Application of Assistive Computer Vision Methods to Oyama Karate Techniques Recognition

Toward Modeling Psychomotor Performance in Karate Combats Using Computer Vision Pose Estimation

Technological advances enable the design of systems that interact more closely with humans in a multitude of previously unsuspected fields. Martial arts are not outside the application of these techniques. From the point of view of the modeling of human movement in relation to the learning of complex motor skills, martial arts are of interest because they are articulated around a system of movements that are predefined, or at least, bounded, and governed by the laws of Physics. Their execution must be learned after continuous practice over time. Literature suggests that artificial intelligence algorithms, such as those used for computer vision, can model the movements performed. Thus, they can be compared with a good execution as well as analyze their temporal evolution during learning. We are exploring the application of this approach to model psychomotor performance in Karate combats (called kumites), which are characterized by the explosiveness of their movements. In addition, modeling psychomotor performance in a kumite requires the modeling of the joint interaction of two participants, while most current research efforts in human movement computing focus on the modeling of movements performed individually. Thus, in this work, we explore how to apply a pose estimation algorithm to extract the features of some predefined movements of Ippon Kihon kumite (a one-step conventional assault) and compare classification metrics with four data mining algorithms, obtaining high values with them.

Application of an Artificial Neural Network to Automate the Measurement of Kinematic Characteristics of Punches in Boxing

This work aimed to study the automation of measuring the speed of punches of boxers during shadow boxing using inertial measurement units (IMUs) based on an artificial neural network (ANN). In boxing, for the effective development of an athlete, constant control of the punch speed is required. However, even when using modern means of measuring kinematic parameters, it is necessary to record the circumstances under which the punch was performed: The type of punch (jab, cross, hook, or uppercut) and the type of activity (shadow boxing, single punch, or series of punches). Therefore, to eliminate errors and accelerate the process, that is, automate measurements, the use of an ANN in the form of a multilayer perceptron (MLP) is proposed. During the experiments, IMUs were installed on the boxers’ wrists. The input parameters of the ANN were the absolute acceleration and angular velocity. The experiment was conducted for three groups of boxers with different levels of training. The developed model showed a high level of punch recognition for all groups, and it can be concluded that the use of the ANN significantly accelerates the collection of data on the kinetic characteristics of boxers’ punches and allows this process to be automated.

Optical motion capture dataset of selected techniques in beginner and advanced Kyokushin karate athletes

Human motion capture is commonly used in various fields, including sport, to analyze, understand, and synthesize kinematic and kinetic data. Specialized computer vision and marker-based optical motion capture techniques constitute the gold-standard for accurate and robust human motion capture. The dataset presented consists of recordings of 37 Kyokushin karate athletes of different ages (children, young people, and adults) and skill levels (from 4th dan to 9th kyu) executing the following techniques: reverse lunge punch (Gyaku-Zuki), front kick (Mae-Geri), roundhouse kick (Mawashi-Geri), and spinning back kick (Ushiro-Mawashi-Geri). Each technique was performed approximately three times per recording (i.e., to create a single data file), and under three conditions where participants kicked or punched (i) in the air, (ii) a training shield, or (iii) an opponent. Each participant undertook a minimum of two trials per condition. The data presented was captured using a Vicon optical motion capture system with Plug-In Gait software. Three dimensional trajectories of 39 reflective markers were recorded. The resultant dataset contains a total of 1,411 recordings, with 3,229 single kicks and punches. The recordings are available in C3D file format. The dataset provides the opportunity for kinematic analysis of different combat sport techniques in attacking and defensive situations.

Improving Human Motion Classification by Applying Bagging and Symmetry to PCA-Based Features

This paper proposes a method for improving human motion classification by applying bagging and symmetry to Principal Component Analysis (PCA)-based features. In contrast to well-known bagging algorithms such as random forest, the proposed method recalculates the motion features for each “weak classifier” (it does not randomly sample a feature set). The proposed classification method was evaluated on a challenging (even to a human observer) motion capture recording dataset of martial arts techniques performed by professional karate sportspeople. The dataset consisted of 360 recordings in 12 motion classes. Because some classes of these motions might be symmetrical (which means that they are performed with a dominant left or right hand/leg), an analysis was conducted to determine whether accounting for symmetry could improve the recognition rate of a classifier. The experimental results show that applying the proposed classifiers’ bagging procedure increased the recognition rate (RR) of the Nearest-Neighbor (NNg) and Support Vector Machine (SVM) classifiers by more than 5% and 3%, respectively. The RR of one trained classifier (SVM) was higher when we did not use symmetry. On the other hand, the application of symmetry information for bagged NNg improved its recognition rate compared with the results without symmetry information. We can conclude that symmetry information might be helpful in situations in which it is not possible to optimize the decision borders of the classifier (for example, when we do not have direct information about class labels). The experiment presented in this paper shows that, in this case, bagging and mirroring might help find a similar object in the training set that shares the same class label. Both the dataset that was used for the evaluation and the implementation of the proposed method can be downloaded, so the experiment is easily reproducible.

