Computational Foresight: Realtime Forecast of Human Body Motion
Booth no: et_0044

  • Full Conference Pass
  • Full Conference 1-Day Pass
  • Basic Conference Pass
  • Experience Pass
  • Exhibitor Pass

28 - 29 November 2017, 10:00am - 06:00pm
30 November 2017, 10:00am - 04:00pm
Venue: BHIRAJ Hall 3 - Experience Hall (Emerging Technologies Exhibits)
Location: Bangkok Int'l Trade & Exhibition Centre (BITEC)

Summary: In this paper, we propose a machine learning-based system named "Comuputational Foresight" that can forecast body motion 0.5 seconds before. The system detects 25 human body joints by Kinect V2. We created 6-layered neural network system for machine-learning. We achieved real-time motion forecast system. This can be used to estimate human gesture inputs in advance, instruct sports actions properly, and prevent elderly from falling to the ground, and so on.

Yuuki Horiuchi, The University of Tokyo
Yasutoshi Makino, The University of Tokyo
Hiroyuki Shinoda, The University of Tokyo