A Multimodal Dataset for the Analysis of Movement Qualities in Karate Martial Art

• Periodical List
• Sci Information
• five.viii; 2021
• PMC7813879

Data Descriptor

Optical movement capture dataset of selected techniques in beginner and avant-garde Kyokushin karate athletes

Agnieszka Szczęsna

^oneDepartment of Estimator Graphics, Vision and Digital Systems, Faculty of Automatic Control, Electronics and Computer science, Silesian University of Technology, 44-100 Gliwice, Akademicka 16 Poland

Monika Błaszczyszyn

^twoFaculty of Physical Educational activity and Physiotherapy, Opole Academy of Technology, 45-758 Opole, Prószkowska 76 Poland

Magdalena Pawlyta

³Smooth-Japanese University of Data Technology, 02-008 Warsaw, Koszykowa 86 Poland

Received 2020 May 22; Accustomed 2020 Dec 14.

Abstract

Man motion capture is usually used in various fields, including sport, to analyze, understand, and synthesize kinematic and kinetic data. Specialized computer vision and mark-based optical motion capture techniques constitute the gold-standard for accurate and robust human motility 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 ninth kyu) executing the post-obit techniques: reverse lunge punch (Gyaku-Zuki), front kick (Mae-Geri), roundhouse boot (Mawashi-Geri), and spinning back kick (Ushiro-Mawashi-Geri). Each technique was performed approximately three times per recording (i.eastward., 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 2 trials per condition. The information presented was captured using a Vicon optical motion capture organization with Plug-In Gait software. 3 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 unlike combat sport techniques in attacking and defensive situations.

Subject terms: Biomedical engineering, Public health

Abstract

Measurement(s)	3D trajectory • joints angle • joints strength • joints power • joints moment • body movement coordination trait
Technology Blazon(s)	optical motion capture
Factor Type(s)	historic period • technique • skill level • condition
Sample Characteristic - Organism	Homo sapiens
Sample Characteristic - Surround	laboratory environment

Car-accessible metadata file describing the reported data: 10.6084/m9.figshare.13164848

Background & Summary

Human motion capture is ordinarily used in diverse fields, including sport, to analyze, understand, and synthesize kinematic and kinetic information.

The ability to execute the right technique in gainsay sports plays an important role in scoring points. Yet, in that location is no mutual optimal movement pattern for the performance of individual techniques. The martial art of karate is a method of fighting and defending with an "empty hand" (i.eastward., without a weapon)¹. Karate requires concrete, technical, and tactical skills, and is based on techniques involving hit the opponent with the mitt, foot, knee, or elbow. The motility patterns for these hit techniques typically involve flexion, extension, abduction, adduction, and rotation of diverse joints. Sufficient force must be transferred through the kinetic chain for striking techniques to score points^ii,3.

In contempo years, martial arts has increased in popularity, and this has resulted in rule changes. The basic features of sport karate that go far recognizable are point-scoring techniques such as kicks and punches. These techniques tin be used in three basic scenarios: (i) to attack, (2) to intercept an opponent's strike, and (three) to counterattack⁴. In karate, it is extremely important to be able to execute techniques and changes of direction at speed, and this requires high levels of coordination and residual. Research in martial arts focuses primarily on injuries^5,6, psychology^7–9, biomechanics^10,11, and perception of health¹².

Findings from investigations that have analyzed competitive karate are of import for planning the grooming process, and helping to ensure that training adapts to changes in competition rules. In competition, it has been institute that punches and kicks account for 89.09% and 8.36% respectively of all techniques used¹³. An analysis using kinematic methods during karate contests revealed that upper limb techniques accomplished a higher score compared to lower limb techniques^{fourteen,fifteen}. Furthermore, it has been shown that punches are a more dominant technique compared to kicks, which are used less oftentimes; this is despite rule changes that favor the utilise of kicks. Punches are less circuitous, allow greater precision and control, and require less energy expenditure^13,xvi,17. Moreover, punches tin can be executed speedily, and thus take a greater risk of scoring points^14,15. However, taking into account spectators' perceptions, punches are not as spectacular as kicks.

Karate kicking techniques include the front kicking (Mae-Geri), roundhouse kick (Mawashi-Geri), hook kick (Ura-Mawashi-Geri), and sidekick (Yoko-Geri). The roundhouse kick to the opponent's head (Mawashi-Geri jodan) is the nigh commonly used kick technique in karate¹⁸. However, a roundhouse kick to the opponent'southward torso (Mawashi-Geri chudan) allows more than control, and greater protection from the opponent's strikes, compared to other kicks; therefore, an athlete may opt to utilize a roundhouse boot to the torso instead of other kicks¹³.

Based on the research cited above, the importance of human motion analysis in combat sports is evident, with both kinematic and kinetic assay required¹⁹. Kinematic analysis is necessary to identify the ranges of motility and speeds required when executing different phases of the movement patterns. Anatomical angles are more important, and facilitate comparison of values from different investigations, regardless of the motion capture arrangement used.

