Improving posture classification accuracy for depth sensor-based human activity monitoring in smart environments

作者：

Highlights：

• A new posture classification framework for Kinect is proposed.

• Accuracy in classifying noisy postures is improved by considering the reliability of each joint.

• Reliability of a joint can be evaluated by the consistency in different aspects over time.

• Performance of classifier is improved by learning the weights of reliability terms.

摘要

•A new posture classification framework for Kinect is proposed.•Accuracy in classifying noisy postures is improved by considering the reliability of each joint.•Reliability of a joint can be evaluated by the consistency in different aspects over time.•Performance of classifier is improved by learning the weights of reliability terms.

论文关键词：Smart environments,Monitoring systems,Posture classification,Max-margin classification,Depth camera,Reliability estimation

论文评审过程：Received 17 April 2015, Revised 21 December 2015, Accepted 29 December 2015, Available online 12 January 2016, Version of Record 27 May 2016.

论文官网地址：https://doi.org/10.1016/j.cviu.2015.12.011