中文摘要：

针对快速、高效的三维模型形状分析与匹配技术的迫切需求,提出了融合内蕴热核特征与局部体积特征的三维模型对应形状分析方法。首先,通过拉普拉斯映射以及热核分布提取模型的内蕴形状特征;其次,结合模型热核特征的稳定性与局部空间体积的显著性,建立特征匹配矩阵;最后,通过特征矩阵相似性度量及最短路径搜索实现模型的配准与形状匹配分析。实验结果表明,融合热核距离以及局部体积约束的形状分析方法不仅有效地提高了模型匹配的效率,而且能够有效地识别同一类模型的结构特征,可以应用于进一步实现多组模型的协同分割与模型检索。

英文摘要：

Aiming at the urgent requirement of rapid and efficient 3D model shape analysis and retrieval technology, a new method of 3D model shape correspondence analysis by combining the intrinsic heat kernel features and local volume features was proposed. Firstly, the intrinsic shape features of the model were extracted by using Laplacian Eigenmap and heat kernel signature. Then, the feature matching matrix was established by combining the stability of the model heat kernel feature and the significance of local space volume. Finally, the model registration and shape correspondence matching analysis was implemented through feature matrix similarity measurement and short path searching. The experimental results show that, the proposed shape correspondence analysis method with the combination of heat kernel distance and local volume constraint can not only effectively improve the efficiency of model shape matching, but also identify the structural features of the same class models. The proposed method can be applied to further realize the co-segmentation and shape retrieval of muhigroup models.