For case, motion assay studies of karate accept investigated reaction time and anticipation^20,21, kicking limb movement patterns¹⁰, and the evolution of segmentation techniques¹⁸. Based on the positions of the cogitating markers in previous studies, the virtually frequently analyzed variables are angular displacement of the hip, human knee, talocrural joint, shoulder, elbow, torso, and head. These variables are most oft analyzed in the sagittal aeroplane. Other approaches to assay include the inter-joint coordination index, coefficients of variation, and the symmetry index. These approaches accept been used to investigate movement coordination, movement velocity, and the human relationship between them^22,23. Several studies accept shown that velocity is the main factor determining operation in karate athletes¹⁵. A novel method to measure interpersonal synchronization of movement using motion capture data is to find relevant dispatch peaks for upper and lower limbs, and and then establish if they are synchronized. Such a method has been constructive in classifying the skill level of karate athletes performing kata²⁴. In²⁵ the basic multi-articulation movement patterns used by karate athletes of different levels (based on experience and skill level) were identified.

Based on the above considerations, we present a comprehensive set of kinematic and kinetic data obtained from recordings of 37 Kyokushin karate athletes. The athletes were of different ages (children, young people, and adults), and of different skill levels equally based upon the karate grading system (from quaternary dan to 9th kyu). Information²⁶ was obtained for the opposite lunge dial (Gyaku-Zuki), forepart boot (Mae-Geri), roundhouse kick (Mawashi-Geri), and spinning back kick (Ushiro-Mawashi-Geri). Every technique was performed three times per recording (resulting in i data file), and nether three weather condition: (i) kicking or punching the air, (ii) kicking or punching a training shield, and (iii) kicking or punching an opponent. Possible applications of the information obtained are:

• comparison of movement patterns between individual athletes, or groups of athletes¹¹, based upon factors such as historic period, gender, training experience, and karate grade,

• kinematic description and analysis of movement patterns used when executing karate techniques²⁴,

• measure personal and interpersonal repetition of motility^24,27,

• evolution of virtual reality environments for virtual training^28,29,

• training and validation of machine learning techniques for the nomenclature, prediction and synthesis of human movement^30,31,

• development and optimization of methods for didactics karate techniques.

Human motility data regarding gait^32–34, activities of daily living (ADL)^35,36, and general sport activities³⁷ is publicly available. However, publicly available human move information regarding the martial arts is limited. In the Physical Activities and Sports category of the Carnegie Mellon University Movement Capture Database (http://mocap.cs.cmu.edu/) the martial arts subcategory contains recordings of only two subjects (motility described as "punch/strike", "swordplay" and "tai chi"). In the HDM05 repository³⁸ the just martial arts related category ("kicking and punching") contains 17 recordings, but without technical descriptions of the techniques depicted, or information about martial arts where the techniques are used, whilst the KIT Whole-Torso Human Move Database^39,40 contains only general recordings described as "kick" and "punch".

Consequently, there is little publicly available human movement data concerning specific martial arts, including karate. There has been an attempt to create an open up karate motion capture data repository with seven participants, and recordings of Shorin-ryu, Shotokan, and Oyama styles past inertial sensor based motility capture system⁴¹.

Additionally, a further dataset described^42,43 contains motion capture data (synchronized with video and sound recordings) of ii katas performed by seven participants with different levels of experience.

The goal of collecting the Martial Arts, Dancing and Sports dataset (MADS) was to provide challenging action sequences for human pose estimation from multi-view or depth information. The footing-truth pose data was captured past optical motion capture organization with only 60 Hz. Equally part of the database, the recordings of 2 martial arts masters in half-dozen forms in tai-chi and 6 katas in karate are bachelor⁴⁴.

Next available motion capture dataset UMONS-TAICHI contains Taijiquan martial art gestures that includes 13 classes (relative to Taijiquan techniques) executed by 12 participants of various skill levels. The dataset was captured using two motion capture systems simultaneously: optical motion capture organisation with frequency 179 Hz, and markerless motion capture system based on depth sensor⁴⁵.

It is of import to accost the absenteeism of high quality, well described, and publicly bachelor martial arts motion capture data. Any hereafter repository should incorporate recordings that depict karate athletes of different levels (due east.1000., grade, feel) executing techniques under various conditions (eastward.chiliad., defending and attacking against an opponent).

Methods

The office of presented dataset was used to investigate the three-dimensional kinematics of the front kick (Mae-Geri) when executed by Kyokushin karate athletes of different levels under 3 conditions¹¹: (i) a boot in the air, (ii) a kicking against a grooming shield, and (iii) a kick against an opponent.

Participants

Thirty-seven healthy participants (13 women, 24 men), aged betwixt x to l years (mean 18 with std ten), took part in the study. Participants trained at the Kyokushin Karate Club (Gliwice or Nysa, Poland). Participant characteristics were: mass 30–118 kg (hateful 54.5 with std 19.9), height 142–192 cm (hateful 160 with std 12.viii), training feel 2–35 years (mean 9.3 with std eight.4), and karate class (9th kyu - 4th dan) (Table1). All participants reported no known motion disorders or other health problems that could touch on their mobility. Before starting the recordings, each subject was comprehensively informed about the process, introduced to the experiment, and informed of whatsoever potential risks. Nosotros required the participants to sign an informed consent form. Written consent from parents/legal guardians was obtained for any participants who were minors. The study was carried out co-ordinate to the Helsinki Proclamation, and each of the participants gave their written consent to participate in the research. The written report was approved by a local bioethics committee, and carried out betwixt March 2017 and April 2017.

Tabular array one

Participant characteristics.

