Robust multi-patch tracking
ICIP(2013)
摘要
In this paper, we propose a robust and fast multi-patch visual tracking algorithm within the Bayesian inference framework. The target template is initialized by selecting the object in the first frame manually and dividing it into small patches. For one certain frame, target candidates are sampled with the state transition model. Each candidate is divided into patches in the same way as the target template. By comparing the candidate's patches with the corresponding template patches, we can get the candidate's likelihood. The tracking result is the candidate which Maximum a Posteriori estimation. After that, tracking is continued using the Bayesian state inference and template update. Our approach can handle appearance variation, occlusion, illumination change, scale variation, rotation and cluttered background. The tracker is fast and performs favorably against several state-of-the-art trackers on challenging sequences.
更多查看译文
关键词
cluttered background,template patches,template update,illumination change,bayesian inference,bayesian state inference framework,multi-patch,bayes methods,maximum a posteriori estimation,maximum likelihood estimation,candidate likelihood,fast multipatch visual tracking algorithm,rotation,state transition model,appearance variation,object tracking,robust,target template,robust multipatch tracking,scale variation,candidate patches,fast,occlusion,visual tracking
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络