Efficient Body Motion Quantification and Similarity Evaluation Using 3-D Joints Skeleton Coordinates

Evaluating whole-body motion is challenging because of the articulated nature of the skeleton structure. Each joint moves in an unpredictable way with uncountable possibilities of movements direction under the influence of one or many of its parent joints. This paper presents a method for human motion quantification via three-dimensional (3-D) body joints coordinates. We calculate a set of metrics that influence the joints movement considering the motion of its parent joints without requiring prior knowledge of the motion parameters. Only the raw joints coordinates data of a motion sequence are needed to automatically estimate the transformation matrix of the joints between frames. We also consider the angles between limbs as a fundamental factor to follow the joints directions. We classify the joints motion as global motion and local motion. The global motion represents the joint movement according to a fixed joint, and the local motion represents the joint movement according to its first parent joint. In order to evaluate the performance of the proposed method, we also propose a comparison algorithm between two skeletons motions based on the quantified metrics. We measured the comparative similarity between the 3-D joints coordinates on Microsoft Kinect V2 and UTD-MHAD dataset. User studies were conducted to evaluate the performance under different factors. Various results and comparisons have shown that our method effectively quantifies and evaluates the motion similarity.

I. Introduction

Understanding human behavior is indispensable for automating many tasks. Human body motion analysis is a branch of understanding human behavior, and it is fundamental for various applications, such as surveillance [1]–[3], human–computer interaction [4]–[6], health care of the elderly [7], [8], human gait analysis [9], [10], and robotics [11]–[16]. A variety of motion capture systems have been built to capture the human motion using different techniques, including wearable devices and sensors, multiple cameras, or even a single camera. Some of the systems combine many devices together to improve the capturing quality and generate accurate positions of the human body joints. Recently, the fast development in machine learning algorithms [17], [18] greatly improved the quality of motion data. Microsoft Kinect [19] can accurately estimate three-dimensional (3-D) human body joints to form a skeleton model from a single depth image using the method in [20]. Real-time motion capture from just a single RGB image is proposed in [21] via a deep learning convolutional neural network (CNN) model to estimate accurate 3-D human body poses.