Learning skeleton information for human action analysis using Kinect

作者：

Highlights：

• We propose a human action recognition method based on skeleton information captured by Kinect sensor.

• We propose a joint angle sequence model for recognizing human actions, where we leverage Kinect sensor to capture both the depth maps as well as skeleton information.

• We design an improved DTW method to improve the matching accuracy. Comprehensive experiments have shown the effectiveness and robustness of our proposed method.

摘要

•We propose a human action recognition method based on skeleton information captured by Kinect sensor.•We propose a joint angle sequence model for recognizing human actions, where we leverage Kinect sensor to capture both the depth maps as well as skeleton information.•We design an improved DTW method to improve the matching accuracy. Comprehensive experiments have shown the effectiveness and robustness of our proposed method.

论文关键词：Human action recognition,Kinect sensor,Depth image,Human skeleton information

论文评审过程：Received 12 November 2019, Revised 4 February 2020, Accepted 20 February 2020, Available online 24 February 2020, Version of Record 3 March 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115814