A Binocular-Camera-Assisted Sensor-to-Segment Alignment Method for Inertial Sensor-Based Human Gait Analysis

Abstract

Lower limb joint angles are powerful clinical indicators for mobility assessment and gait rehabilitation training. Inertial motion capture (IMC), which is both accurate and convenient, is becoming an ideal method to estimate joint angles. Considering that the corresponding segment and sensor frame are usually misaligned, an alignment procedure is required to determine the orientation offset between the segment and the sensor frame. This article presents a binocular-camera-assisted alignment procedure to align the frames of segment and inertial sensor. This procedure uses a binocular camera to acquire lower limb segment’s initial orientations with image-based human pose algorithm and then estimates the joint angle with kinematic constraint. The alignment procedure requires only sitting posture and does not need any functional movement. Ten healthy participants were recruited for the validation experiments, which included stand-up, turn-around, and walking. The accuracy and effectiveness of our alignment procedure were validated against the optical motion capture (OMC). The mean root mean square errors (RMSEs) of hip, knee, and ankle angles were 1.6°, 2.9°, and 3.9°, respectively. The result demonstrates that our procedure performs well on joint angle estimation. The proposed alignment procedure did not require any complicated functional movement, but only sitting posture, which could enable more practical joint angle estimation for patient subjects in clinical applications.