Effective and efficient human action recognition using dynamic frame skipping and trajectory rejection

作者：

Highlights：

• Removing redundant trajectories induced by camera movement

• A fast dynamic frame skipping technique for efficient feature extraction

• Consideration of both effectiveness and efficiency of human action recognition

摘要

•Removing redundant trajectories induced by camera movement•A fast dynamic frame skipping technique for efficient feature extraction•Consideration of both effectiveness and efficiency of human action recognition

论文关键词：Frame skipping,Human action recognition (HAR),Motion descriptor,Motion trajectory,Optical flow

论文评审过程：Received 1 October 2015, Revised 17 April 2016, Accepted 10 June 2016, Available online 18 June 2016, Version of Record 20 February 2017.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.06.002