Exploiting a depth context model in visual tracking with correlation filter  

作　　者：Zhao-yun CHEN Lei LUO Da-fei HUANG Mei WEN Chun-yuan ZHANG 

机构地区：[1]College of Computer,National University of Defense Technology,Changsha 410073,China [2]National Key Laboratory of Parallel and Distributed Processing,Changsha 410073,China

出　　处：《Frontiers of Information Technology & Electronic Engineering》2017年第5期667-679,共13页信息与电子工程前沿（英文版）

基　　金：Project supported by the National Natural Science Foundation of China(Nos.61502509,61402504,and 61272145);the National High-Tech R&D Program(863)of China(No.2012AA012706);the Research Fund for the Doctoral Program of Higher Education of China(No.21024307130004)

摘　　要：Recently correlation filter based trackers have attracted considerable attention for their high computational efficiency. However, they cannot handle occlusion and scale variation well enough. This paper aims at preventing the tracker from failure in these two situations by integrating the depth information into a correlation filter based tracker. By using RGB-D data, we construct a depth context model to reveal the spatial correlation between the target and its surrounding regions. Furthermore, we adopt a region growing method to make our tracker robust to occlusion and scale variation. Additional optimizations such as a model updating scheme are applied to improve the performance for longer video sequences. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed tracker performs favourably against state-of-the-art algorithms.Recently correlation filter based trackers have attracted considerable attention for their high computational efficiency. However, they cannot handle occlusion and scale variation well enough. This paper aims at preventing the tracker from failure in these two situations by integrating the depth information into a correlation filter based tracker. By using RGB-D data, we construct a depth context model to reveal the spatial correlation between the target and its surrounding regions. Furthermore, we adopt a region growing method to make our tracker robust to occlusion and scale variation. Additional optimizations such as a model updating scheme are applied to improve the performance for longer video sequences. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed tracker performs favourably against state-of-the-art algorithms.

关 键 词：Visual tracking Depth context model Correlation filter Region growing 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]