Object Tracking with Embedded Deformable Parts in Dynamic Conditional Random Fields

Suofei ZHANG  Zhixin SUN  Xu CHENG  Lin ZHOU  

IEICE TRANSACTIONS on Information and Systems   Vol.E99-D    No.4    pp.1268-1271
Publication Date: 2016/04/01
Publicized: 2016/01/19
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2015EDL8139
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
visual tracking,  conditional random field,  deformable part based model,  graph model,  

Full Text: PDF(1.9MB)>>
Buy this Article

This work presents an object tracking framework which is based on integration of Deformable Part based Models (DPMs) and Dynamic Conditional Random Fields (DCRF). In this framework, we propose a DCRF based novel way to track an object and its details on multiple resolutions simultaneously. Meanwhile, we tackle drastic variations in target appearance such as pose, view, scale and illumination changes with DPMs. To embed DPMs into DCRF, we design specific temporal potential functions between vertices by explicitly formulating deformation and partial occlusion respectively. Furthermore, temporal transition functions between mixture models bring higher robustness to perspective and pose changes. To evaluate the efficacy of our proposed method, quantitative tests on six challenging video sequences are conducted and the results are analyzed. Experimental results indicate that the method effectively addresses serious problems in object tracking and performs favorably against state-of-the-art trackers.

open access publishing via