The gold standard assessment of normal and pathologic human movement is laboratory-based optoelectronic three-dimensional motion analysis. This type of equipment is relatively expensive, and requires a dedicated lab and specific expertise to conduct. The equipment imposes several restrictions on the assessment of motion, as analysis is restricted to the lab, markers need to be placed on specific anatomical landmarks, and specific clothing is required to reduce marker movement error.
Recent advances in biomedical engineering resulted in new techniques based on deep learning to track body landmarks in simple video recordings, which include a high degree of automatization, and allow unobtrusive recordings in a more natural environment.
We will present the most recent advances of markerless tracking options to assess human movement, including their advantages and disadvantages and some examples of application (e.g. gait analysis, assessment of balance control and movement disorders).