Optimization of a Markerless Gait Analysis Application Aimed at Orthopedic Care for Developing Countries

In this work, a low-budget markerless gait analysis application that is aimed at orthopedic care was built and optimized for use in developing countries and small practices. The application utilizes Microsoft Kinect to detect and track body joints and then calculates nine gait parameters that are important for performing a gait assessment. By tracking the progression of the lower limb joints over time, we were able to measure motion angles for these joints. Also, the following spatial and temporal parameters were extracted using the data received from the Kinect: swing time, stance time, stride length, step width and speed. For testing and evaluation, the application was validated using gait data from 10 participants. The measurements of the hip flexion/extension, hip abduction/adduction and knee flexion/extension followed the graphs of standard gait pattern. Also they were consistent and homogeneous among all ten participants. Due to the low tracking accuracy for both the ankle and the foot, measurements of ankle plantar flexion and dorsiflexion didn’t follow the trajectory of the standard graph. Moreover, measurements from all ten participants were sparsely distributed across their average value. To overcome the tracking accuracy of the Kinect in non-ideal conditions, a novel algorithm was proposed and implemented for joint inference. The algorithm uses the subject’s gait pattern and geometric relationships between the lower limb joints to infer the ankle joint positio