Code	Historic period [years]	Gender [F|M]	Weight [kg]	Meridian [cm]	Training time [years]	Karate grade [Kyu|Dan]
B0367	48	M	80	173	34	4 dan
B0368	24	M	68	170	ix	1 dan
B0369	l	Yard	88	182	30	3 dan
B0370	twenty	1000	71	178	x	2 kyu
B0371	22	M	78	172	vii	1 kyu
B0372	25	Thou	74	172	19	ane dan
B0373	13	F	62	168	7	four kyu
B0374	11	Thousand	42	150	5	7 kyu
B0375	12	F	45	152	8	8 kyu
B0376	10	F	35	143	six	6 kyu
B0377	xi	M	44	154	7	nine kyu
B0378	11	G	49	156	seven	8 kyu
B0379	12	M	35	145	3	7 kyu
B0380	13	Thou	30	144	v	5 kyu
B0381	13	M	50	161	6	5 kyu
B0382	24	Chiliad	86	182	12	5 kyu
B0383	10	Chiliad	36	142	5	8 kyu
B0384	eleven	Chiliad	44	151	5	6 kyu
B0385	11	F	42	150	3	8 kyu
B0386	11	F	45	152	2	9 kyu
B0387	11	F	52	158	five	7 kyu
B0388	14	F	54	157	4	vi kyu
B0389	14	F	52	153	viii	4 kyu
B0391	43	M	80	180	iv	3 kyu
B0392	26	M	118	192	10	two kyu
B0393	13	Thou	40	160	5	6 kyu
B0394	12	One thousand	thirty	142	5	seven kyu
B0395	fourteen	One thousand	45	158	4	7 kyu
B0396	17	F	47	164	eight	iv kyu
B0398	31	F	62	176	xviii	1 dan
B0399	20	F	70	166	thirteen	ii kyu
B0400	12	M	35	150	three	8 kyu
B0401	12	M	39	152	3	8 kyu
B0402	12	One thousand	34	150	iii	7 kyu
B0403	12	Thousand	32	143	iv	8 kyu
B0404	29	F	67	163	29	two dan
B0405	28	F	62	162	28	ii kyu

Instrumentation

Data was recorded using a motion tracking system (Vicon Motion Systems Limited, Oxford, UK) sampling at 250 Hz. 30-ix reflective markers from the Plug-In Gait software total-body mark set were attached to specific anatomical landmarks (according to the Vicon system documentation). In this arroyo, one marker is placed on each joint (e.thou., elbow, talocrural joint, knee). Between adjacent joints there is a further marker placed at dissimilar heights on the correct and left limbs to distinguish them from each other. Additionally, iv markers are used for the pelvis (for the front and dorsum spines), 5 for the torso (2 for the spine at C7 and TH12, ane for the shoulder blade, and two for the breastbone), and four for the head. An additional iv markers were placed on the training shield. For recordings with an opponent, both the attacker and defender had markers placed on them, resulting in ii sets of data (i.e., a set from the aggressor, and a set from the defender). Information conquering was carried out in the Human being Move Lab (HML) at the Enquiry and Development Center of the Polish-Japanese Academy of Information Applied science in Bytom, Poland. The system for data acquisition consisted of ten almost-infrared (NIR) Vicon MX-T40 cameras with 4 megapixel resolution and 10-bit grayscale, and 10 Vantage V5 cameras with five megapixel resolution. The area used for measurement had the shape of an ellipsoidal cylinder, with a top of 3 m, and a base with axes of 6.47 thou and iv.2 one thousand.

Conquering protocol

Before the execution of the technique was recorded, participants performed a standardized individual warm-up. The warm-up was approximately ii minutes duration, and predominately consisted of stretching exercises. The athletes had to execute the designated technique in the measurement area. After the markers were placed on the participant, and before they executed the technique, calibration of the motion capture organization was carried out according to the standard Vicon protocol. For the scale, the athlete had to stand in a "T" position by joining their legs and raising their artillery to the side.

The reference position (starting stance) for the participants was kumite no kamae. This position involved standing with ane foot in front of the other, and both heels touching the ground. The lateral altitude between the two anxiety corresponded to the width of the participant'southward pelvis. The designated technique was executed with the rear leg, and post-obit execution of the technique participants returned to the reference position. Participants were instructed to utilize their ascendant leg to execute the technique, with the exception of the opponent condition (i.due east., when kicking an opponent), where participants could employ either leg to execute the technique in a manner best suited to the combat state of affairs, and their preferred attacking strategy. Participants were instructed to execute the technique with maximum speed, and the intent to reach maximum forcefulness upon bear on. No prompt was given to the athletes to showtime the boot. Participants performed three repetitions of the designated technique, and two trials of each status were conducted.

Description of recorded techniques:

• Front end kick (Mae-Geri) is a bones kick. It is useful for self-defense situations such as boot the opponent (Fig.i, starting time row). This kick is normally performed by the rear leg in the fighting stance. The forepart kick is the most ofttimes used kick, every bit information technology can be performed at speed, requires little preparatory movement, and is hard to block. There are slight variations in how to perform a front end kick, from a quick snap kick (i.e., short contact time) to a powerful thrusting front kicking (i.e., longer contact fourth dimension that "pushes" the opponent away).

  

  Skeletons (the attacker is represented as a cerise skeleton) during the following techniques (in rows from the superlative): Mae-Geri, Mawashi-Geri gedan, Mawashi-Geri jodan, Ushiro-Mawashi-Geri and Gyaku-Zuki. Iii different conditions (in columns from left): air, shield, opponent.

