In a recent study, we compared a markerless method to determine body position on the bicycle, which can be an important tool for remote bike fitting. The method involves using video recording with Artificial Inteligence (AI) determining body segments, which can then be used to calculate joint angles. Even though, there were significant differences (3-12°, d=0.38-1.92) in relation to the use of skin markers, there is potential for this method to be used in bike fitting. We are testing variations of the AI to further improve the detection of joint angles with the expectation to automate calculation of angles.
Bini, Rodrigo; Serrancolí, Gil; Santiago, Paulo Roberto Pereira; and Moura, Felipe (2019) "ASSESSMENT OF A MARKLESS MOTION TRACKING METHOD TO DETERMINE BODY POSITION ON THE BIKE," ISBS Proceedings Archive: Vol. 37 : Iss. 2 , Article 1.
Available at: https://commons.nmu.edu/isbs/vol37/iss2/1