To read the full-text of this research, you can request a copy directly from the authors.
Abstract
The objective of this study was to discriminate different types of punches based on signals measured by gyro sensors. If a boxer consistently uses the same pattern of attack, his opponent could easily determine what type of punch is coming next. Thus, by feeding back information on the frequency of each type of punch, the attack pattern can be identified and the counterattack can be improved.
To read the full-text of this research, you can request a copy directly from the authors.
... Due to these values, we can estimate a realistic upper limit to 10 000 N considering the force of a kick like two times the punch's one. The use of acceleration measurements has been proposed in [11] but limited to a single-axis while, as discussed Biometric performance measurements in combat sports ...
... Navas et al. [21] [22] devised a training glove aimed at aiding fighters in mastering defensive techniques and punching mechanics to enhance their endurance. Morita et al. [20] [10]introduced a system capable of distinguishing between various punch types based on signals recorded by gyro sensors. This system provides valuable feedback on a boxer's attacking patterns to refine their fighting style. ...
In competitive combat sports like boxing, analyzing a boxers's performance statics is crucial for evaluating the quantity and variety of punches delivered during bouts. These statistics provide valuable data and feedback, which are routinely used for coaching and performance enhancement. We introduce BoxMAC, a real-world boxing dataset featuring 15 professional boxers and encompassing 13 distinct action labels. Comprising over 60,000 frames, our dataset has been meticulously annotated for multiple actions per frame with inputs from a boxing coach. Since two boxers can execute different punches within a single timestamp, this problem falls under the domain of multi-label action classification. We propose a novel architecture for jointly recognizing multiple actions in both individual images and videos. We investigate baselines using deep neural network architectures to address both tasks. We believe that BoxMAC will enable researchers and practitioners to develop and evaluate more efficient models for performance analysis. With its realistic and diverse nature, BoxMAC can serve as a valuable resource for the advancement of boxing as a sport
... In recent years, triboelectric nanogenerators (TENGs), which transform mechanical energy into electrical energy through triboelectric effects and electrostatic induction, have proven to be a method of energy harvesting that is inexpensive, portable, efficient, and easy to miniaturize. [16][17][18][19][20][21][22] Fluid power collection utilizing TENGs has been the subject of a large amount of study and development to date. In the context of carbon neutrality, the development and application of new energy technologies are crucial. ...
Recently, intelligent sports monitor devices based on self-powered sensor technology have received widespread attention. Here, we designed a triboelectric nanogenerator based on a poly(vinylidene fluoride-vinyl chloride) PV(DF-A) film and a polydimethylsiloxane (PDMS) film (PP-TENG) to harvest bio-mechanical energy and serve as the basketball training sensor. After experimental testing, the electron loss ability of the PV(DF-A) film is greater than that of a polyvinylidene fluoride film. Also, the open-circuit voltage (Voc) and short-circuit current density (Jsc) of PP-TENG can get to 1856.4 V and 269 mA m−2, respectively. The PP-TENG can obtain a maximum power density of 130.28 W m−2. Moreover, the PP-TENG sensor can monitor various gait patterns of players in basketball and achieve auxiliary analysis of basketball training strategies. This research will promote the development of intelligent basketball training sensors.
... The creation of stretchy electrodes is essential for the realization of stretchable TENGs. There have been reports of stretchable TENGs with electrodes comprised of conductive filler-percolation composites, ionic solutions, gels [28,29]. The low modulus and high elasticity of ionconductive gel electrodes, such as hydrogels, ionic gels, and organogels, are advantageous. ...
The research of boxing has been paid more and more attention in today's sports field. And the research and development of relevant monitoring equipment is very important, especially wearable sports monitoring equipment. In this work, we proposed a novel hydrogel triboelectric nanogenerator (H-TENG) with self-healing function to obtain bio-mechanical energy and boxing training monitoring. The H-TENG follows the single-electrode working mode. In detail, the polydimethylsiloxane (PDMS) serve as the triboelectric layer and the ionic hydrogel play the role of conductive electrode. According to the experimental results, the Voc and Isc of the H-TENGs are 90 V, 0.72 μA, respectively. The H-TENG can be installed on the boxing glove to monitor boxing motion information to achieve the self-powered sports sensor. Our research will promote the development of self-powered sports sensor.
... The output results from this experimental process proved the efficient outperforming of our proposed IoT-based Sport jacket when compared with similar existing systems in respect to the accuracy of measurements and the fast response time. Figure 5 depicts the recorded angular signal of consecutive hits that are detected by used force sensors [38], [39]. These signals illustrate the angular velocity for varying punches of kick-boxing. ...
... The output results from this experimental process proved the efficient outperforming of our proposed IoT-based Sport jacket when compared with similar existing systems in respect to the accuracy of measurements and the fast response time. Figure 5 depicts the recorded angular signal of consecutive hits that are detected by used force sensors [38], [39]. These signals illustrate the angular velocity for varying punches of kick-boxing. ...
