Person identification from partial gait cycle using fully convolutional neural networks

Newly compiled Tai Chi (Bafa Wubu) promotes lower extremity exercise: a preliminary cross sectional study

Background

Tai Chi (Bafa Wubu) is a new type of simplified Tai Chi widely practiced by Tai Chi enthusiasts that has developed and perfected simplified Tai Chi movement and enriched Tai Chi practice methods. When practicing, Tai Chi athletes and enthusiasts can choose the Bafa Wubu movements to practice according to their physical conditions. The purpose of this article is to discuss the mechanism by which Bafa Wubu promotes lower extremity exercise from the perspective of exercise biomechanics.

Objectives

This article aims to explore the scientific training methods and technical characteristics of Bafa Wubu, and its contribution to comprehensive exercise of the lower extremities, by analyzing the biomechanical characteristics of the lower extremities of participants who practice Bafa Wubu at different levels and by comparing their ground reaction force, lower limb joints, and muscles during Bafa Wubu.

Methods

A total of 16 male participants were recruited and divided into an amateur group (N = 8) and a professional group (N = 8). The data were collected by a BTS 3D infrared-based motion capture system, and Kistler 3D force plate. The lower extremity joint forces and muscle strength were calculated by anybody simulation software with inverse dynamics.

Results

During elbowing and leaning sideways with steps sideways (ELS), the ground reaction force of the professional group was significantly higher than that of the amateur group in the sagittal, vertical, and frontal axes (P < 0.01). While stepping forward, backward, and sideways, the professional group's joints loading at the hip, knee, and ankle was always higher in the vertical direction (P < 0.01). Furthermore, during warding off with steps forward (WOF), laying with steps forward (LF), and rolling back with steps backward (RBB), hip joint loading increased in the med-lat direction. During actions with steps backward and sideways, the professional group's ankle flexion/extension torque and hip abduction/rotation torque were significantly larger than those of the amateur group (P < 0.01). Different actions in Bafa Wubu activate muscles to different degrees, whereas the iliacus is mainly responsible for stabilizing postures when practitioners perform standing knee lifting motions.

Conclusions

Professional groups who have been practicing Tai Chi (Bafa Wubu) for a long time have higher ground reaction force, and the force on the three joints of the lower extremities is different for various movements, which has positive significance for exercising the joints of the lower extremities. In addition, various motions activate muscles of different types at different levels. For amateurs to practice different movements to stimulate the muscles, targeted areas of practice promote the lower extremity muscles' synergistic force. In summary, the muscles and joints of the lower extremity can obtain comprehensive and balanced exercise through Bafa Wubu.

Personal Identification Using Gait Spectrograms and Deep Convolutional Neural Networks

Human gait can serve as a useful behavioral trait for biometrics. Compared to fingerprint, face, and iris, the most commonly used physiological identifiers, gait can be unobtrusively monitored from a distance without requiring explicit involvement and physical restraint from people. Advances in wearable technology facilitate direct and faithful measurement of gait motions with easy-to-use and low-cost inertial sensors. This study aimed to propose an approach to using kinematic gait data collected with wearable inertial sensors for reliable personal identification. Sixty-nine individuals ranged in age from 24 to 62 years old participated in this study. The 3-axis acceleration and the 3-axis angular velocity signals were measured using the inertial measurement units attached to the feet, shanks, thighs, and posterior pelvis while walking. The gait spectrograms were acquired by applying time-frequency analyses to the lower body movement signals measured in one stride. Among each participant's 15 strides, 12 strides were used in the 4-fold cross validation of the deep convolutional neural network-based classifiers, and the remaining three strides were used to evaluate the classifiers. An accuracy of 99.69% was achieved by using the foot, shank, thigh, and pelvic spectrograms, and the accuracy was 96.89% using only the foot spectrograms. This study has the potential to be applied in behavior-based biometric technologies by confirming the feasibility of the proposed kinematic and spectrographic approaches in identifying personal behavioral characteristics.

Gait recognition using a few gait frames

Gait has been deemed as an alternative biometric in video-based surveillance applications, since it can be used to recognize individuals from a far distance without their interaction and cooperation. Recently, many gait recognition methods have been proposed, aiming at reducing the influence caused by exterior factors. However, most of these methods are developed based on sufficient input gait frames, and their recognition performance will sharply decrease if the frame number drops. In the real-world scenario, it is impossible to always obtain a sufficient number of gait frames for each subject due to many reasons, e.g., occlusion and illumination. Therefore, it is necessary to improve the gait recognition performance when the available gait frames are limited. This paper starts with three different strategies, aiming at producing more input frames and eliminating the generalization error cause by insufficient input data. Meanwhile, a two-branch network is also proposed in this paper to formulate robust gait representations from the original and new generated input gait frames. According to our experiments, under the limited gait frames being used, it was verified that the proposed method can achieve a reliable performance for gait recognition.