• The roundhouse kicking (Mawashi-Geri) is likewise referred to every bit a circular kick. The roundhouse kick is similar to the front kick, the only difference existence that the motion pattern for the roundhouse kick is circular, and attacks the opponent from the side. From the fighting stance the boot is executed with the rear leg. The roundhouse kick was recorded at 2 heights: (i) from knee to hip (gedan, Fig.1, second row), and (two) from shoulder to the top of the head (jodan, Fig.i, 3rd row). Initially, the joint movements involved in the execution of this technique are flexion, abduction, and external rotation of the hip, and knee flexion, followed past hip internal rotation and extension, and knee extension in the direction of the target.

• The spinning back boot (Ushiro-Mawashi-Geri) begins with the fighting stance, and is generally executed with the rear leg (Fig.1, 4th row). The attacker firstly spins 180 degrees, resulting in their back facing the target. Whilst turning, the knee is brought up such that the angle between the thigh and the calf is 90 degrees. In one case in this position, the kicking is ready to exist executed by extending the leg to strike the target.

• The contrary dial (Gyaku-Zuki) is executed with the hand contralateral to the front leg (Fig.1, fifth row). The objective is to execute the punch quickly, and from a controlled distance. This punch is the first to exist learnt due to its simplicity. By executing Gyaku-Zuki at speed, the ability of the opponent to anticipate and react is limited. Execution of the punch requires a proximal-to-distal generation of force, showtime at the pelvis, and progressing through the trunk and upper arm, before culminating at the fist. The movement begins with rotation of the pelvis, and continues with arm flexion, immediately followed by forearm extension.

The following iii conditions were specified:

• a preparation kicking or punch in the air,

• a kick or punch at a target (i.e., a training shield held by the passenger vehicle),

• a kick or dial against an opponent in a gainsay situation, with both assaulter and defender recorded.

Not all techniques were performed past all participants. For example, the roundhouse kick (Mawashi-Geri) and spinning back kick (Ushiro-Mawashi-Geri) are technically hard, and some of the less experienced participants were not able to execute these techniques successfully. If a less experienced participant was unable to execute a technique successfully, there is no recording of the technique in the participant'south catalogue. The overall statistics are listed in Tableii.

Tabular array 2

Recording statistics for private techniques in conditions: air (A), shield (S), opponent (O).

