同时采用行程编码辅助模型存储决策树分类结果。在遍历体素模型时,只访问感兴趣的体素分类,而忽略那些空的和不感兴趣的体素分类,减少了体素的计算量。实验结果表明,此算法不仅保持了图像的绘制质量,而且明显提高了体绘制速度。In order to increase the speed of rendering model, a new accelerating algorithm was proposed, which used the decision tree to classify the segmented voxels into categories and used the run-length encoding （RLE） to memorize the categories. Whenever the voxel model was traversed, only the selected categories were visited and the empty and non-selected voxels were skipped. The results show that the voxel model not only preserves the quality of the images but also significantly accelerates the volume rendering.

关 键 词：体绘制 加速 决策树 行程编码 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]