Abstract
A method is proposed to assess risk parameters of anterior cruciate ligament (ACL) injury using human pose estimation (HPE) and a single stereo depth camera. Detectron2 is used to identify key points of a subject performing a single leg jump test. This allows dynamic pivot of the knee to be assessed during landing using four risk parameters: knee valgus, knee translation in the coronal plane, pelvic tilt, and head-ankle alignment (body sway).
Results show the model has an accuracy of 7° in angular measurements and 38 mm in linear measurements. Compared to previous studies, which only consider front-on analysis, this method has partially reduced accuracy in linear measurements and half the accuracy in angular measurements. Despite this, coupling information from multiple risk parameters reduces the accuracy required on any one parameter and the use of a single depth camera enables reliable analysis at a subject orientation of ±45° relative to the camera.
These factors create a novel solution, proposing the ability for broad evaluation of ACL risk parameters in environments outside a testing laboratory, which has not been done before.