Artificial intelligence (AI) has become an interdisciplinary subject that integrates digital image processing, machine learning, and computer science, etc. A lot of work in martial arts benefits from AI technology. In this paper, we highlight and summarize the applications of AI in martial arts and indicate the main progress of related studies. Through the investigation of martial arts styles, tasks, data acquisition methods, and algorithm improvements, a paradigm that represents a possible technological process for an intelligent martial arts training system was summarized. These applications bring more scientific training and more effective technical analysis to martial arts. Furthermore, this paper delves into specific AI applications in areas such as action recognition, pose estimation, action evaluation, elite athlete support, sports betting, health care, animation generation, and competition field segmentation. By exploring these areas, the research prospects of AI applications in martial arts are comprehensively discussed. This paper inspires further research on martial arts by using AI, which includes helping researchers expand their research ideas and research methods, identify frontier issues, and innovate based on existing research.
MartínkováIParryJ.Martial categories: clarification and classification. J Philos Sport2016; 43(1): 143–162.
6.
CharlesMTerryF MD. The martial arts. J Philos Sport2006; 17(3): 645–676.
7.
AnglemanAJShinzatoYVan HasseltVB, et al. Traditional martial arts versus modern self-defense training for women: some comments. Aggress Violent Behav2009; 14(2): 89–93.
8.
DourisPChinanAGomezM, et al. Fitness levels of middle aged martial art practitioners. Br J Sports Med2004; 38(2): 143–147. discussion 147.
9.
TsangTWKohnMChowCM, et al. Health benefits of kung fu: a systematic review. J Sports Sci2008; 26(12): 1249–1267.
10.
BuBHaijunHYongL, et al. Effects of martial arts on health status: a systematic review. J Evid Based Med2010; 3(4): 205–219.
11.
Origua RiosSMarksJEstevanI, et al. Health benefits of hard martial arts in adults: a systematic review. J Sports Sci2018; 36(14): 1614–1622.
12.
YuqingZMingliangCHaoyangZ, et al. VR technology and application in martial arts. In: 2021 IEEE 7th international conference on virtual reality(ICVR), pp.240–245. DOI: 10.1109/ICVR51878.2021.9483700.
13.
PangYWangQZhangC, et al. Analysis of computer vision applied in martial arts. In: 2022 2nd international conference on consumer electronics and computer engineering(ICCECE), pp.191–196. DOI: 10.1109/ICCECE54139.2022.9712803.
14.
KeY. Application of artificial intelligence in large-scale international wushu (taolu) events. In: 2021 2nd international conference on big data & artificial intelligence & software engineering (ICBASE), pp.575–578. DOI: 10.1109/ICBASE53849.2021.00113.
15.
ZhangD. Research on the innovative development of Chinese mixed martial arts (MMA) events based on artificial intelligence. In: 2021 3rd international conference on machine learning, big data and business intelligence(MLBDBI), pp.785–788. DOI: 10.1109/MLBDBI54094.2021.00153.
16.
TitsMLarabaSCaulierE, et al. Umons-taichi: a multimodal motion capture dataset of expertise in Taijiquan gestures. Data Brief2018; 19: 1214–1221.
17.
ZhangWLiuZZhouL, et al. Martial arts, dancing and sports dataset: a challenging stereo and multi-view dataset for 3d human pose estimation. Image Vis Comput2017; 61: 22–39.
18.
de Souza VicenteCNascimentoEEmeryL, et al. High performance moves recognition and sequence segmentation based on key poses filtering. In: 2016 IEEE winter conference on applications of computer vision(WACV), pp.1–8. IEEE.
19.
LeeJJungH.Tuhad: taekwondo unit technique human action dataset with key frame-based cnn action recognition. Sensors2020; 20(17): 4871.
20.
HachajTOgielaM. Classification of karate kicks with hidden Markov models classifier and angle-based features. In: 2018 11th international congress on image and signal processing, biomedical engineering and informatics(CISP-BMEI), pp.1–5. IEEE.
21.
HachajTOgielaMPiekarczykM. The open online repository of karate motion capture data: a tool for scientists and sport educators. In: 2017 IEEE symposium series on computational intelligence(SSCI), pp.1–5. IEEE.
22.
ScottJRavichandranBFunkC, et al. From image to stability: learning dynamics from human pose. In: European conference on computer vision, pp.536–554. Springer.
23.
HitkulKAYadavNDwivedyM. A comparative study of machine learning algorithms for prior prediction of ufc fights. In: YadavNYadavABansalJ, et al. (eds) Harmony search and nature inspired optimization algorithms advances in intelligent systems and computing. Gurgaon: Springer Singapore, 2018, pp. 67–76.
NiewiadomskiRKolykhalovaKPianaS, et al. Analysis of movement quality in full-body physical activities. ACM Trans Interact Intell Syst2019; 9(1): 1–20.
26.
WagnerTJägerJWolffV, et al. A machine learning driven approach for multivariate timeseries classification of box punches using smartwatch accelerometer sensordata. In 2019 Innovations in Intelligent Systems and Applications Conference (ASYU). pp. 1–6. DOI:10.1109/ASYU48272.2019.8946422.
27.
ChenXChenZLiY, et al. Immertai: immersive motion learning in VR environments. J Vis Commun Image Represent2019; 58: 416–427.
28.
ChoDLeeHLeeW, et al. Detecting anomalous kicks in taekwondo with spatial and temporal features. IEEE Access2021; 9: 164928–164934.
29.
SiarohinALathuilièreSTulyakovS, et al. First order motion model for image animation. Advances in Neural Information Processing Systems2019; 32.
