Saravana K. Natarajan, Xingchen Wang, Matthias Spranger, and Axel Gräser
Human gait, Markerless gait analysis, RGBD camera
Vision based gait analysis systems has gained a lot of importance in recent years due to its low cost, time efficient and non-invasive procedure. The existing gait analysis systems are either expensive or require controlled environments such as a laboratory or a clinic. Reha@Home system is an inexpensive and non-intrusive markerless gait analysis system based on a RGBD camera. The presented system is capable of measuring the subject’s gait on a continuous basis in a typical living room environment. Based on the human body proportion ratios, a novel approach to compute the lower extremities from the segmented depth image is presented. The joint angles and the gait parameters are automatically extracted from the detected body joints. The performance of the system was evaluated with the ground truth values obtained from an electrogoniometer. The clinical evaluation shows that the system could be a useful tool for the therapists to assess the progress in rehabilitation and ascertain the therapy success.