Search Results (4)

Background and Objectives: Studies analyzing lower extremity alignment (LEA) LEA among taekwondo subdisciplines athletes are lacking. This study compared LEA in the dominant and nondominant legs intaekwondo athletes. Materials and Methods: Twelve measurements of LEA were analyzed for 157 athletes (63 sparring, 50 demonstration, and 44 poomsae athletes) registered with the Korea Taekwondo Association. LEA was measured in the standing, supine, and prone positions using alignment application, a goniometer, a bubble inclinometer, a height gage, and a palpation meter. Results: The analysis revealed that the dominant leg of poomsae athletes showed greater genu valgum alignment than that of sparring athletes (p < 0.01), whereas the dominant leg of sparring athletes showed greater rearfoot varum alignment than that of demonstration athletes (p < 0.01). Furthermore, the nondominant leg of poomsae athletes showed greater genu valgum alignment than that of sparring and demonstration athletes (p < 0.01), whereas the nondominant leg of sparring athletes showed greater rearfoot varum alignment than that of demonstration athletes (p < 0.01). In addition, demonstration athletes had better forefoot varus alignment than poomsae athletes (p < 0.01). Conclusions: This study revealed that LEA characteristics vary among taekwondo athletes according to their subdiscipline. The results of this study would help in designing training programs tailored to each subdiscipline that would best address their LEA characteristics and help to prevent injuries. Full article

Issues of fairness and consistency in Taekwondo poomsae evaluation have often occurred due to the lack of an objective evaluation method. This study proposes a three-dimensional (3D) convolutional neural network–based action recognition model for an objective evaluation of Taekwondo poomsae. The model exhibits robust recognition performance regardless of variations in the viewpoints by reducing the discrepancy between the training and test images. It uses 3D skeletons of poomsae unit actions collected using a full-body motion-capture suit to generate synthesized two-dimensional (2D) skeletons from desired viewpoints. The 2D skeletons obtained from diverse viewpoints form the training dataset, on which the model is trained to ensure consistent recognition performance regardless of the viewpoint. The performance of the model was evaluated against various test datasets, including projected 2D skeletons and RGB images captured from diverse viewpoints. Comparison of the performance of the proposed model with those of previously reported action recognition models demonstrated the superiority of the proposed model, underscoring its effectiveness in recognizing and classifying Taekwondo poomsae actions. Full article

The purpose of this study was to investigate whether there is a gender-specific difference in the indirect effect of perceived coaching behaviors of Taekwondo Poomsae athletes on performance mediated by basic psychological needs. To this end, a survey was conducted to collect data from 474 Taekwondo Poomsae athletes (male = 285). Based on the collected data, analysis of basic descriptive statistics and confirmatory factor analysis were performed, and PROCESS was used to test the proposed model of multi mediated moderation. For female athletes, there was an indirect effect of controlling coaching behaviors resulting in performance improvement mediated by autonomy, but this effect was not observed in male athletes. The findings of this study indicate that different mental conditioning strategies should be applied in consideration of athletes’ gender to improve coaches’ methods of instruction and ultimately improve performance in Taekwondo Poomsae. Full article

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. Full article