Self-feeding frequency estimation and eating action recognition from skeletal representation using Kinect

• Published in: World wide web (Bussum) Vol. 22; no. 3; pp. 1343 - 1358
• Main Authors: Men, Qianhui, Leung, Howard, Yang, Yang
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.05.2019; Springer Nature B.V
• Subjects: Acceleration; Activity recognition; Computer Science; Database Management; Drinking; Eating; Eating behavior; Estimation; Feature extraction; Information Systems Applications (incl.Internet); Operating Systems; Sensors; Skeletal representation; Special Issue on Social Media and Interactive Technologies; Eating action recognition; Microsoft Kinect; Skeleton motions; Self-feeding detection

Under healthcare research, eating activity detection and recognition have been studied for many years. Most of the previous approaches rely on body worn sensors for eating behavior detection. However, measurement errors from these sensors will largely reduce the tracking accuracy in estimating veloc...