检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:雍伟[1] 吴壮志[2] 吴明磊[1] 刘何庆[1] 卜伟平[1] 王兴伟[1] 贾银芳
机构地区:[1]空军航空医学研究所,北京100142 [2]北京航空航天大学,北京100191 [3]百度公司,北京100193
出 处:《人类工效学》2016年第1期1-6,共6页Chinese Journal of Ergonomics
摘 要:目的人体测量项目是由测点定义的,在三维非接触人体测量中,测点识别是人体测量的关键。为快速有效地实现头面部测点的识别,本文研究提出了一种基于模板变形的三维人体头面部测点自动识别方法。方法建立了一个标注了50个测点的三维人体头面部三角网格模型作为模板网格,每个被测者的三维头面部扫描模型作为目标模型。首先通过自动查找模板网格和目标模型上对应的14个特征点作为约束进行初始变形,将模板网格变形为接近目标模型的最小二乘网格;然后进行精细配准,即在目标模型上不断增加与模板网格的顶点相对应的点进行变形配准。经过迭代计算,最终将模板网格变形为一个拓扑上与模板网格一致、几何上逼近目标模型的头部网格;最后,变形后的模板网格上测点即为目标模型的测点。结果对42名志愿者的三维扫描模型,将本方法所得到的测点与按照测点定义基于人体头面部几何特征所确定的测点进行对比。结果表明,以测点定义所确定的测点为圆心,用本方法所得到的测点,85%以上都落在半径为6mm圆内。结论本研究建立的方法实现了三维头面部测点的自动识别,对特征不明显的测点也能够达到较好的识别,对提高大样本三维头面部人体测量工作的效率有重要意义。Objective The anthropometrical items are defined by landmarks. The landmark recognition is the key step in the noncontact 3D scanning anthropometry. A template - based method for landmark recognition on 313 human head and face is proposed for the landmarks acquiring automatically and efficiently. Methods A standard 3D human head and face triangular mesh labeled with 50 landmarks is built as a template mesh, and each scanned human head and face model is regarded as target model. First,the initial deformation is guided by 14 pairs of corresponding feature point~ between template mesh and target model which are automatically found, a least - squares mesh similar to the target model is created at this time. Then for the fine fitting,we find more correspondence points iteratively to improve mesh quality. Template mesh is approached to target model within error range via iteration, finally the mapping relation between template mesh and target model is built. So the landmarks on deformed template mesh can be regarded as ones of the target model. Results There is a comparison of landmark recognition between this method and that meth- od based on the geometric characteristics with 42 volunteer 3D head and face scan images. The test showed that more than 85% landmarks obtained by this method are distributed within a 6mm radius circle centered in the landmarks ob- tained by the geometric characteristics. Conclusion The landmark recognition on 3D human head and face can auto- matically obtained by the template - based method. This method also can achieve a better recognition for the unobvious landmarks. It is efficiency for large scale anthropometrical measurement.
关 键 词:人体测量 三维扫描 测点识别 模板配准 非接触测量 军事工效 飞行员 计算机图形学
分 类 号:TP391.4[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.143.228.88