30.
SzczęsnaABłaszczyszynMPawlytaM.Optical motion capture dataset of selected techniques in beginner and advanced kyokushin karate athletes. Sci Data2021; 8(1): 13.
31.
KhasanshinIOsipovA.Using an artificial neural network to develop an optimal model of straight punch in boxing and training in punch techniques based on this model and real-time feedback. PLoS One2021; 16(11): 1–17.
32.
XuLWangQLinX, et al. Skeleton-based tai chi action segmentation using trajectory primitives and content. Neural Comput Appl2023; 35(13): 9549–9566.
33.
HudovernikVSkocajD. Video-based detection of combat positions and automatic scoring in jiu-jitsu. In: Proceedings of the 5th international ACM workshop on multimedia content analysis in sports. MMSports ‘22, pp.55–63. New York, NY: Association for Computing Machinery. ISBN 9781450394888. DOI: 10.1145/3552437.3555707.
34.
RodrigoMCuevasCBerjónD, et al. Automatic highlight detection in videos of martial arts tricking. Multimed Tools Appl2023; 83(6): 17109–17133.
35.
SunSWangFLiangQ, et al. Taichi: a fine-grained action recognition dataset. In: Proceedings of the 2017 ACM on international conference on multimedia retrieval. ICMR ‘17, pp.429–433. New York, NY: Association for Computing Machinery. DOI: 10.1145/3078971.3079039.
36.
WangHKläserASchmidC, et al. Dense trajectories and motion boundary descriptors for action recognition. Int J Comput Vis2013; 103(1): 60–79.
37.
HoshinoKNoguchiYNakaiY, et al. Predicting the types of striking and thrusting motions by using deep learning. In: Proceedings of the 2019 6th international conference on biomedical and bioinformatics engineering, ICBBE ‘19, pp.199–202. New York, NY: Association for Computing Machinery. ISBN 9781450372992. DOI: 10.1145/3375923.3375954.
38.
WuEKoikeH. Futurepose -mixed reality martial arts training using real-time 3D human pose forecasting with a rgb camera. In: 2019 IEEE winter conference on applications of computer vision (WACV), pp.1384–1392. DOI: 10.1109/WACV.2019.00152.
39.
HörhanMEidenbergerH. New content-based features for the distinction of violent videos and martial arts. In: 2013 IEEE international conference on acoustics, speech and signal processing, pp.1836–1839. DOI: 10.1109/ICASSP.2013.6637970.
40.
MishraASrinivasaG. Automated detection of fighting styles using localized action features. In: 2018 2nd international conference on inventive systems and control (ICISC), pp.1385–1389. DOI: 10.1109/ICISC.2018.8399036.
41.
WangJ.Research on wushu movement decomposition method based on image recognition. Mod Electron Tech2017; 40(15): 33–36.
42.
SunRSunYDuanL, et al. Taijiquan key action recognition algorithm based on perceptron network. China New Telecommunications2021, in Chinese.
43.
PouloseAKimJHanD. Motion classifier using deep learning architecture. In: The 2nd Korea artificial intelligence conference, pp.16–18.
44.
KongYWeiZHuangS.Automatic analysis of complex athlete techniques in broadcast taekwondo video. Multimed Tools Appl2018; 77(11): 13643–13660.
45.
ZhangHGuoHLiangC, et al. Grading tai chi performance in competition with rgbd sensors. In: AgapitoLBronsteinMMRotherC (eds) Computer vision -ECCV 2014 workshops, pp.3–13. Cham: Springer International Publishing, 2014.
46.
SalazarKGarciaJMateusA, et al. Autonomous recognition of martial arts forms using rgb-d cameras. In: 2017 Congreso Internacional de Innovacion y Tendencias en Ingenieria (CONIITI), pp.1–5. IEEE.
47.
HachajTOgielaMKoptyraK.Application of assistive computer vision methods to oyama karate techniques recognition. Symmetry2015; 7(4): 1670–1698.
48.
HongSKimMKimY. Kick recognition system using dual rgb-d cameras. In: Proceedings of the 2018 the 2nd international conference on video and image processing, pp.12–16.
BiancoSTisatoF. Karate moves recognition from skeletal motion. In: BaskurtAMSitnikR (eds) Three-dimensional image processing (3DIP) and applications 2013, vol. 8650, pp.86500K. Burlingame, California: International Society for Optics and Photonics, 2013, pp. 86500K1–86500K10.
51.
HachajT. Key frames detection in motion capture recordings using machine learning approaches. In: International conference on image processing and communications, pp.79–86. Springer.
52.
HachajTOgielaMRKoptyraK.Human actions recognition from motion capture recordings using signal resampling and pattern recognition methods. Ann Oper Res2018; 265(2): 223–239.
53.
HachajTOgielaMKoptyraK. Human actions modelling and recognition in low-dimensional feature space. In: 2015 10th international conference on broadband and wireless computing, communication and applications (BWCCA), pp.247–254. IEEE.
54.
HachajTOgielaMPiekarczykM. Dependence of kinect sensors number and position on gestures recognition with gesture description language semantic classifier. In: 2013 federated conference on computer science and information systems, pp. 571–575. IEEE.
55.
HachajTOgielaM. Computer karate trainer in tasks of personal and homeland security defense. In: International conference on availability, reliability, and security, pp.430–441. Springer.
56.
HachajTOgielaMKoptyraK. Application of hidden Markov models and gesture description language classifiers to oyama karate techniques recognition. In: 2015 9th international conference on innovative mobile and internet services in ubiquitous computing, pp.160–165. IEEE.
