Sensor technology--and more specifically a new approach that leverages sensor fusion--has the potential to give medical researchers a leg up in their efforts improve treatment for people with walking gait disabilities, according to a new paper from the Tokyo University of Science.
Patients who need corrective measures to address walking gait disabilities historically have been subjected to gait analysis by equipment and systems that use reflective or infrared markers that are applied to different parts of the body to measure patients’ walking gaits, and then deliver metrics that are used to drive clinical treatment for gait correction. The metrics involved might have to do with gait speed, stride length, joint kinematics, or other factors.
However, using this approach can be costly and time-consuming, and require physical space and gear that makes them unlikely to be feasible for many clinical settings.
Less intensive markerless, video-based gait analysis systems also can be used, but often are inaccurate, according to the paper.
In this case, the university researchers turned to the increasingly popular notion of sensor fusion. They employed RGB (red, green and blue wavelength measurement) camera-based sensor technology, which they used for pose estimation, and combined it with an inertial measurement unit sensor (IMU) for gait analysis, an approach which they say “significantly reduces errors in the process.”
The research team–Dr. Masataka Yamamoto, Mr. Yuto Ishige, and Professor Hiroshi Takemura from the Faculty of Science and Technology, Tokyo University of Science, and Professor Koji Shimatani from the Prefectural University of Hiroshima, Japan–explained in the paper how they developed “a simple and accurate sensor-fusion method” that improves the accuracy of gait analysis.
“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,” stated Dr. Yamamoto, the lead author of the study.
The paper, published by Nature’s Scientific Reports, explained in further detail, “The team used single RGB [red, green and blue wavelength measurement] camera-based pose estimation by OpenPose (OP) [a software library that recognizes body poses] and an IMU sensor on the foot to measure ankle joint kinematics under various gait conditions for 16 healthy adult men between 21 and 23 years of age who did not have any limitation of physical activity. 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 OP as well combined measurements from OP and the IMUs–the latter combined approach being the team’s novel proposed method.
The results showed reduced errors when compared with traditional gait analysis methods, suggesting that with further research the sensor fusion-based approach could be adapted for use in a larger number of clinical settings and be used in the treatment of many more patients with gait disabilities and abnormalities, as well as for other purposes.
“Our method has the potential to be used not 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,” noted Dr. Yamamoto.