A grid-based tracker for erratic targets

作者：

Highlights：

• The grid-based Bayesian tracker achieves excellent video tracking performance.

• We present a method to enhance its capability to track targets with erratic motion.

• We incorporate adaptation in the motion model and iterative position estimation.

• We present results on tracking of leukocytes, vehicles and Drosophila larva.

摘要

Highlights•The grid-based Bayesian tracker achieves excellent video tracking performance.•We present a method to enhance its capability to track targets with erratic motion.•We incorporate adaptation in the motion model and iterative position estimation.•We present results on tracking of leukocytes, vehicles and Drosophila larva.

论文关键词：Target tracking,Visual tracking,Grid-based Bayesian approach,Erratic target motion,Predication model adaptation,Iterative position estimation

论文评审过程：Received 24 December 2013, Revised 30 March 2015, Accepted 14 May 2015, Available online 23 May 2015, Version of Record 16 July 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.05.014