VIV: Using visible internal volume to compute junction-aware shape descriptor of 3D articulated models
VIV: Using visible internal volume to compute junction-aware shape descriptor of 3D articulated models
复制标题
VIV：使用可见内部体积计算 3D 铰接模型的连接感知形状描述符
DOI：
10.1016/j.neucom.2015.06.115
复制
发表时间：
2016-11
期刊：
影响因子：
6
通讯作者：
Gong Lianjie
中科院分区：
文献类型：
--
作者：
Liu Yu-Shen;Deng Hongchen;Liu Min;Gong Lianjie
铰接形状由一组刚性部分组成，这些刚性部分由一些柔性连接点连接。在许多视觉任务中，如特征识别、分割、匹配、运动跟踪和功能预测等，连接都被证明是关键的局部特征。然而，由于关节变形的高度复杂性，有效的描述和检测关节仍然是一个研究挑战。针对由闭流形曲面定义的三维关节模型，提出了一种新的连接感知形状描述子。为了编码形状边界上的连接信息，核心思想是开发一种新的几何度量，称为可见内部体积（VIV）函数，该函数将形状的体积上下文与其边界表面相关联。形状边界上任意点处的涡激振动定义为从该点观察到的形状内可见区域的体积。VIV变化作为新的形状描述符。将VIV用于3D铰接形状描述的一个优点是，它对铰接是鲁棒的，并且它很好地反映了形状结构和变形，而无需任何显式的形状分解或先前的骨架提取过程。实验结果和几个潜在的应用证明了我们的方法的有效性。
An articulated shape is composed of a set of rigid parts connected by some flexible junctions. Junctions have been demonstrated to be critical local features in many visual tasks such as feature recognition, segmentation, matching, motion tracking and functional prediction. However, efficient description and detection of junctions still remain a research challenge due to the high complexity of articulated deformation. This paper presents a novel junction-aware shape descriptor for a 3D articulated model defined by a closed manifold surface. To encode junction information on the shape boundary, the core idea is to develop a new geometric measure, called the visible internal volume (VIV) function, which associates the shape's volumetric context to its boundary surface. The VIV at an arbitrary point on the shape boundary is defined as the volume of visible region within the shape as observed from the point. The VIV variation serves as the new shape descriptor. One advantage of using the VIV for 3D articulated shape description is that it is robust to articulation and it reflects the shape structure and deformation well without any explicit shape decomposition or prior skeleton extraction procedure. The experimental results and several potential applications are presented for demonstrating the effectiveness of our method.
登录
查看更多内容
DOI：
--
发表时间：
2010-05
期刊：
--
影响因子：
--
作者：
Kiran Varanasi;Edmond Boyer
通讯作者：
Kiran Varanasi;Edmond Boyer
DOI：
10.1109/tcbb.2008.62
发表时间：
2010-04
期刊：
IEEE/ACM Transactions on Computational Biology and Bioinformatics
影响因子：
--
作者：
T. Shibuya
通讯作者：
T. Shibuya
使用扩散距离进行灵活的分子形状比较
影响因子：
3
作者：
Liu YS;Li Q;Zheng GQ;Ramani K;Benjamin W
通讯作者：
Benjamin W
影响因子：
19.5
作者：
A. Bronstein;M. Bronstein;A. Bruckstein;R. Kimmel
通讯作者：
A. Bronstein;M. Bronstein;A. Bruckstein;R. Kimmel
DOI：
10.1007/978-3-642-15558-1_21
发表时间：
2010-09
期刊：
--
影响因子：
--
作者：
Raghuraman Gopalan;P. Turaga;R. Chellappa
通讯作者：
Raghuraman Gopalan;P. Turaga;R. Chellappa