A Joint-Level Hybrid Framework for Gait Analysis Using Camera-IMU Fusion and LSTM-Based Temporal Correction.

Gait analysis is an essential tool in clinical domains for diagnosing musculoskeletal disorders and evaluating rehabilitation, yet traditional marker-based systems are limited by high costs and spatial constraints. To overcome these challenges, this study proposes and evaluates a joint-level hybrid framework that integrates a single RGB camera with two shoe-mounted inertial measurement units (IMUs) to leverage their complementary strengths. The camera-based module estimates hip and knee sagittal joint angles using 3D pose estimation, where the DEAS optimization algorithm aligns estimated coordinates with a humanoid model, and an LSTM-based refinement network corrects hip angles by referencing more accurately estimated knee data. Simultaneously, the IMU-based module estimates sagittal ankle angles through kinematic chain relationships that combine camera-derived proximal joint information with IMU-measured foot orientation. Experimental validation with 11 healthy participants in a controlled laboratory environment demonstrates promising estimation performance, achieving an average mean absolute error (MAE) of 7.89° and RMSE of 10.09° on the held-out test set across sagittal hip, knee, and ankle angles. Leave-one-subject-out (LOSO) cross-validation of the LSTM correction model further confirmed its generalizability, yielding an average MAE of 6.40° across bilateral hip angles. By accurately mitigating the trunk-inclination-induced overestimation of hip angles with a minimal sensor configuration (one camera and two IMUs), the proposed framework provides a practical and interpretable approach for portable lower limb gait analysis.