A Robust Object Tracking Method Based on Sparse Representation
While much progress has been made for object tracking in recent years,it is still a challenging problem to handle large change in motion,appearance,scale and pose variation.One of the main reasons is the lack of effective representation to account for appearance variation.For this issue a flexible method based on superpixel segmentation is applied to divide an image into several patches.Besides,under the framework of sparse code a discriminative model based on superpixel is proposed.Experimental results show that our method tracks the object accurately and reliably in realistic videos where the appearance and motion are drastically changing overtime.
SLIC Superpixel Segmentation Sparse Representation Object Tracking
Yuanchen Qi Chengdong Wu Dongyue Chen Ziwei Lu
College of Information Science and Engineering,Northeastern University,Shenyang 11000
国际会议
长沙
英文
2015-2019
2014-05-31（万方平台首次上网日期，不代表论文的发表时间）