TY - JOUR
T1 - A lattice-based MRF model for dynamic near-regular texture tracking
AU - Lin, Wen Chieh
AU - Liu, Yanxi
N1 - Funding Information:
The authors would like to thank the reviewers for their valuable comments and Robert T. Collins, Alexei A. Efros, Greg Turk, Jing Xiao, Chieh-Chih Wang, Jiayong Zhang, Sanjiv Kumar, Srinivasa Narasimhan, and Tim Cootes for their insightful suggestions on this work. They also thank Ting Yu, Igor Guskov, and Changbo Hu for providing the results of their algorithms in dynamic NRT tracking comparison. This work was supported in part by US National Science Foundation grant IIS-0099597, Taiwan National Science Council grant 95-2218-E-009-207, and Taiwan MOE ATU Program.
PY - 2007/5
Y1 - 2007/5
N2 - A near-regular texture (NRT) is a geometric and photometric deformation from its regular originA-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.
AB - A near-regular texture (NRT) is a geometric and photometric deformation from its regular originA-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.
UR - http://www.scopus.com/inward/record.url?scp=34047210162&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34047210162&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2007.1053
DO - 10.1109/TPAMI.2007.1053
M3 - Article
C2 - 17356199
AN - SCOPUS:34047210162
SN - 0162-8828
VL - 29
SP - 777
EP - 792
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 5
ER -