基于块对应的时变体数据挖掘的统一框架

实现时空体数据集的有效探索仍然是科学可视化的一大挑战。尽管这些年来已经取得了长足的进步，但现有解决方案通常只关注数据分析和可视化的一两个方面，仍然缺少一个以全面、统一方式进行时变数据分析的工作流程。

为此，来自山东大学、马里兰大学等团队提出了一种新颖的时变数据可视化方法，可在单个统一框架下进行关键帧识别、特征提取和跟踪。

该方法的核心为GPU加速的Block匹配，它将2D像素中的Patch匹配扩展到3D体素的密集的块对应。基于密集的对应结果，该方法能够使用k-中心点聚类以及双向相似性度量从时间序列中识别关键帧。此外，结合图割算法，该框架还能够执行细粒度的特征提取和跟踪。

Fig. 1.  Our approach for analysis and visualization of time-varying volumetric data includes correspondence search (a) and keyframe selection (b). The applications of our approach is feature tracking (c).

该方法在几个时变数据集上进行了测试，证明了它的有效性和实用性。

关键词： 时变数据可视化、块对应、特征提取和跟踪

 

~原文信息~

 

A unified framework for exploring time-varying volumetric data based on block correspondence

BY：Kecheng Lu, Chaoli Wang, Keqin Wu, Minglun Gong, Yunhai Wang

Abstract: 

Effective exploration of spatiotemporal volumetric data sets remains a key challenge in scientific visualization. Although great advances have been made over the years, existing solutions typically focus on only one or two aspects of data analysis and visualization. A streamlined workflow for analyzing time-varying data in a comprehensive and unified manner is still missing. Towards this goal, we present a novel approach for time-varying data visualization that encompasses keyframe identification, feature extraction and tracking under a single, unified framework. At the heart of our approach lies in the GPU-accelerated BlockMatch method, a dense block correspondence technique that extends the PatchMatch method from 2D pixels to 3D voxels. Based on the results of dense correspondence, we are able to identify keyframes from the time sequence using k-medoids clustering along with a bidirectional similarity measure. Furthermore, in conjunction with the graph cut algorithm, this framework enables us to perform fine-grained feature extraction and tracking. We tested our approach using several time-varying data sets to demonstrate its effectiveness and utility.

Keywords: Time-varying data visualization, Block correspondence, Feature extraction and tracking

Link(open access): https://www.sciencedirect.com/science/article/pii/S2468502X19300464

~更多信息，请关注VI官方公众号~

期刊信息：
*Visual Informatics*（中文名《可视信息学》）是由浙江大学主办、浙江大学出版社和Elsevier出版集团联合出版、在线发行、开放获取的国际学术期刊。该刊聚焦于面向人类感知的视觉信息的建模、分析、合成、增强与自然交互。主编是周昆教授、Hans-Peter Seidel教授。
Elsevier link (including First Online Articles): https://www.journals.elsevier.com/visual-informatics
Submit your paper:
https://www.editorialmanager.com/VISINF/default.aspx
Tel:(86-571)88206681-519
E-mail: lujinzhi@cad.zju.edu.cn
Linked in：Visual Informatics
Official account on Wechat: visinf