首页> 外文会议>International FLINS conference >Optimization of the body part recognition method of 3D human mesh based on propagation algorithm
【24h】

Optimization of the body part recognition method of 3D human mesh based on propagation algorithm

机译:基于传播算法的3D人体网格物体部位识别方法的优化

获取原文

摘要

Armhole specify is the base of base in 3D digital human mannequin measuring. Finding the key body part armpit is very important in the process of measuring and modeling 3D digital human polygon mannequin, especially these meshes are raw and incomplete. A recognition method by propagation algorithm which can distinguish body parts automatically has been applied in industrial production. However, this method also has the contradiction of recognition precision and speed. In this paper, we present a new method for optimizing the step of the "Isolation Plane" using binary search like method. Based on the optimized step, both recognition speed and accuracy are greatly increased. The effectiveness of our method has been validated by more than 2000 mannequins. It can also be applied for specifying other body.
机译:袖孔指定是3D数字人体模特测量的基础。在3D数字人体多边形人体模型的测量和建模过程中,找到人体关键部位的腋窝非常重要,尤其是这些网格物体是原始且不完整的。能够自动识别身体部位的基于传播算法的识别方法已经在工业生产中得到了应用。但是,该方法也存在识别精度和速度矛盾。在本文中,我们提出了一种新的方法,该方法使用类似于二进制的搜索方法来优化“隔离平面”的步骤。基于优化的步骤,可以大大提高识别速度和准确性。我们的方法的有效性已被2000多个人体模型验证。它也可以用于指定其他主体。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号