Athletes encounter different types of hits, which sometimes could be strong or light hits. Heavy or strong hits on some parts of an athlete's body such as the chest or lungs may be harmful and cause severe damage to the human body. In some cases, the heavy hits may cause heart failure or a serious lung rupture. In the athlete's healthcare domain, there are potential trails efforts based on Internet-of-Thing (IoT) technology; however, building a comprehensive and efficient system is still a demanding concern. In this paper, we present a new comprehensive real-time platform for monitoring athletes during Mixed Martial Arts (MMA). The proposed real-time monitoring platform is called the IoT-Sports Health system, which particularly fuses based on IoT devices with in-sport healthcare services. Therefore, our proposed system is integrated, designed, and implemented to monitor and measure the athlete's body temperature, strike force, and the number of strikes that the athlete has been received from the opponent. Several real field trials and many experiments proved the feasibility of our proposed IoT-Sport health system, which directly and automatically plays a significant role in chest guarding against heavy and strong strikes. Furthermore, our proposed real-time monitoring system can be easily deployed to monitor aging people that suffering from chronic diseases in-home. In conclusion, experimental tests are performed to evaluate the proposed IoT-Sports Health system by applying a real case on three different matches. The obtained results proved that our proposed IoT-Sports Health system outperforms similar systems with respect to the accuracy, and regarding to the response time.
... However, with the recent technological advances, micro-electromechanical sensor systems (MEMS) are becoming more widely implemented for the purposes of obtaining more sensitive and sport-specific information (compared to human observation commonly used in sport praxis) in relation to the level of achieved preparedness in athletes [20,21]. In this sense, fairly recent papers [18,22] point to the possibility of applicable use of IMUs (Inertial Measurement Unit) in combat sports, while similar solutions have been widely developed and implemented in other sport disciplines. Papers [23,24] have shown that IMUs can be used to provide information on different phases of the movement in baseball pitching and golf swing, respectively, while a paper [25] provides an exemplary overview on the use of inertial sensors for the purposes of human motion tracking. ...
To achieve good performance, athletes need to synchronize a series of movements in an optimal manner. One of the indicators used to monitor this is the order of occurrence of relevant events in the movement timeline. However, monitoring of this characteristic of rapid movement is practically limited to the laboratory settings, in which motion tracking systems can be used to acquire relevant data. Our motivation is to implement a simple-to-use and robust IMU-based solution suitable for everyday praxis. In this way, repetitive execution of technique can be constantly monitored. This provides augmented feedback to coaches and athletes and is relevant in the context of prevention of stabilization of errors, as well as monitoring for the effects of fatigue. In this research, acceleration and rotational speed signal acquired from a pair of IMUs (Inertial Measurement Unit) is used for detection of the time of occurrence of events. The research included 165 individual strikes performed by 14 elite and national-level karate competitors. All strikes were classified as slow, average, or fast based on the achieved maximal velocity of the hand. A Kruskal–Wallis test revealed significant general differences in the order of occurrence of hand acceleration start, maximal hand velocity, maximal body velocity, maximal hand acceleration, maximal body acceleration, and vertical movement onset between the groups. Partial differences were determined using a Mann–Whitney test. This paper determines the differences in the temporal structure of the reverse punch in relation to the achieved maximal velocity of the hand as a performance indicator. Detecting the time of occurrence of events using IMUs is a new method for measuring motion synchronization that provides a new insight into the coordination of articulated human movements. Such application of IMU can provide additional information about the studied structure of rapid discrete movements in various sporting activities that are otherwise imperceptible to human senses.
... It is noticed that these parameters are key components in deciding the boxing performance. A gyrosensor-based device is presented to differentiate the four different types of punches, 13 and a device was developed for 3D kinetics and kinematics of maximal effort punches. 14 There are studies and devices that either focused on punch force analysis or attempted to assess the kinematic parameters. ...
... 3D kinematics of straight and hook punches found an elevation of the wrist above the elbow, as described by the coaches (Whiting, Gregor, & Finerman, 1988). In conjunction with the elevated wrist, Morita et al. (2011) pinpointed a rotation of the wrist in the same plane, as again explained by the experienced coaches. Much like the hip and shoulder rotation literature, no research was found that compared 'good' and 'bad' kinematics in relation to the variables provided by the coaches. ...
