Multi-level Context-Adaptive Correlation Tracking
作者: Peng LiuChang LiuWei ZhaoXianglong Tang
作者单位: 1Department of Computer Science, Harbin institute of Technology, Harbin, China
刊名: Pattern Recognition, 2018
来源数据库: Elsevier Journal
DOI: 10.1016/j.patcog.2018.10.013
关键词: Visual trackingCorrelation filterContext-adaptive trackerContext pyramid
原始语种摘要: Abstract(#br)The discriminative correlation filter (DCF) has shown impressive performance in visual tracking. Context has two functions in DCF: addressing the disturbance in target locating, and supplying cues for locating the target within the context. To improve the context utilization, we introduce a multi-level context-adaptive tracking (MCAT) approach for DCF tracking. Firstly, a multi-level context representation—called a context pyramid—is proposed to exploit the relationship between the target and its context for better visual tracking. Secondly, for each level of the context pyramid, we control the effect of context in DCF learning and tracking using context-adaptive spatial windows. An accurate target model can thereby be learned, even when the background clutter is severe....
全文获取路径: Elsevier  (合作)
影响因子:2.632 (2012)

  • pyramid 角锥体
  • Tracking 追踪
  • tracker 跟踪装置
  • discriminative 有辨别力的
  • locating 定位
  • context 菌髓
  • tracking 跟踪
  • adaptive 适应的
  • level 水准
  • visual 可见