Visual Feedback for Core Training with 3D Human Shape and Pose

In this paper, we propose a visual feedback system for core training using a monocular camera image. To support the user in maintaining the correct postures from target poses, we adopt 3D human shape estimation for both the target image and input camera video. Because it is expensive to capture human pose using depth cameras or multiple cameras using conventional approaches, we employ the skinned multi-person linear model of human shape to recover the 3D human pose from 2D images using pose estimation and human mesh recovery methods. We propose a user interface for providing visual guidance based on the estimated target and current human shapes. To clarify the differences between the target and current postures of 3D models, we adopt markers for visualization at ten body parts with color changes. From user studies conducted, the proposed visual feedback system is effective and convenient in performing core training.