57.
HachajTOgielaMKoptyraK.Effectiveness comparison of kinect and kinect 2 for recognition of oyama karate techniques. In: 2015 18th international conference on network-based information systems, pp.332–337. IEEE.
58.
HachajTOgielaM. Computer system prototype for qualitative and quantitative evaluation of selected movement activities, pp. 73–76. DOI: 10.1145/3332305.3332309.
59.
IdrisWRafiABidinA. Evaluating extrinsic feedback of martial art techniques using minimal values of rules in frame-based rules ranges. In: 2018 IEEE conference on systems, process and control (ICSPC), pp.112–117. DOI: 10.1109/SPC.2018.8703983.
60.
IdrisWMRWRafiABidinA, et al. Developing new robust motion templates of martial art techniques using r-gdl approach: a case study of sscm. Int J Arts Technol2019; 11(1): 36.
61.
WenX. Research on the registration of Tai Chi video clips. Master’s Thesis, 2019, in Chinese. DOI: 10.27426/d.cnki.gxtdu.2019.000570.
62.
YeSWenX.Taichi video registration method based on joint angle and dtw. Comput Technol Autom2020; 39(01): 117–122.
63.
GuoH. Research and implementation of action training system on key point detection. Master’s Thesis, 2021, in Chinese. DOI: 10.27398/d.cnki.gxalu.2021.000248.
64.
ZhangKPangYWangQ, et al. Action recognition and temporal localization for wushu routine competition: taking the international long fist routine v3 as an example. In: Proceedings of the 14th international conference on educational technology and computers. DOI: 10.1145/3572549.3572643.
65.
DongLLiDLiS, et al. Tai chi action recognition based on structural lstm with attention module. In: 2019 international conference on image and video processing, and artificial intelligence, vol. 11321, p. 113211O. International Society for Optics and Photonics.
66.
LiX. Research on skeletal gesture recognition based on a spatio-temporal feature network. Master’s Thesis, 2022, in Chinese. DOI: 10.27670/d.cnki.gcqdu.2022.002973.
67.
LiXLiaJLiuL, et al. Recognizing skeleton-based hand gestures by a spatio-temporal network. In: DongYKourtellisNHammerB (eds) Machine learning and knowledge discovery in databases. Applied data science track, pp.151–167. Cham: Springer International Publishing, 2021.
68.
EcheverriaJSantosO. Punch anticipation in a karate combat with computer vision. In: Adjunct proceedings of the 29th ACM conference on user modeling, adaptation and personalization, pp. 61–67.
69.
EcheverriaJKumitronCSO. Artificial intelligence system to monitor karate fights that synchronize aerial images with physiological and inertial signals. In: 26th international conference on intelligent user interfaces-companion, pp.37–39.
70.
EcheverriaJSantosO. Kumitron: A multimodal psychomotor intelligent learning system to provide personalized support when training karate combats. maied’21 workshop. In: The first international workshop on multimodal artificial intelligence in education.
71.
YanSXiongYLinD. Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol. 32. DOI: 10.1609aaai.v32i1.12328.
72.
LiMChenSChenX, et al. Actional-structural graph convolutional networks for skeleton-based action recognition. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp.3590–3598. DOI: 10.1109/CVPR.2019.00371.
73.
GuoJLiXLiuJ, et al. The application of behavior recognition technology based on graph convolutional network in karate tactics analysis. J Nat Sci Hunan Norm Univ2021; 44(18): 81–87.
74.
LiuJ. Research on key algorithms in tactical intelligence analysis system of karate competition video. Master’s Thesis, 2020, in Chinese. DOI: 10.27137/d.cnki.ghusu.2020.000419.
75.
GuoJLiuHLiX, et al. An attention enhanced spatial–temporal graph convolutional LSTM network for action recognition in karate. Appl Sci2021; 11(18): 8641.
76.
XieJLiXZhouH, et al. Weak supervised behavior recognition algorithm based on domain knowledge graph. In: 2021 4th international conference on advanced electronic materials, computers and software engineering (AEMCSE), pp.899–904. IEEE.
77.
WangZ. Human motion evaluation method based on multimodal information. Master’s Thesis, 2020, in Chinese. DOI: 10.27075/d.cnki.ghzdc.2020.000125.
78.
ZhouY. Research on long sequence action recognition and prediction. Master’s Thesis, 2021, in Chinese. DOI: 10.27426/d.cnki.gxtdu.2021.001534.
79.
YeSZhouYFanH, et al. Joint learning of causality and spatio-temporal graph convolutional network for skeleton-based action recognition. Comput Sci2021; 48: 130–135. DOI: 10.11896/jsjjx.201200205
80.
TitsMTilmanneJDutoitT. Morphology independent feature engineering in motion capture database for gesture evaluation. In: Proceedings of the 4th international conference on movement computing. MOCO ‘17. New York, NY: Association for Computing Machinery. ISBN 9781450352093. DOI: 10.1145/3077981.3078037.
81.
CizmicDHoelblingDBaranyiR, et al. Smart Boxing Glove “RD α”: imu combined with force sensor for highly accurate technique and target recognition using machine learning. Appl Sci2023; 13(16): 9073.
82.
LinSLinYChenC, et al. Learning and inferring human actions with temporal pyramid features based on conditional random fields. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 2617–2621. IEEE.
83.
BurdackJHorstFAragonésD, et al. Fatigue-related and timescale-dependent changes in individual movement patterns identified using support vector machine. Front Psychol2020; 11: 2273.
84.
