Head pose estimation: An extensive survey on recent techniques and applications
作者：
Highlights：
• An extensive survey collecting more than 60 new methods on the HPE.
• Methods are divided by the input, RGBs, depth images, and videos.
• Sensors and datasets used in this field are discussed in pros and cons.
• Fields of applications of HPE are discussed, together with emerging applications.
• A highlight about differences between learning and learning-free techniques.
摘要
•An extensive survey collecting more than 60 new methods on the HPE.•Methods are divided by the input, RGBs, depth images, and videos.•Sensors and datasets used in this field are discussed in pros and cons.•Fields of applications of HPE are discussed, together with emerging applications.•A highlight about differences between learning and learning-free techniques.
论文关键词：Biometrics,Head pose estimation,Face recognition,Frontalization
论文评审过程：Received 3 January 2021, Revised 7 February 2022, Accepted 14 February 2022, Available online 16 February 2022, Version of Record 28 February 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108591
