OBJECT TRACKING WITH ROTATION-INVARIANT LARGEST DIFFERENCE INDEXED LOCAL TERNARY PATTERN
作者: J Shajeena1 K Ramar2
作者单位: 1James College of Engineering and Technology, India1, Einstein College of Engineering, India2
刊名: ICTACT JOURNAL OF IMAGE AND VIDEO PROCESSING, 2017, Vol.7 (3)
来源数据库: ICT Academy of Tamil Nadu
关键词: LTPMotion VectorRotation-InvariantHistogramObject TrackingDCT
原始语种摘要: This paper presents an ideal method for object tracking directly in the compressed domain in video sequences. An enhanced rotation-invariant image operator called Largest Difference Indexed Local Ternary Pattern (LDILTP) has been proposed. The Local Ternary Pattern which worked very well in texture classification and face recognition is now extended for rotation invariant object tracking. Histogramming the LTP code makes the descriptor resistant to translation. The histogram intersection is used to find the similarity measure. This method is robust to noise and retain contrast details. The proposed scheme has been verified on various datasets and shows a commendable performance
全文获取路径: PDF下载  ICT Academy of Tamil Nadu  (合作)
分享到:

×
关键词翻译
关键词翻译
  • invariant 不变量
  • rotation 旋转
  • histogram 倾率分布图
  • intersection 交叉
  • compressed 侧扁的
  • texture 结构
  • recognition 识别
  • descriptor 描述符
  • tracking 跟踪
  • details 细节