ShanWFangZWangJ, et al. Design of intelligent boxing gloves based on arduino and neural network. Journal of Fuyang Normal University (Natural Science)2020; 37(03): 54–58.
85.
XuLWangQYuanL, et al. Using trajectory features for tai chi action recognition. In: 2020 IEEE international instrumentation and measurement technology conference (I2MTC).
86.
LiHYapHJKhooS.Motion classification and features recognition of a traditional Chinese sport (Baduanjin) using sampled-based methods. Appl Sci2021; 11(16): 7630.
87.
KlempousRKluwakKAtsushiI, et al. Neural networks classification for training of five German longsword mastercuts-a novel application of motion capture: Analysis of performance of sword fencing in the historical European martial arts (hema) domain. In: 2021 IEEE 21st international symposium on computational intelligence and informatics (CINTI), pp.000137–000142. IEEE.
88.
GuoW. Research on surface EMG measurement and characteristics of typical movements of traditional Taijiquan. Master’s Thesis, 2021, in Chinese. DOI: 10.27312/d.cnki.gshsu.2022.000531.
89.
MaLGuoWSunH, et al. Study on surface electromyography characteristics of traditional taijiquan typical movement. J Optoelectron2021; 32: 257–265.
90.
AmerineniRGuptaLSteadmanN, et al. Fusion models for generalized classification of multi-axial human movement: validation in sport performance. Sensors2021; 21(24): 8409.
91.
DharmmestaRJayaIRizalA, et al. Classification of foot kicks in taekwondo using svm (support vector machine) and knn (k-nearest neighbors) algorithms. In: 2022 IEEE international conference on industry 4.0, artificial intelligence, and communications technology (IAICT), pp.36–41. DOI: 10.1109/IAICT55358.2022.9887475.
92.
FaisalMAAChowdhuryMEHKhandakarA, et al. An investigation to study the effects of tai chi on human gait dynamics using classical machine learning. Comput Biol Med2022; 142 : 1–14.
93.
LiHKhooSYapHJ.Implementation of sequence-based classification methods for motion assessment and recognition in a traditional Chinese sport (baduanjin). Int J Environ Res Public Health2022; 19(3): 1744.
94.
YadavSDeshmukhAGonelaR, et al. Ms-kard: a benchmark for multimodal karate action recognition. In: 2022 international joint conference on neural networks (IJCNN), pp.1–8. DOI: 10.1109/IJCNN55064.2022.9892646.
95.
RhodinHConstantinVKatirciogluI, et al. Neural scene decomposition for multi-person motion capture. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp.7695–7705. DOI: 10.1109/CVPR.2019.00789.
96.
KaewpleeKKhamsemananNNatteeC. A rule-based approach for improving kinect skeletal tracking system with an application on standard muay thai maneuvers. In: 2014 Joint 7th international conference on soft computing and intelligent systems (SCIS) and 15th international symposium on advanced intelligent systems (ISIS), pp.281–285. DOI: 10.1109/SCIS-ISIS.2014.7044763.
97.
OokeNIkegamiYYamamotoK, et al. Transfer learning of deep neural network human pose estimator by domain-specific data for video motion capturing. In: 2022 IEEE international conference on advanced robotics and its social impacts (ARSO), pp.1–6. DOI: 10.1109/ARSO54254.2022.9802965.
98.
DuvelekSHölblingDBaranyiR, et al. 2trax3: raising accessibility and everyday use of automatic motion analysis in (combat) sports via ml enhanced 2d to 3d estimation algorithms. In: 11th international conference on sport sciences research and technology support, pp.128–135. DOI: 10.5220/0012165200003587.
99.
YasinHGhaniSKrügerB.An effective and efficient approach for 3d recovery of human motion capture data. Sensors2023; 23(7): 3664.
100.
AlharbiNLiangYWuD. A data preprocessing technique for gesture recognition based on extended-kalman-filter. In: 2017 IEEE/ACM international conference on connected health: applications, systems and engineering technologies (CHASE), pp.77–83. IEEE.
101.
BaekSKimM. User pose estimation based on multiple depth sensors. In: SIGGRAPH Asia 2017 posters. 2017, pp.1–2.
102.
KamelALiuBLiP, et al. An investigation of 3d human pose estimation for learning tai chi: a human factor perspective. Int J Hum Comput Interact2019; 35(4-5): 427–439.
103.
PengXBKanazawaAMalikJ, et al. Sfv: reinforcement learning of physical skills from videos. ACM Trans Graph2018; 37(6): 1–14.
104.
PengXBMaZAbbeelP, et al. Amp: adversarial motion priors for stylized physics-based character control. ACM Trans Graph2021; 40(4) : 1–20.
105.
GirónVChauJalfaro alfaroA, et al. 3D human pose estimation for martial arts analysis through graph convolutional networks, p. 43. DOI: 10.1117/12.2623512.
106.
LeVNguyenTTranN, et al. Openpose’s evaluation in the video traditional martial arts presentation. In: 2019 19th international symposium on communications and information technologies (ISCIT), pp.76–81. DOI: 10.1109/ISCIT.2019.8905243.
107.
LeVHSchererR.Human segmentation and tracking survey on masks for mads dataset. Sensors2021; 21(24): 8397.
108.
MaJMaLRuanW, et al. A wushu posture recognition system based on mediapipe. In: 2022 2nd international conference on information technology and contemporary sports (TCS), pp.10–13. DOI: 10.1109/TCS56119.2022.9918744.
109.
YinKHuangHHoESL, et al. A sampling approach to generating closely interacting 3d pose-pairs from 2d annotations. IEEE Trans Vis Comput Graph2019; 25(6): 2217–2227.
