Multimodal Feature-Level Fusion CBAM U-Net for Static Plantar Pressure Prediction Using Plantar Geometry and Sparse Anatomical Landmarks
Published in: Sensors, 2026; 26(13):4143
Authors: Wang C, Evans K, Hartley D, Morrison S, McDonald S, et al.
This peer-reviewed, open-access study introduces a multimodal feature-level fusion model (CBAM U-Net) that predicts static plantar pressure distributions using only plantar geometry and sparse anatomical landmarks. The approach offers a clinically accessible pathway to pressure estimation without dedicated force-plate hardware.
iOrthotics clinicians Dean Hartley and Scott Morrison are named authors on this research, conducted in partnership with QUT as part of our ongoing sponsorship of PhD biomechanics research.
Badges: Peer-reviewed · Open Access