Using Joint Angles Based on the International Biomechanical Standards for Human Action Recognition

Abstract

Keypoint data is widely used in machine learning for tasks like action detection and recognition.  However, human experts in movement use a notion of joint angles standardised by the International Society of Biomechanics to precisely and efficiently communicate static body poses and movements. In this paper, we introduce the basic biomechanical notions and show how they can be used to convert common keypoint data into joint angles that uniquely describe the given pose and have various desirable mathematical properties, such as independence of both the camera viewpoint and the subject. We experimentally demonstrate that the joint angle representation of keypoint data is suitable for machine learning applications and can in some cases bring an immediate performance gain. This representation is particularly valuable for applications requiring interpretability and communication with human experts, such as in sports and medical fields. A link to the repository will be included in the camera ready version.

Keywords: Action Recognition, Joint Angle Representation, International Biomechanical Standards