110.
LiuYXuSSongS, et al. Recognition and comparison of traditional wushu movements based on openpose. Electron Compon Inf Technol2021; 5(3): 126–128.
111.
JayasekaraSWeerasingheSAbayawardanaD, et al. Kaizen: computer vision based interactive karate training platform. In: TENCON 2022 -2022 IEEE region 10 conference (TENCON), pp.1–6. DOI: 10.1109/TENCON55691.2022.9977691.
112.
ChenHMaLLinZ, et al. Application of artificial intelligence vision technology in Chinese fencing teaching. In: 2022 2nd international conference on information technology and contemporary sports (TCS), pp.43–47. DOI: 10.1109/TCS56119.2022.9918801.
113.
LiuJZhengYWangK, et al. A real-time interactive tai chi learning system based on vr and motion capture technology. Procedia Comput Sci2020; 174: 712–719.
114.
ZhouSZhangFZhengY.Research on wushu action recognition and matching based on kinect acquisition. Techniques of Automation and Applications2020, in Chinese; 39: 94–97.
115.
CaiXHuoYLiF, et al. Human pose estimation and similarity calculation for tai chi learning. J Graph2022; 43(04): 695–706.
116.
MorelMAchardCKulpaR, et al. Automatic evaluation of sports motion: a generic computation of spatial and temporal errors. Image Vis Comput2017; 64: 67–78.
117.
XuZ.Taiji boxing assist teaching and evaluation method based on whole body motion capture. Master’s Thesis, 2018, in Chinese.
118.
YangHLiY. Wushu movement evaluation method based on kinect. In: 2022 2nd international conference on information technology and contemporary sports (TCS), pp.29–33. DOI: 10.1109/TCS56119.2022.9918736.
119.
KhanAHarisMNadeemS, et al. Virtual self defense trainer -analyzing and scoring user pose. In: 2020 international congress on human-computer interaction, optimization and robotic applications (HORA), pp.1–5. DOI: 10.1109/HORA49412.2020.9152860.
120.
LiHKhooSYapHJ.Differences in motion accuracy of baduanjin between novice and senior students on inertial sensor measurement systems. Sensors2020; 20(21) : 1–23. DOI: 10.3390/s20216258
121.
TangCChenXGongJ, et al. Wmnn: wearables-based multi-column neural network for human activity recognition. IEEE J Biomed Health Inform2023; 27(1): 339–350.
122.
PangYWangQZhangC. Time-frequency domain pattern analysis of tai chi 12 gong fa based on skeleton key points detection. In: 2021 international conference on neural networks, information and communication engineering, vol. 11933, pp.431–436. SPIE.
123.
ZhongMHungJYangY, et al. Ga-svm classifying method applied to dynamic evaluation of taekwondo. In: 2016 international conference on advanced materials for science and engineering (ICAMSE), pp.534–537. DOI: 10.1109/ICAMSE.2016.7840191.
124.
WessaEAshrafAAtiaA. Can pose classification be used to teach kickboxing? In: 2021 international conference on electrical, computer and energy technologies (ICECET), pp.1–6. DOI: 10.1109/ICECET52533.2021.9698656.
125.
YamanakaSShimaKMutohA, et al. Evaluation of martial arts demonstration focusing on peak timing using acceleration data. In: 2021 IEEE 10th global conference on consumer electronics (GCCE), pp.337–341. DOI: 10.1109/GCCE53005.2021.9621988.
126.
YamanakaSShimaKMutohA, et al. Evaluation system for martial arts demonstration from smartphone sensor data using deep neural networks on noisy labels. In: 2023 IEEE international conference on consumer electronics (ICCE), pp.1–5. DOI: 10.1109/ICCE56470.2023.10043511.
127.
Quintero OvalleJStawarzKMarzo PérezA. Exploring the addition of audio input to wearable punch recognition. In: Interacción’19: proceedings of the 2019 international conference on human computer interaction, 2019, Donostia-San Sebasti’an, Spain. Association for Computing Machinery (ACM).
128.
ZhangFZhouS.Intelligent recognition of athletes’ wrong actions based on computer vision technology. Adhes2020; 44(12): 82–85.
129.
EmadBAtefOShamsY, et al. Ikarate: Karate kata guidance system. Procedia Comput Sci2020; 175: 149–156.
HülsmannFGöpfertJPHammerB, et al. Classification of motor errors to provide real-time feedback for sports coaching in virtual reality — a case study in squats and tai chi pushes. Comput Graph2018; 76: 47–59. DOI: 10.1016/j.cag.2018.08.003
132.
JangWJLeeKKLeeWJ, et al. Development of an inertial sensor module for categorizing anomalous kicks in taekwondo and monitoring the level of impact. Sensors20222022; 22(7): 2591.
133.
Tuong ThanhNDang TuyenNDungL, et al. Implementation of technical data analysis of skeleton extracted from camera kinect in grading movements of Vietnamese martial arts. In: 2017 international conference on advanced technologies for communications (ATC), pp.241–244. DOI: 10.1109/ATC.2017.8167625.
134.
LiZZhouLMengM. Research and development of an action evaluation intelligent system for eight-style taichi based on kinect 2.0. Journal of Hangzhou Normal University (Natural Sciences Edition)2021; 20(04): 381–386.
135.
DaiZ. Recognition and evaluation of Taichi based on graph convolutional neural network. Master’s Thesis, 2022, in Chinese. DOI: 10.27005/d.cnki.gdzku.2022.002396.
136.