Code	Mae-Geri	Mawashi-Geri Gedan	Mawashi-Geri Jodan	Ushiro-Mawashi-Geri	Gyaku-Zuki
B0367	half-dozen(A),5(S),0(O)	half dozen(A),half-dozen(S),0(O)	six(A),half-dozen(S),0(O)	six(A),3(South),0(O)	3(A),6(S),0(O)
B0368	vi(A),6(S),0(O)	6(A),six(S),0(O)	vi(A),6(S),0(O)	6(A),6(S),0(O)	9(A),6(S),0(O)
B0369	6(A),half dozen(South),0(O)	6(A),6(S),0(O)	6(A),6(S),0(O)	half-dozen(A),6(S),0(O)	6(A),6(S),0(O)
B0370	six(A),half dozen(S),0(O)	6(A),six(S),0(O)	6(A),6(Due south),0(O)	0(A),0(South),0(O)	6(A),6(S),0(O)
B0371	6(A),6(S),6(O)	six(A),half dozen(S),6(O)	6(A),6(S),6(O)	6(A),6(S),half dozen(O)	6(A),6(S),6(O)
B0372	6(A),six(S),half dozen(O)	6(A),6(S),vi(O)	6(A),6(S),6(O)	half dozen(A),half dozen(S),half-dozen(O)	6(A),6(S),6(O)
B0373	6(A),half-dozen(S),six(O)	half dozen(A),half-dozen(S),6(O)	half-dozen(A),6(Southward),6(O)	6(A),vi(S),6(O)	six(A),half dozen(S),6(O)
B0374	6(A),6(South),vi(O)	six(A),half-dozen(South),half dozen(O)	6(A),six(S),6(O)	vi(A),vi(S),6(O)	vi(A),6(Southward),eight(O)
B0375	6(A),vi(Due south),vi(O)	half dozen(A),six(Due south),6(O)	6(A),6(S),vi(O)	6(A),6(S),6(O)	vi(A),6(S),vii(O)
B0376	vi(A),half-dozen(S),iii(O)	half dozen(A),6(S),8(O)	6(A),half-dozen(S),6(O)	9(A),half-dozen(S),6(O)	6(A),6(S),7(O)
B0377	6(A),6(S),6(O)	6(A),vi(S),half dozen(O)	half dozen(A),six(S),half-dozen(O)	6(A),half dozen(S),6(O)	6(A),half-dozen(S),6(O)
B0378	6(A),6(S),six(O)	half-dozen(A),half-dozen(Due south),6(O)	six(A),nine(S),6(O)	6(A),3(S),6(O)	half-dozen(A),6(S),6(O)
B0379	7(A),6(S),six(O)	half dozen(A),6(S),6(O)	half dozen(A),half-dozen(S),6(O)	6(A),vii(South),6(O)	6(A),7(South),xi(O)
B0380	6(A),half-dozen(S),6(O)	6(A),6(S),6(O)	6(A),six(S),6(O)	6(A),8(S),six(O)	6(A),7(S),6(O)
B0381	6(A),half dozen(S),ix(O)	6(A),6(S),6(O)	6(A),6(S),5(O)	6(A),6(South),half-dozen(O)	6(A),6(S),vii(O)
B0382	vi(A),6(Due south),0(O)	half-dozen(A),6(Due south),0(O)	6(A),6(South),0(O)	six(A),6(Due south),0(O)	7(A),half-dozen(Southward),0(O)
B0383	half-dozen(A),6(Due south),0(O)	three(A),vi(Southward),0(O)	6(A),6(S),0(O)	half dozen(A),6(Southward),0(O)	half-dozen(A),six(Southward),0(O)
B0384	vi(A),6(S),ix(O)	vi(A),6(S),six(O)	6(A),half-dozen(S),half dozen(O)	half-dozen(A),half-dozen(S),6(O)	6(A),half-dozen(S),8(O)
B0385	6(A),half dozen(South),6(O)	half-dozen(A),6(S),six(O)	vi(A),6(S),6(O)	half dozen(A),half-dozen(S),viii(O)	6(A),six(S),ten(O)
B0386	six(A),6(S),7(O)	6(A),6(Southward),half dozen(O)	6(A),half-dozen(S),9(O)	6(A),half dozen(S),6(O)	half dozen(A),half-dozen(Due south),8(O)
B0387	6(A),6(Southward),6(O)	6(A),6(S),6(O)	6(A),six(S),half-dozen(O)	6(A),6(S),vi(O)	six(A),6(South),6(O)
B0388	half-dozen(A),6(S),12(O)	six(A),6(S),12(O)	six(A),6(S),11(O)	6(A),half dozen(S),12(O)	half-dozen(A),6(S),12(O)
B0389	6(A),6(S),half dozen(O)	half dozen(A),6(Due south),6(O)	5(A),6(S),half-dozen(O)	6(A),6(S),6(O)	half dozen(A),6(S),6(O)
B0391	half dozen(A),half-dozen(South),six(O)	6(A),vi(S),half-dozen(O)	6(A),6(South),6(O)	6(A),6(S),six(O)	6(A),8(S),half-dozen(O)
B0392	6(A),6(S),half dozen(O)	6(A),6(S),half dozen(O)	6(A),6(S),six(O)	6(A),6(S),6(O)	6(A),6(S),7(O)
B0393	7(A),half dozen(S),vi(O)	6(A),ix(Southward),7(O)	six(A),6(S),6(O)	6(A),6(South),vi(O)	half dozen(A),xviii(S),vii(O)
B0394	6(A),6(S),6(O)	6(A),6(S),viii(O)	half-dozen(A),six(South),half-dozen(O)	half-dozen(A),6(S),6(O)	6(A),half dozen(Southward),7(O)
B0395	6(A),half dozen(S),6(O)	6(A),six(S),6(O)	6(A),vi(Southward),6(O)	6(A),6(Southward),6(O)	half dozen(A),6(S),9(O)
B0396	half dozen(A),half-dozen(South),half dozen(O)	six(A),vi(S),vi(O)	vi(A),6(Southward),6(O)	half dozen(A),6(Due south),6(O)	6(A),vi(S),half-dozen(O)
B0398	half dozen(A),6(S),vi(O)	6(A),6(S),vi(O)	6(A),six(Southward),6(O)	half-dozen(A),6(S),half dozen(O)	9(A),6(S),half dozen(O)
B0399	six(A),6(S),6(O)	six(A),6(Southward),6(O)	half dozen(A),vi(S),half-dozen(O)	vi(A),half-dozen(S),three(O)	6(A),6(Due south),6(O)
B0400	6(A),6(Southward),7(O)	6(A),6(S),7(O)	half-dozen(A),6(S),vii(O)	6(A),half-dozen(S),7(O)	7(A),6(S),seven(O)
B0401	vi(A),6(S),6(O)	6(A),half dozen(S),6(O)	half-dozen(A),6(South),vi(O)	6(A),3(S),6(O)	six(A),6(Due south),6(O)
B0402	3(A),half-dozen(Due south),vi(O)	half dozen(A),6(S),half-dozen(O)	6(A),vi(S),6(O)	half dozen(A),6(South),6(O)	vi(A),half-dozen(S),half-dozen(O)
B0403	6(A),6(South),six(O)	half dozen(A),6(South),six(O)	six(A),vi(South),9(O)	6(A),6(S),half-dozen(O)	6(A),5(S),6(O)
B0404	half dozen(A),vi(S),6(O)	vi(A),6(S),6(O)	half dozen(A),6(Due south),half-dozen(O)	vi(A),six(S),six(O)	six(A),6(S),6(O)
B0405	half dozen(A),half-dozen(South),half-dozen(O)	six(A),6(S),6(O)	half dozen(A),vi(S),6(O)	6(A),half-dozen(Southward),6(O)	6(A),6(S),six(O)

Figurei shows unmarried frame images of skeletons (represented past stick figures with joint markers) performing each technique under each condition. The techniques were performed as described above.

