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:贾晖 张建刚[2] JIA Hui;ZHANG Jian-gang(School of Computer Science,Xi’an University of Posts and Telecommunications,Xi’an 710121,China;Technological Department of Power Station Information and Monitoring,Xi’an Thermal Power Research Institute Co.,Ltd.,Xi’an 710032,China)
机构地区:[1]西安邮电大学计算机学院,陕西西安710121 [2]西安热工研究院有限公司电站信息及监控技术部,陕西西安710032
出 处:《计算机技术与发展》2019年第11期21-26,共6页Computer Technology and Development
基 金:国家自然科学基金面上项目(61572399);国家自然科学青年项目(71501156);陕西省教育专项科研计划项目(15JK1656)
摘 要:为提高三维模型集一致性分割算法的准确率,提出一种基于谱聚类和SDF特征的三维模型集一致性分割算法。该算法在具有相似形状特征的模型上进行。选择对模型集上各个模型的部位相似性具有较好表现的SDF特征来描述部位的相似程度。首先提取模型集中各个模型的面片SDF特征;其次计算模型各面片之间的形状相似性,形成相似性矩阵,并用测地距离对相似性矩阵进行稀疏化。即只考虑在一定距离范围内的形状相似性,超过该范围即使形状相似也不属于一个划分。最后采用谱聚类算法对模型集进行一致性分割。将该算法与相关方法进行对比,实验结果表明,该算法能够对具有类似形状的模型集中的各个模型进行有意义的一致性分割,使得分割部位具有一定的对应关系,且面片平均划分准确率较好。同时,对于模型面片简化具有较好的分割稳定度。In order to improve the accuracy of 3D model set consistency segmentation algorithm,we propose an algorithm of 3D model set consistency segmentation based on spectral clustering and SDF,which is applied to the models with similar shape characteristics.The similarity of the parts is described by SDF feature which has a better representation of the part similarity of each models in the model set.At first,the face SDF feature of each model in the model set is extracted,and then the similarity between each face of the model is calculated to form similarity matrix which is sparse by the geodesic distance.That is to say,only the shape similarity within a certain distance range is considered,even the shape similarity beyond this range does not belong to a division.At last we utilize the spectral clustering algorithm to segment the model set consistently.Compared with relevant methods,the experiment shows that the proposed algorithm can consistently segment the models of the model set meaningfully,so that the segmentation parts have a certain correspondence,and the average segmentation accuracy is superior.At the same time,it has superb segmentation stability for the simplification of model surface.
分 类 号:TP301.6[自动化与计算机技术—计算机系统结构]
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:216.73.216.28