Traditionally, the field of sports science has been interested in conducting research that is predominately quantitative in nature. Although this approach has provided significant findings, this has led to expert coaches' experiential knowledge being neglected in favour of empirical knowledge. By investigating punching in boxing, we are interested in developing an understanding of whether elite coaches, through their experiential knowledge, intuitively identify key characteristics of effective punching as identified in controlled experimental research. For this purpose, five interviews were conducted with professional and amateur boxing coaches. From this qualitative approach it was evident that coaches' knowledge was consistent with that of the empirical research on effective punching performance with four principal components emerging from the interview data. These included: 1) whole body movement, 2) footwork, 3) hip and shoulder rotation, and 4) hand and arm position. The data illuminated how coaches' knowledge can be used to strengthen empirical findings in sports performance, in this case punching in boxing. Additionally, characteristics of performance that were discussed by coaches that were not identified in the empirical literature highlight directions for further research regarding effective punching technique, an area that requires further investigation before conclusive structures of good practice can be applied.
... Morita et. al. [4] proposed an approach for box punch classifications based on 3D gyrometer sensor data. The developed hardware system is placed on the waist of the athletes and communicates with the classification unit via bluetooth. ...
Competitive sporting environments demand reliable statistics on an athlete’s performance to measure an athlete’s actions during competition, and to differentiate between the fine-grained actions performed. This is especially true for combat sports such as boxing where the variations observed between main punching actions are subtle, making automatic classification and the assessment of quality movements extremely difficult. This paper presents a robust framework for the automatic classification of a boxer’s punches. Overhead depth imagery is employed to alleviate challenges associated with occlusions, and robust body-part tracking is developed for the noisy time-of-flight sensors. Punch recognition is addressed through multi-class Support Vector Machine (SVM) and Random Forest classifiers using combination of features. A coarse-to-fine hierarchical SVM classifier is presented in this paper based on prior knowledge of boxing punches. This framework has been applied to boxing image sequences taken at the Australian Institute of Sport with 14 elite boxers. Results demonstrate the effectiveness of the action recognition method, with the hierarchical SVM classifier yielding a 97.3% accuracy improving on the recent state-of-the-art action recognition systems.
This paper presents the design of a wearable system for measurements of athlete's performance in combat sports. The system provides objective measurements of athletes' shots, posture, and movements, and of the effectiveness of their training. The proposed instrumentation is useful to overcome the limits of traditional training methods, which are characterized by a subjective evaluation of the training effectiveness by a coach. The measuring system consists of a distributed network of three battery-powered wireless-sensing node types, worn by the athletes, and one master node, which is in charge of signal acquisition and processing tasks. The master node elaborates training statistics and visualizes them, either in real time during a combat session, or off-line for posttraining analysis. The wearable measuring system has been tested through real combat training sessions of athletes with different weights, ages, and experiences, both male and female. Different from the state-of-art athletes' biometric measurement machines, which are cumbersome and expensive, the proposed system is designed to ensure a low-cost and wearable implementation and to give easy-to-understand feedbacks during training, particularly to nonprofessional athletes.
Wearable technology for physical activity recognition has emerged as one of the fastest growing research fields in recent years. A great variety of body-worn motion capture and tracking systems have been designed for a wide range of applications including medicine, health care, well-being, and gaming. In this paper we present an experimental inertial measurement system for physical impact analysis in sport-science applications. The presented system is a small cordless wearable device intended to track athletes physical activity during intensive workout sessions. The main distinctive feature of the system is its capability to detect and measure a wide range of shock intensities typical for many active sports, including martial arts, baseball, football, hockey, etc. Tracking of the sport specific irregular and fast movements is another important aspect addressed in the presented experimental system. In this paper we present the hardware-software architecture of the system and discuss preliminary in-field experimental results.
Computer vision offers a growing capacity to detect and classify actions in a large range of sports. Since combat sports are highly dynamic and physically demanding, it is difficult to measure features of performance from competition in a safe and practical way. Also, coaches frequently wish to measure the performance characteristics of other competitors. For these reasons it is desirable to be able to measure features of competitive performance without using sensors or physical devices. We present a non-invasive method for extracting pose and features of behaviour in boxing using vision cameras and time of flight sensors. We demonstrate that body parts can be reliably located, which allow punching actions to be detected. Those data can then visualised in a way that allows coaches to analysis behaviour.
This paper describes the measurement and analysis of a player's motion while making a jump shot in basketball. In order to increase the probability of a shot going into the basket, a player must develop good shooting form. We find the features of the motion that leads to a good jump shot using a simple sensoring device that combines a 3-D acceleration sensor and a gyroscopic sensor. Players practiced jump shots with the device mounted on the back of their hand to help them correct the errors in their shooting through sound feedback based on these features. The results of the experiments show that the device can improve a player's shooting form.
This paper describes the measurement and analysis of the human form when running. When people walk or run, they perform these activities unconsciously. While individuals have their own ways of walking and running, there may be ideal forms of movement that are more efficient, in the sense of minimizing the physical burden. In this study, by referring to the running form of track and field athletes, we define a beneficial jogging form and build a biofeedback system that enables a person to approach that superior form. A 3-D acceleration sensor and gyro sensor were used as the means of measurement to analyze such superior movement.
ResearchGate has not been able to resolve any references for this publication.