Data preprocessing and available variables

Plug-In Gait software was used to make up one's mind angles, moments, force output, and power output at individual joints, and to estimate virtual markers, such every bit the center of mass (COM). A clarification of all variables is bachelor in the system documentation (https://docs.vicon.com). The data in the repository is non-normalized giving the broadest possibility of analysis. Available data contains 3D trajectories of all markers (set up of 39 markers) and angles of human joints without information virtually the skeleton. Additional moments, powers and forces in those joints. In that location are also trajectories of shield markers for determining the position of the target. The additional 4 trajectory markers used on the grooming shield are labeled as: Tarcza1, Tarcza2, Tarcza3 and Tarcza4.

Data Records

Dataset organization

In the dataset, there is one catalogue for each participant (37 catalogues in total). Catalogues are named as per the participant code number (run into Tableone). Each catalogue contains sub-folders corresponding to the techniques recorded. Sub-folders are labeled as follows:

YYYY-MM-DD-CODE-S0X

where

YYYY - year

MM - calendar month

DD - day

CODE - participant code;

S0X - karate technique, S01 - Gyaku-Zuki, S02 - Mae-Geri, S03 - Mawashi-Geri gedan, S04 - Mawashi-Geri jodan, S05 - Ushiro-Mawashi-Geri.

The following file labeling convention is used:

YYYY-MM-DD-Lawmaking-S0X-E0Z-T0J.c3d

where

E0Z - condition: E01 - air, E02 - shield, E03 - assailant, E04 - defender;

T0X - number for trial, T01 or T02.

The dataset comprises 1,411 files, with three,229 single kicks and punches. Data is stored in the C3D file format (https://www.c3d.org/). There are three–four repetitions of the same technique in a given trial (T01 and T02). It gives also the possibility of a time and a preparatory movement analysis for the technique. The C3D file format is widely used in the biomechanical field by companies and laboratories to store motion capture system data. The dataset is available at figshare (x.6084/m9.figshare.c.4981073)²⁶.

Technical Validation

Normalization was required for analysis of the data. Here a very bones normalization is proposed concerning merely the assay on the basis of one selected ankle maker for kicks and a finger for the punching. The data gives the possibility of a much broader and comprehensive analysis using a full-body gear up of information. The time taken to execute the aforementioned technique differed betwixt and within subjects. Therefore, the data was normalized for fourth dimension. Using an arroyo taken from gait analysis inquiry, the start and end points for a given technique were determined, and then scaled to ensure that execution of the technique always lasted a given number of frames. The algorithm used consisted of several steps. The kickoff step was to increase the sampling frequency by a given value by adding zeros to the signal. Then the finite impulse response (FIR) anti-aliasing filter was applied. The last footstep was to downsample the filtered signal to the desired value by discarding the samples. The trajectories obtained in this manner had the aforementioned length, whilst maintaining their shape. These steps were carried out using the resample role available in Matlab.

For joint angles, moments, force outputs, and power outputs, this normalization was sufficient. However, for the trajectory of joint markers spatial normalization was necessary. The participant'south position within the scene affected the marking position (east.thousand., the participant's summit afflicted their kick height). Therefore, all trajectories had be normalized in some manner. A bones method to standardize trajectories is to use the z-score of p (the fourth dimension serial of coordinates for 10, y, and z):

where μ is the hateful value and σ is the standard departure of p. This method has been used for motility feature normalization in classification tasks^46,47. Figures2 to ​ half dozen were normalized using this method.

Ankle mark trajectory and hip articulation angles of the boot leg in Mae-Geri technique for three weather: air (green), shield (red), opponent (blueish). (a) Normalized y coordinate of trajectory of the kicking leg ankle mark. (b) Normalized z coordinate of trajectory of the kicking leg ankle marker. (c) Adduction/abduction hip angle of the kick leg. (d) Flexion/extension hip angle of the kicking leg.

Finger marker trajectory and shoulder joint angles of the punching upper limb in Gyaku-Zuki technique for 3 weather condition: air (green), shield (red), opponent (blue). (a) Normalized 10 coordinate of trajectory of the punching upper limb finger marker. (b) Normalized y coordinate of trajectory of the punching upper limb finger marker. (c) Adduction/abduction shoulder bending of the punching upper limb. (d) Flexion/extension shoulder angle of the punching upper limb.

Whilst this method works well for simple visualization, information technology is as well simple to evaluate private trajectories. For example, this method of normalizing would not show the difference in kick acme. To obtain such information, other normalization methods that take into consideration factors such as participants' limb length and acme tin be used.

When analyzing movement anatomical axis and planes are used. The x-axis is the frontal axis (representing movement from the left to right side of the body), the y-axis is the sagittal axis (representing front and back movements), and the z-axis is the vertical axis (representing up and downwardly movements).

To automatically detect the kick, and the boot leg (right or left), the value of the z coordinate and basic peak assay can exist used. If the peak value exceeds a specified limit, it ways a boot has occurred. To standardize the boot leg data (e.g., the left leg), the value of the 10 coordinate should be changed to the opposite side (i.e., reflection transformation).

The trajectories of the ankle marker on the kicking leg are presented on the charts. Each status has been drawn using a different color: (i) a kick in the air (green), (ii) a kick at the training shield (red), and (iii) a kick at the opponent (bluish). Kicking leg hip joint angles, punching upper limb finger mark trajectories, and punching upper limb shoulder angles are presented in the same manner.

In Figs.ii–6, a similarity in the trajectories and angles observed in participants for a given technique tin be seen. The movement is presented from the preparatory stage to the final phase. Therefore, it is possible to separate the motility into its composite phases, and to select specific phases for comparative analysis.

