TUHAD: Taekwondo Unit Technique Human Action Dataset with Key Frame-Based CNN Action Recognition

Abstract

In taekwondo, poomsae (i.e., form) competitions have no quantitative scoring standards, unlike gyeorugi (i.e., full-contact sparring) in the Olympics. Consequently, there are diverse fairness issues regarding poomsae evaluation, and the demand for quantitative evaluation tools is increasing. Action recognition is a promising approach, but the extreme and rapid actions of taekwondo complicate its application. This study established the Taekwondo Unit technique Human Action Dataset (TUHAD), which consists of multimodal image sequences of poomsae actions. TUHAD contains 1936 action samples of eight unit techniques performed by 10 experts and captured by two camera views. A key frame-based convolutional neural network architecture was developed for taekwondo action recognition, and its accuracy was validated for various input configurations. A correlation analysis of the input configuration and accuracy demonstrated that the proposed model achieved a recognition accuracy of up to 95.833% (lowest accuracy of 74.49%). This study contributes to the research and development of taekwondo action recognition.

Evaluating Martial Arts Punching Kinematics Using a Vision and Inertial Sensing System

“…Motion-based analysis in martial arts has widely been used for optimising techniques [ 18 ], while interactive systems are used for teaching beginners [ 19 ]. Alternatively, technology in martial arts is also used for scoring, such as the system presented in [ 20 ] which uses machine learning to recognize and score Taekwondo Poomsae hand motions. A similar approach uses inertial measurements units for performance analysis [ 21 ].…”

An overview of Human Action Recognition in sports based on Computer Vision

“…However, recognizing similar actions is becoming more popular and challenging, especially if multiple players in the field are performing different actions simultaneously ( Figure 20 ). HAR is applied in individual sports such as Taekwondo [ 71 ]. Still, here we analyze sports involving the ball (which moves fast and presents a challenge to find active players) and involving two or more players.…”

Motion Action Analysis at Basketball Sports Scene Based on Image Processing

“…Calculating by formula (13), we obtain the corresponding coordinate confidence of each coordinate point and posture estimation output heat map. In addition, the edge of the spatial temporal graph structure can be decomposed into the edge set of each frame and the edge set between two adjacent frames, which are expressed as formulas ( 14) and ( 15), respectively, where H represents the joint of the human limb, and all edges of E F represent the locus of the joint [24].…”