Action Description from 2D Human Postures in Care Facilities

Wataru Takano, Lee Haeyeon
2020 IEEE Robotics and Automation Letters  
This article describes a novel approach to classification of whole-body motions from estimated human postures in 2D camera images and subsequent generation of their relevant descriptions. The motions are encoded into stochastic motion models referred to as motion primitives. Words are connected to the motion primitives, and word n-grams are represented stochastically. More specifically, the motion observation is classified into the motion primitive, from which its relevant words are generated.
more » ... rds are generated. These words are arranged in a grammatically correct order to make the descriptions for the observation. This approach was tested on actions performed by older adults in the care facility and its validity was demonstrated. Index Terms-Gesture, posture and facial expressions, probability and statistical methods, recognition.
doi:10.1109/lra.2020.2965394 fatcat:7peo2affczhdxfmmwobwqpzaie