For the Mae-Geri kick (Fig.2), the ankle marker trajectory is presented in the sagittal plane (Fig.2a), and every bit vertical axis coordinates (Fig.2b). The angle value ranges bear witness that the movement takes place mainly in the frontal and sagittal planes (Fig.2c,d), with the large ranges (-20 degrees to 120 degrees) in Fig.2d dependent on the stage of the movement. The Mawashi-Geri gedan (Fig.three) is a sidekick, with the largest range of motion seen in the sagittal (Fig.3d) and frontal (Fig.3c) planes. The talocrural joint marker trajectory shows the high repeatability of the technique for individual participants. Figure4 presents the same kick only at a much higher acme, as shown by the ankle marker ranges. Figure5 presents the talocrural joint marker trajectory and hip joint angles for the spinning back kick. The range of hip joint angles is large, but compared to other boot techniques, participants constitute it difficult to accomplish the required range of movement. Additionally, motion phases can be observed in the upper limb techniques (Fig.half-dozen) for the finger marker (Fig.6a,b) and shoulder joint angle (Fig.6c,d).

Ankle marker trajectory and hip joint angles of the kicking leg in Mawashi-Geri gedan technique for three conditions: air (green), shield (red), opponent (blue). (a) Normalized y coordinate of trajectory of the kick leg ankle marker. (b) Normalized z coordinate of trajectory of the boot leg ankle marker. (c) Adduction/abduction hip angle of the boot leg. (d) Flexion/extension hip bending of the kicking leg.

Talocrural joint marking trajectory and hip articulation angles of the kicking leg in Mawashi-Geri jodan technique for three conditions: air (green), shield (red), opponent (blueish). (a) Normalized y coordinate of trajectory of the kicking leg ankle marker. (b) Normalized z coordinate of trajectory of the kick leg ankle marking. (c) Adduction/abduction hip angle of the kicking leg. (d) Flexion/extension hip angle of the kicking leg.

Ankle marker trajectory and hip articulation angles of the kicking leg in Ushiro-Mawashi-Geri technique for iii atmospheric condition: air (greenish), shield (blood-red), opponent (blueish). (a) Normalized y coordinate of trajectory of the kicking leg ankle mark. (b) Normalized z coordinate of trajectory of the boot leg ankle marker. (c) Adduction/abduction hip angle of the kicking leg. (d) Flexion/extension hip bending of the kick leg.

Usage Notes

The dataset can be used for kinematic analyses. The Biomechanical ToolKit (BTK)⁴⁸, or standalone application Mokka, can be used to read and visualize the C3D files. BTK and Mokka also allow data to be exported from C3D to other file types (e.g., comma-separated values; CSV). For analyses in Matlab, the external MoCap Toolbox can be used to open C3D files. Data normalization and synchronization appropriate to the planned analysis are required^43,49.

Acknowledgements

The authors' special thank you go to Maciej Marszałek and the athletes from Kyokushin Karate Club (Gliwice, Poland), and Dariusz Karczmit and the athletes from Kyokushin Karate Social club (Nysa, Poland), for their participation and support in producing the recordings. The data was recorded in the Human Motion Laboratory (http://bytom.pja.edu.pl) of the Smooth–Japanese Academy of It in Bytom, Poland. This publication was partially supported by the Rector's grant in the field of scientific research and development works, Grant No. 02/090/RGJ20/0001, (2020–2021), and by the Section of Graphics, Computer Vision and Digital Systems, under statue inquiry project (Rau6, 2020), Silesian Academy of Applied science (Gliwice, Poland).

Author contributions

Conceptualization: A.Sz. and M.B. Methodology: A.Sz. and 1000.B. Software: M.P. and A.Sz. Formal analysis: Grand.B. and A.Sz. Investigation: A.Sz. and Thousand.B. Information curation: Chiliad.B and M.P. Writing – original typhoon: A.Sz. Writing – review and editing: Grand.B., A.Sz. and Thousand.P.

Competing interests

The authors declare no competing interests.

Footnotes

Publisher's notation Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

References

one. Pappas E. Boxing, wrestling, and martial arts related injuries treated in emergency departments in the the states, 2002-2005. J. sports scientific discipline & medicine. 2007;6:58. [PMC free article] [PubMed] [Google Scholar]

ii. Wasik J, Czarny W, Malolepszy Eastward, Drozdek-Malolepsza T. Kinematics of taekwon-practise front kick. Arch. Budo Sci. Martial Arts Extrem. Sports. 2015;eleven:23–28. [Google Scholar]

3. Worsey MT, Espinosa HG, Shepherd JB, Thiel DV. Inertial sensors for performance analysis in combat sports: A systematic review. Sports. 2019;seven:28. doi: ten.3390/sports7010028. [PMC complimentary article] [PubMed] [CrossRef] [Google Scholar]

four. Koropanovski North, Jovanovic S. Model characteristics of gainsay at elite male karate competitors. Serbian Serbian J. Sports Sci. 2007;ane:97–115. [Google Scholar]

5. McPherson M, Pickett Due west. Characteristics of martial art injuries in a defined canadian population: a descriptive epidemiological study. BMC public health. 2010;10:795. doi: 10.1186/1471-2458-10-795. [PMC costless article] [PubMed] [CrossRef] [Google Scholar]

6. Arriaza R, Inman D, Arriaza A, Saavedra MA. Depression run a risk of injuries in young adolescents participating in top-level karate contest. The Am. journal sports medicine. 2016;44:305–308. doi: 10.1177/0363546515615577. [PubMed] [CrossRef] [Google Scholar]

7. Kusnierz, C., Cynarski, W. J. & Litwiniuk, A. Comparison of aggressiveness levels in combat sports and martial arts male person athletes to not-practising peers. Arch. Budo. 10 (2014).

