Human tracking from single RGB-D camera using online learning

作者：

Highlights：

• A new human tracking method using online learning classifiers with no ground plane assumption.

• Different sampling methods to find potential positive and negative candidates for updating the online classifier.

• The kernelized Support Vector Machine (SVM) is used as the online classifier to recognize the target human.

• The method achieves higher success rates compared to a 2D tracker and a 3D human detection method.

摘要

•A new human tracking method using online learning classifiers with no ground plane assumption.•Different sampling methods to find potential positive and negative candidates for updating the online classifier.•The kernelized Support Vector Machine (SVM) is used as the online classifier to recognize the target human.•The method achieves higher success rates compared to a 2D tracker and a 3D human detection method.

论文关键词：Human-robot collaboration,RGB-D cameras,Online classifier,Candidate sampling

论文评审过程：Received 13 November 2018, Revised 14 March 2019, Accepted 15 May 2019, Available online 23 May 2019, Version of Record 13 June 2019.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.05.003