FunkCNagendraSScottJ, et al. Learning dynamics from kinematics: estimating 2d foot pressure maps from video frames, 2018.
137.
WiacekMTomasiukRZubrzyckiIZ.Correlations between anthropometric measurements and sports discipline aptitude. Appl Sci2022; 12(12): 5932.
138.
LeVH.Deep learning-based for human segmentation and tracking, 3d human pose estimation and action recognition on monocular video of mads dataset. Multimed Tools Appl2023; 82(14): 20771–20818.
139.
SooJWoodsCTArjunanSP, et al. Identifying the performance characteristics explanatory of fight outcome in elite pencak silat matches. Int J Perform Anal Sport2018; 18(6): 973–985.
140.
HolmesBMcHaleIGŻychalukK.Detecting individual preferences and erroneous verdicts in mixed martial arts judging using Bayesian hierarchical models. Eur J Oper Res2024; 312(2): 733–745.
HachajTOgielaMKoptyraK. Learning from annotated video: an initial study based on oyama karate tournament recordings. In: 2015 10th international conference on P2P, parallel, grid, cloud and internet computing (3PGCIC), pp.358–362. IEEE.
143.
HolmesBMcHaleIGŻychalukK.A Markov chain model for forecasting results of mixed martial arts contests. Int J Forecast2023; 39(2): 623–640.
144.
GrzendaASpeierWSiddarthP, et al. Machine learning prediction of treatment outcome in late-life depression. Front Psychiatry2021; 12: 1783.
145.
MengDGuoHLiangS, et al. Effectiveness of a hybrid exercise program on the physical abilities of frail elderly and explainable artificial-intelligence-based clinical assistance. Int J Environ Res Public Health2022; 19(12): 6988.
146.
WuKLiYZouY, et al. Tai chi increases functional connectivity and decreases chronic fatigue syndrome: a pilot intervention study with machine learning and fmri analysis. PLoS One2022; 17(12): 1–20.
147.
GuoHQiuJYiL, et al. Validation of accelerometers combined with machine learning for estimating energy expenditure of health qigong baduanjin: 620. Med Sci Sports Exerc2021; 53(8S): 208–208.
148.
ZhanXLiuYRaymondS, et al. Rapid estimation of entire brain strain using deep learning models. IEEE Trans Biomed Eng2021; 68(11): 3424–3434.
149.
FalconeMYadavNPoellabauerC, et al. Using isolated vowel sounds for classification of mild traumatic brain injury. In: 2013 IEEE international conference on acoustics, speech and signal processing, pp.7577–7581. DOI: 10.1109/ICASSP.2013.6639136.
150.
ZhanXLiuYCecchiNJ, et al. Finding the spatial co-variation of brain deformation with principal component analysis. IEEE Trans Biomed Eng2022; 69(10): 3205–3215.
151.
ZhanXLiYLiuY, et al. Machine-learning-based head impact subtyping based on the spectral densities of the measurable head kinematics. J Sport Health Sci2023; 12(5): 619–629.
152.
ZhanXSunJLiuY, et al. Toward more accurate and generalizable brain deformation estimators for traumatic brain injury detection with unsupervised domain adaptation. arXiv2023; 2306(02): 05255.
153.
StarkeSZhaoYZinnoF, et al. Neural animation layering for synthesizing martial arts movements. ACM Trans Graph2021; 40(4): 1–16.
154.
WonJGopinathDHodginsJ.Control strategies for physically simulated characters performing two-player competitive sports. ACM Trans Graph2021; 40(4): 1–11.
155.
ZhouYLiZXiaoS, et al. Auto-conditioned recurrent networks for extended complex human motion synthesis. arXiv: Learning2017.
156.
LiHDaiJZengR, et al. Foot-constrained spatial-temporal transformer for keyframe-based complex motion synthesis. Comput Animat Virtual Worlds2024; 35(1): 1–13.
157.
SunRSunYDuanL, et al. Wushu competition field segmentation based on expectation-maximization algorithm. China New Telecommunications2021; 23(01): 95–97.
158.
TakataMNakamuraYTorigoeY, et al. Strikes-thrusts activity recognition using wrist sensor towards pervasive kendo support system. In: 2019 IEEE international conference on pervasive computing and communications workshops (PerCom Workshops), pp.243–248. DOI: 10.1109/PERCOMW.2019.8730861.
159.
PangY. Action recognition for plum blossom boxing (Meihua Quan) based on graph convolutional neural network. Master’s Thesis, 2023, in Chinese. DOI: 10.27340/d.cnki.gstxy.2023.000253.
160.
ScottJCollinsRFunkC, et al. 4D model-based spatiotemporal alignment of scripted taiji quan sequences. In: 2017 IEEE international conference on computer vision workshops (ICCVW), pp.795–804. DOI: 10.1109/ICCVW.2017.99.
161.
ZengYCaoMZhangH, et al. An automatic matching interactive and visualization system for virtual martial arts. In XiaoLXuD (eds.) Thirteenth international conference on graphics and image processing (ICGIP 2021), p. 120832A, vol. 12083. International Society for Optics and Photonics, SPIE. DOI: 10.1117/12.2623402.
162.
MalawskiFKwolekB. Real-time action detection and analysis in fencing footwork. In: 2017 40th international conference on telecommunications and signal processing (TSP), pp.520–523. DOI: 10.1109/TSP.2017.8076041.
163.
HaoZDuanYDangX, et al. Human complex motion recognition method based on channel state information. Comput Eng2020; 46: 286–293.
164.
HaoZDangJZhangD.A highly robust human motion recognition method based on channel state information. Journal of Lanzhou Jiaotong University2020; 39: 37–44.
