Marker-based human pose tracking using adaptive annealed particle swarm optimization with search space partitioning

作者：

Highlights：

• A marker-based human pose tracking algorithm is presented.

• Problem is defined as optimization model and is solved with a modified PSO algorithm.

• Proposed algorithm is independent of motion type.

• Search space partitioning is used to reduce search space complexity.

• Adaptive computation of particle velocity is used to increase algorithm performance.

摘要

•A marker-based human pose tracking algorithm is presented.•Problem is defined as optimization model and is solved with a modified PSO algorithm.•Proposed algorithm is independent of motion type.•Search space partitioning is used to reduce search space complexity.•Adaptive computation of particle velocity is used to increase algorithm performance.

论文关键词：Pose tracking,Marker-based human pose estimation,Particle swarm optimization,Search space partitioning

论文评审过程：Received 21 April 2016, Revised 1 January 2017, Accepted 22 March 2017, Available online 31 March 2017, Version of Record 28 April 2017.

论文官网地址：https://doi.org/10.1016/j.imavis.2017.03.003