Estimation of Joints Performance in Human Running through Mocap Data

Abstract

In Human, the lower limb joints attained more importance during the locomotor system, they play a valuable role during different styles of movement. The study of the 3D biomechanics of these joints have significance important for recording the morphological changes allied with the acquisition of a habitual bipedal gait in humans. Human body on any joint has important inference in joint stability and performance. In this paper, we measure the performance of human lower limb joints (hip, knee and ankle) during running based on statistical techniques. The data of joints acquisition from the motion captured system. This data provides plentiful information in human running. For instance, we can determine which joint has more variation in human running gait based on mocap of each joint. Our experimental results indicate that among these joints, the knee joint has a dominant influence in human running gait.

Extended Multi-Stream Adaptive Graph Convolutional Networks (EMS-AAGCN) for Skeleton-Based Human Action Recognition

“…Table 5 and 6, as their names imply, are dedicated to displaying the results. Handcraftfeature-based approaches [19,22], RNN-based methods [25,46,47], CNN-based methods [6,38], and GCN-based methods were employed for comparisons. Our model achieves much better results on both datasets than the current state-of-the-art, suggesting our approach is more effective.…”

“…We only review relevant works here. Handcrafted features usually model the human body in skeleton-based action recognition [18,19]. A Lie group can be used to encode the iterations and translations of the joints in the skeleton [20,21].…”