Paper Review: AR-Enhanced Workouts: Exploring Visual Cues for At-Home Workout Videos in AR Environment

DOI

Problem

  • Hard to quickly learn the correct movements from the 2D video
  • Failed to provide effective feedback

Solution

AR:

  • Workout video centered in the user’s field of view
  • Real-time visual feedback

Additional Camera:

  • For the full-body status of the users
  • Give feedback to adjust users’ movements in real-time

Design Space

Data:

  • Motion-data:
    • The movements that users need to pay attention
    • Movement direction & sequence
  • Non-motion data:
    • Goals that users only need to aim to achieve
    • Body skeleton (give feedback using joints)
    • Visual metaphors
      • Chair (where to squat)
      • Cone (height)

Task:

  • Identification:
    • Key movement information -> better understanding
  • Comparison:
    • Apply superposition
    • Overlaying users’ exercise performance onto standard visual cues

Situation:

  • Address frequent viewpoint shifts
    • Floating screen (out of sight)
    • On-ground (within sight)
Hyungjun Doh
Hyungjun Doh
Master’s Student

My research interests are Human-AI interaction and its practical applications, with a specific focus on Extended Reality, Task Guidance Systems, and AI-infused interfaces.