A Lattice-Based MRF Model for Dynamic Near-Regular Texture Tracking
A Lattice-Based MRF Model for Dynamic Near-Regular Texture Tracking
复制标题
DOI：
10.1109/tpami.2007.1053
复制
发表时间：
2007-05
影响因子：
23.6
通讯作者：
Wen-Chieh Lin;Yanxi Liu
中科院分区：
文献类型：
--
作者：
Wen-Chieh Lin;Yanxi Liu
近规则纹理（NRT）是从其规则原点（由单个瓷砖的2D平移形成的全等墙纸图案）进行的几何和光度变形。动态NRT是运动中的NRT。尽管NRT普遍存在于人工和自然环境中，但有效的NRT计算算法却很少。本文讨论了特定的计算挑战，在建模和跟踪动态NRT，包括模糊的对应关系，闭塞，和激烈的照明和外观变化。我们提出了一个基于格的马尔可夫随机场（MRF）模型的动态NRT在三维时空空间。我们的模型包括一个全球性的晶格结构，其特点是多个texton之间的拓扑约束和图像观察模型，处理局部几何形状和外观变化。基于所提出的MRF模型，我们开发了一种跟踪算法，该算法利用置信传播和粒子滤波来有效地处理动态NRT跟踪的特殊挑战，而无需对运动类型或光照条件进行任何假设。我们对现有的跟踪算法提出的方法进行定量评估，并展示其在视频编辑中的应用
A near-regular texture (NRT) is a geometric and photometric deformation from its regular origin - a congruent wallpaper pattern formed by 2D translations of a single tile. A dynamic NRT is an NRT under motion. Although NRTs are pervasive in man-made and natural environments, effective computational algorithms for NRTs are few. This paper addresses specific computational challenges in modeling and tracking dynamic NRTs, including ambiguous correspondences, occlusions, and drastic illumination and appearance variations. We propose a lattice-based Markov-random-field (MRF) model for dynamic NRTs in a 3D spatiotemporal space. Our model consists of a global lattice structure that characterizes the topological constraint among multiple textons and an image observation model that handles local geometry and appearance variations. Based on the proposed MRF model, we develop a tracking algorithm that utilizes belief propagation and particle filtering to effectively handle the special challenges of the dynamic NRT tracking without any assumption on the motion types or lighting conditions. We provide quantitative evaluations of the proposed method against existing tracking algorithms and demonstrate its applications in video editing