Trajectory-based human action segmentation

作者：

Highlights：

• We develop a entropy feedback model to adjust sliding window parameters.

• Independent models have been developed for time shift and window size adjustment.

• The method is generalizable and works in run-time classification.

• Our results show an improvement in classification precision.

• The model allows reducing the delay between classified states and ground truth.

摘要

Highlights•We develop a entropy feedback model to adjust sliding window parameters.•Independent models have been developed for time shift and window size adjustment.•The method is generalizable and works in run-time classification.•Our results show an improvement in classification precision.•The model allows reducing the delay between classified states and ground truth.

论文关键词：Motion segmentation,Classification framework,Signal processing,Motion variability,Adaptive sliding window

论文评审过程：Received 26 June 2013, Revised 7 July 2014, Accepted 17 August 2014, Available online 27 August 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.08.015