165.
LiJHuHXingQ, et al. Tai chi action quality assessment and visual analysis with a consumer rgb-d camera. In: 2022 IEEE 24th international workshop on multimedia signal processing (MMSP), pp.1–6. DOI: 10.1109/MMSP55362.2022.9949464.
166.
MottaghiASoryaniMSeifiH.Action recognition in freestyle wrestling using silhouette-skeleton features. Eng Sci Technol Int J2020; 23(4): 921–930.
167.
BaumannJWesselRKrügerB, et al. Action graph a versatile data structure for action recognition. In: 2014 international conference on computer graphics theory and applications (GRAPP), pp. 1–10.
168.
ChoiWLiLSekiguchiH, et al. Recognition of gait motion by using data mining. In: 2013 13th international conference on control, automation and systems (ICCAS 2013), pp.1213–1216. DOI: 10.1109/ICCAS.2013.6704173.
169.
KasiriSFookesCSridharanS, et al. Fine-grained action recognition of boxing punches from depth imagery. Comput Vis Image Underst2017; 159: 143–153.
170.
de GomaJBustosMSebastianJ, et al. Detection of taekwondo kicks using rgb-d sensors. In: Proceedings of the 2019 3rd international conference on software and e-business. ICSEB ‘19, pp.129–133, New York, NY: Association for Computing Machinery. DOI: 10.1145/3374549.3374576.
171.
ZhuHPunC. Human action recognition with skeletal information from depth camera. In: 2013 IEEE international conference on information and automation (ICIA), pp.1082–1085. DOI: 10.1109/ICInfA.2013.6720456.
172.
TorigoeYNakamuraYFujimotoM, et al. Strike activity detection and recognition using inertial measurement unit towards kendo skill improvement support system. Sens Mater2020; 32(2): 651.
173.
HachajTPiekarczykMOgielaMR.Human actions analysis: templates generation, matching and visualization applied to motion capture of highly-skilled karate athletes. Sensors2017; 17(11): 2590.
174.
Vega-Mart’ınezGMirabent-AmorDFigueroa-CaveroF, et al. Experience of use of an artificial neural network as an auxiliary in the physical fitness classification of taekwondo athletes from Mexico city. In: 2022 global medical engineering physics exchanges/pan American health care exchanges (GMEPE/PAHCE), pp.1–6. DOI: 10.1109/GMEPE/PAHCE55115.2022.9757793.
175.
KhasanshinI.Application of an artificial neural network to automate the measurement of kinematic characteristics of punches in boxing. Appl Sci2021; 11(3): 1223.
176.
EcheverriaJSantosOC.Toward modeling psychomotor performance in karate combats using computer vision pose estimation. Sensors2021; 21(24): 8378.
177.
NurahmadanIJayantaPradnyanaI. Utilization of pose estimation and multilayer perceptron methods in the development of taekwondo martial arts independent learning. In: 2021 international conference on informatics, multimedia, cyber and information system (ICIMCIS), pp.267–272. DOI: 10.1109/ICIMCIS53775.2021.9699268.
178.
SharmaGUttamA. Multilayer neural network model for mixed martial arts winner prediction. In: 2021 5th international conference on information systems and computer networks (ISCON), pp.1–5. DOI: 10.1109/ISCON52037.2021.9702452.
179.
GrinsztajnLOyallonEVaroquauxG. Why do tree-based models still outperform deep learning on typical tabular data? In: 36th conference on neural information processing systems (NeurIPS 2022) track on datasets and benchmarks. Advances in neural information processing, New Orleans, United States.
180.
MahdiFSandya PrasvitaDTheresiawati. Implementation of convolutional neural network algorithm for android-based classification of taekwondo martial arts. In: 2022 international conference on informatics, multimedia, cyber and information system (ICIMCIS), pp.407–412. DOI: 10.1109/ICIMCIS56303.2022.10017502.
181.
HoangHHaCNguyenD, et al. Poses classification in a taekwondo lesson using skeleton data extracted from videos with shallow and deep learning architectures. In: FDSE 2022: future data and security engineering. big data, security and privacy, smart city and industry 4.0 applications, pp.447–461. Springer. DOI: 10.1007/978-981-19-8069-530.
182.
YuanLHeZWangQ, et al. Spatial transformer network with transfer learning for small-scale fine-grained skeleton-based tai chi action recognition, pp.1–6. DOI: 10.1109/IECON49645.2022.9968668.
183.
SatoKMatsubaraHSuzukiK. Commonality of motions having effective features with respect to methods for identifying the moves made during kumite sparring in karate. In: 8th international conference on sport sciences research and technology support (icSPORTS 2020), pp.75–82. DOI: 10.5220/0010132400750082.
184.
JiangK. Research on wushu action recognition based on deep learning. Master’s Thesis, 2019, in Chinese. DOI: 10.27312/d.cnki.gshsu.2022.000531.
185.
OhishiYTanakaYKashinoK. Unsupervised co-segmentation for athlete movements and live commentaries using crossmodal temporal proximity. In: 2020 25th international conference on pattern recognition (ICPR), pp.9137–9142. DOI: 10.1109/ICPR48806.2021.9412233.
186.
LabintsevAKhasanshinIBalashovD, et al. Recognition punches in karate using acceleration sensors and convolution neural networks. IEEE Access2021; 9: 138106–138119.
187.
ChenY. Research on action analysis based on human skeleton information. Master’s Thesis, 2021, in Chinese. DOI: 10.27075/d.cnki.ghzdc.2021.000196.