Kinematic Analysis of Mae-Geri Kicks in Beginner and Advanced Kyokushin Karate Athletes

Background: Each of the techniques used in sport is a complex technique requiring a combination of neuromuscular conduction, motor anticipation, and extremely developed proprioception. This is especially the case in martial arts when we deal with a kick or a blow to a specific target. Methods: The main purpose of this study was to determine the kinematic differences in the tested movement pattern among athletes with different levels of advancement in the conditions of kicking: in the air, at a target (a shield), and in direct contact with a competitor. Comparative analysis was performed among 26 players: 13 advanced (group G1) and 13 beginners (group G2). Kinematic data was recorded using an optical motion capture system. The examination consisted of performing three tests of mae-geri kick in sequences of three kicks in three different conditions (without a target, with a static target, and with an opponent). The examination was performed with the back leg and only the moment of kick was analyzed. Results: The most significant differences were observed in the movement of head, torso, hip, knee, and ankle segments, especially during a kick at a shield. Based on the conducted analysis, we can assume that karate training changes the strategy of neuromuscular control, promoting improvement of mobility pattern efficiency. Conclusion: Acquiring this type of knowledge can lead to better results, elimination of errors in training, especially in the initial period of training, and the prevention of possible injuries that occur during exercise or competition.

Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance

Objective assessment of an athlete's performance is of importance in elite sports to facilitate detailed analysis. The implementation of automated detection and recognition of sport-specific movements overcomes the limitations associated with manual performance analysis methods. The object of this study was to systematically review the literature on machine and deep learning for sport-specific movement recognition using inertial measurement unit (IMU) and, or computer vision data inputs. A search of multiple databases was undertaken. Included studies must have investigated a sport-specific movement and analysed via machine or deep learning methods for model development. A total of 52 studies met the inclusion and exclusion criteria. Data pre-processing, processing, model development and evaluation methods varied across the studies. Model development for movement recognition were predominantly undertaken using supervised classification approaches. A kernel form of the Support Vector Machine algorithm was used in 53% of IMU and 50% of vision-based studies. Twelve studies used a deep learning method as a form of Convolutional Neural Network algorithm and one study also adopted a Long Short Term Memory architecture in their model. The adaptation of experimental set-up, data pre-processing, and model development methods are best considered in relation to the characteristics of the targeted sports movement(s).

Human Actions Analysis: Templates Generation, Matching and Visualization Applied to Motion Capture of Highly-Skilled Karate Athletes

The aim of this paper is to propose and evaluate the novel method of template generation, matching, comparing and visualization applied to motion capture (kinematic) analysis. To evaluate our approach, we have used motion capture recordings (MoCap) of two highly-skilled black belt karate athletes consisting of 560 recordings of various karate techniques acquired with wearable sensors. We have evaluated the quality of generated templates; we have validated the matching algorithm that calculates similarities and differences between various MoCap data; and we have examined visualizations of important differences and similarities between MoCap data. We have concluded that our algorithms works the best when we are dealing with relatively short (2–4 s) actions that might be averaged and aligned with the dynamic time warping framework. In practice, the methodology is designed to optimize the performance of some full body techniques performed in various sport disciplines, for example combat sports and martial arts. We can also use this approach to generate templates or to compare the correct performance of techniques between various top sportsmen in order to generate a knowledge base of reference MoCap videos. The motion template generated by our method can be used for action recognition purposes. We have used the DTW classifier with angle-based features to classify various karate kicks. We have performed leave-one-out action recognition for the Shorin-ryu and Oyama karate master separately. In this case, 100% actions were correctly classified. In another experiment, we used templates generated from Oyama master recordings to classify Shorin-ryu master recordings and vice versa. In this experiment, the overall recognition rate was 94.2%, which is a very good result for this type of complex action.

The adaptation of GDL motion recognition system to sport and rehabilitation techniques analysis

The main novelty of this paper is presenting the adaptation of Gesture Description Language (GDL) methodology to sport and rehabilitation data analysis and classification. In this paper we showed that Lua language can be successfully used for adaptation of the GDL classifier to those tasks. The newly applied scripting language allows easily extension and integration of classifier with other software technologies and applications. The obtained execution speed allows using the methodology in the real-time motion capture data processing where capturing frequency differs from 100 Hz to even 500 Hz depending on number of features or classes to be calculated and recognized. Due to this fact the proposed methodology can be used to the high-end motion capture system. We anticipate that using novel, efficient and effective method will highly help both sport trainers and physiotherapist in they practice. The proposed approach can be directly applied to motion capture data kinematics analysis (evaluation of motion without regard to the forces that cause that motion). The ability to apply pattern recognition methods for GDL description can be utilized in virtual reality environment and used for sport training or rehabilitation treatment.