Three-dimensional motion capture gait analysis systems drive clinical treatment, but require expensive equipment, space, and expertise, but less expensive video-based systems tend to be less accurate. A research team in Japan developed and tested a novel method to improve the accuracy
Photograph courtesy of Masataka Yamamoto from Tokyo University of Science.
of the less expensive systems. Their method reduced errors in the video-based gait analysis systems by using an RGB camera and an inertial measurement unit (IMU) sensor in the user’s shoe, thereby improving the accuracy of the gait data.
“We combined information from a small IMU sensor attached to the shoe with estimated information on the bones and joints of the lower limb, obtained by capturing the gait from a single RGB camera,” said Masataka Yamamoto, PhD, assistant professor in the Department of Mechanical Engineering at Tokyo University of Science, where the study was conducted. Yamamoto is the lead author of the published study.
Sixteen healthy adult men who did not have any limitation of physical activity participated. The team used OpenPose, a real-time multiperson system that can detect 135 human body, hand, facial, and foot key points on a single image, and an IMU sensor on the foot to measure ankle joint kinematics under various gait conditions.
The participants’ gait parameters and lower-limb joint angles during four gait conditions with varying gait speed and foot progression angles were noted using only OpenPose as well combined measurements from OpenPose and the IMUs. The latter was the team’s novel proposed method. Results from these techniques were compared to gait analysis using 3D motion capture, the current gold standard.
The researchers’ combination method measured gait parameters and lower-limb joint angles in the sagittal plane. The mean absolute errors of peak ankle joint angles calculated by the combination method were significantly less compared to OpenPose alone in all the four gait conditions.
“Our method has the potential to be used not [only] in medicine and welfare, but also to predict the decline of gait function in healthcare, for training and skill evaluation in gyms and sports facilities, and accurate projection of human movements onto an avatar by integrating with virtual reality systems,” said Yamamoto.
Editor’s note: This story was adapted from materials provided by Tokyo University of Science.
The open-access study, “Verification of gait analysis method fusing camera-based pose estimation and an IMU sensor in various gait conditions,” was published in Scientific Reports.