188.
RuanWZhangBLuS, et al. Stance recognition applied to Chinese martial arts long stick combat sports. In: 2023 IEEE 3rd international conference on electronic technology, communication and information (ICETCI), pp.1780–1783. DOI: 10.1109/ICETCI57876.2023.10176867.
189.
LiangJZuoG.Taekwondo action recognition method based on partial perception structure graph convolution framework. Sci Program2022; 2022: 1–10.
190.
TungPSGiangPH, et al.; Do TT. Support learning vovinam exercises based on computer vision. In: RutkowskiLSchererRKorytkowskiM (eds) Artificial intelligence and soft computing. Cham: Springer Nature Switzerland, 2023, pp.102–111.
191.
Tejero-de PablosANakashimaYSatoT, et al. Summarization of user-generated sports video by using deep action recognition features. IEEE Trans Multimedia2018; 20(8): 2000–2011.
192.
Tejero-de PablosANakashimaYSatoT, et al. Human action recognition-based video summarization for rgb-d personal sports video. In: 2016 IEEE international conference on multimedia and expo (ICME), pp.1–6. DOI: 10.1109/ICME.2016.7552938.
193.
HouYSeydouFMKenderdineS.Unlocking a multimodal archive of southern Chinese martial arts through embodied cues. J Doc2023; 80: 1148–1166. DOI: 10.1108/JD-01-2022-0027
194.
MinY. Research on sports auxiliary training system based on multi-kinect. Master’s Thesis, 2021, in Chinese. DOI: 10.27390/d.cnki.gxbfc.2021.000064.
195.
MinYMouL.Research on sports auxiliary training system based on multiple kinect. Electron Des Eng2021; 29(18): 115–120.
196.
BehendiSMorganSFookesC. Non-invasive performance measurement in combat sports. In ChungPSoltoggioADawsonCW, et al. (eds.) Proceedings of the 10th international symposium on computer science in sports (ISCSS), pp.3–10. Cham: Springer International Publishing. ISBN 978-3-319-24560-7.
197.
Kasiri-BidhendiSFookesCMorganS, et al. Combat sports analytics: Boxing punch classification using overhead depthimagery. In: 2015 IEEE international conference on image processing (ICIP), pp.4545–4549. DOI: 10.1109/ICIP.2015.7351667.
198.
ZhuKWongAMcPheeJ. Fencenet: fine-grained footwork recognition in fencing. In: 2022 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW), pp.3588–3597. DOI: 10.1109/CVPRW56347.2022.00403.
199.
BarbosaPCunhaPCarvalhoV, et al. Deep learning in taekwondo techniques recognition system: a preliminary approach. In: MachadoJSoaresFTrojanowskaJ (eds) Innovations in mechatronics engineering II. Cham: Springer International Publishing, 2022, pp. 280–291.
200.
CunhaPBarbosaPFerreiraF, et al. Real-time evaluation system for top taekwondo athletes: project overview. In: International conference on biomedical electronics and devices. DOI: 10.5220/0010414200002865.
201.
BarbosaPCunhaPCarvalhoV, et al. Classification of taekwondo techniques using deep learning methods: first insights. In: Proceedings of the 14th international joint conference on biomedical engineering systems and technologies (BIOSTEC 2021) -BIODEVICES. INSTICC, pp.201–208. SciTePress. DOI: 10.5220/0010412400002865.
202.
NakamuraTNagaiTMochihashiD, et al. Segmenting continuous motions with hidden semi-Markov models and gaussian processes. Front Neurorobot2017; 11: 67.
203.
DakerMElsayaadFAtiaA.Karate kata style classification using pose landmarks and deep learning. In: 2023 5th novel intelligent and leading emerging sciences conference (NILES), pp.228–231. DOI: 10.1109/NILES59815.2023.10296806.
204.
DongJFangQJiangW, et al. Fast and robust multi-person 3d pose estimation and tracking from multiple views. IEEE Trans Pattern Anal Mach Intell2022; 44(10): 6981–6992.
205.
PengSZhangYXuY, et al. Neural body: implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp.9050–9059. DOI: 10.1109/CVPR46437.2021.00894.
206.
LiZLiuJZhangZ, et al. Cliff: carrying location information in full frames into human pose and shape estimation. In: AvidanSBrostowGCisseM (eds) Computer Vision – ECCV 2022. Cham: Springer Nature Switzerland, 2022, pp. 590–606.
207.
HongJFisherMGharbiM, et al. Video pose distillation for few-shot, fine-grained sports action recognition. In: 2021 IEEE/CVF international conference on computer vision (ICCV), pp.9234–9243. DOI: 10.1109/ICCV48922.2021.00912.
208.
HirosawaSKatoTYamashitaT, et al. Action Quality Assessment Model using specialists’ gaze location and kinematics data—focusing on evaluating figure skating jumps. Sensors2023; 23(22): 9282.
209.
KimJKimHLeeJ, et al. A deep learning approach for fatigue prediction in sports using GPS data and rate of perceived exertion. IEEE Access2022; 10: 103056–103064.
210.
HalilajERajagopalAFiterauM, et al. Machine learning in human movement biomechanics: best practices, common pitfalls, and new opportunities. J Biomech2018; 81: 1–11.
211.
RommersNRösslerRVerhagenE, et al. A machine learning approach to assess injury risk in elite youth football players. Med Sci Sports Exerc2020; 52(8): 1745–1751.
212.
WangYLiuWLiuX.Explainable ai techniques with application to NBA gameplay prediction. Neurocomputing2022; 483: 59–71.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
