A hybrid algorithm based on particle filter and genetic algorithm for target tracking

作者：

Highlights：

• Proposing a very fast and accurate visual tracker based on particle filtering.

• Using a genetic algorithm in an efficient manner to solve sample impoverishment.

• Using the idea of selecting target in the first frame (partitioning idea).

• Noticeably reducing the number of particles and resolving the occlusion problem.

• Remarkable tracking accuracy with a very low computational complexity.

摘要

•Proposing a very fast and accurate visual tracker based on particle filtering.•Using a genetic algorithm in an efficient manner to solve sample impoverishment.•Using the idea of selecting target in the first frame (partitioning idea).•Noticeably reducing the number of particles and resolving the occlusion problem.•Remarkable tracking accuracy with a very low computational complexity.

论文关键词：Video objects tracking,Particle filter,Genetic algorithm,Resampling,Sample impoverishment

论文评审过程：Received 5 February 2019, Revised 14 November 2019, Accepted 6 January 2020, Available online 8 January 2020, Version of Record 25 January 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113188