8. Chaabène H, et al. Time–move analysis and physiological responses to karate official combat sessions: is at that place a difference between winners and defeated karatekas? Int. J. Sports Physiol. Perform. 2014;9:302–308. doi: 10.1123/ijspp.2012-0353. [PubMed] [CrossRef] [Google Scholar]

9. Chaabene H, Hachana Y, Franchini E, Mkaouer B, Chamari K. Physical and physiological contour of elite karate athletes. Sports medicine. 2012;42:829–843. [PubMed] [Google Scholar]

10. VencesBrito AM, Ferreira MAR, Cortes N, Fernandes O, Pezarat-Correia P. Kinematic and electromyographic analyses of a karate punch. J. Electromyogr. Kinesiol. 2011;21:1023–1029. doi: 10.1016/j.jelekin.2011.09.007. [PubMed] [CrossRef] [Google Scholar]

11. Błaszczyszyn 1000, Szczęsna A, Pawlyta M, Marszałek M, Karczmit D. Kinematic analysis of mae-geri kicks in beginner and advanced kyokushin karate athletes. Int. journal environmental research public wellness. 2019;sixteen:3155. doi: 10.3390/ijerph16173155. [PMC gratuitous article] [PubMed] [CrossRef] [Google Scholar]

12. Gorner One thousand, Kusnierz C, Nowak PF. Perception of health by combat sports athletes. ARCHIVES OF BUDO. 2019;xv:213–219. [Google Scholar]

13. Koropanovski N, Dopsaj Chiliad, Jovanovic S. Characteristics of pointing deportment of pinnacle male competitors in karate at world and european level. Braz. J. Biomotricity. 2008;two:241–251. [Google Scholar]

14. Chaabène H, et al. Physiological responses and performance analysis difference between official and faux karate combat conditions. Asian periodical sports medicine. 2014;five:21. [PMC complimentary article] [PubMed] [Google Scholar]

fifteen. Chaabene H, Negra Y, Capranica L, Prieske O, Granacher U. A needs analysis of karate kumite with recommendations for performance testing and training. Strength & Cond. J. 2019;41:35–46. doi: ten.1519/SSC.0000000000000445. [CrossRef] [Google Scholar]

16. Iide K, et al. Physiological responses of simulated karate sparring matches in young men and boys. The J. Strength & Cond. Res. 2008;22:839–844. doi: 10.1519/JSC.0b013e31816a5af6. [PubMed] [CrossRef] [Google Scholar]

17. Doria C, et al. Energetics of karate (kata and kumite techniques) in superlative-level athletes. Eur. journal applied physiology. 2009;107:603. doi: 10.1007/s00421-009-1154-y. [PubMed] [CrossRef] [Google Scholar]

18. Gavagan CJ, Sayers MG. A biomechanical analysis of the roundhouse boot technique of expert practitioners: A comparison between the martial arts disciplines of muay thai, karate, and taekwondo. PLoS One. 2017;12:e0182645. doi: ten.1371/journal.pone.0182645. [PMC free commodity] [PubMed] [CrossRef] [Google Scholar]

19. Idris WMRW, Rafi A, Bidin A, Jamal AA, Fadzli SA. A systematic survey of martial art using movement capture technologies: the importance of extrinsic feedback. Multimed. Tools Appl. 2019;78:10113–10140. doi: 10.1007/s11042-018-6624-y. [CrossRef] [Google Scholar]

twenty. Mori S, Ohtani Y, Imanaka K. Reaction times and anticipatory skills of karate athletes. Hum. movement science. 2002;21:213–230. doi: x.1016/S0167-9457(02)00103-3. [PubMed] [CrossRef] [Google Scholar]

21. Borysiuk Z, Waskiewicz Z. Information processes, stimulation and perceptual training in fencing. J. Hum. Kinetics. 2008;19:63–82. doi: x.2478/v10078-008-0005-y. [CrossRef] [Google Scholar]

22. Witte 1000, Emmermacher P, Langenbeck N, Perl J. Visualized move patterns and their assay to classify similarities–demonstrated by the karate kick mae-geri. Kinesiol. Int. periodical fundamental applied kinesiology. 2012;44:155–165. [Google Scholar]

23. Kim YK, Kim YH, Im SJ. Inter-joint coordination in producing kicking velocity of taekwondo kicks. J. sports science & medicine. 2011;ten:31. [PMC gratis commodity] [PubMed] [Google Scholar]

24. De Giorgis N, Puppo E, Alborno P, Camurri A. Evaluating move quality through intrapersonal synchronization. IEEE Transactions on Human-Machine Syst. 2019;49:304–313. doi: 10.1109/THMS.2019.2912498. [CrossRef] [Google Scholar]

25. Zago 1000, Codari M, Iaia FM, Sforza C. Multi-segmental movements every bit a part of feel in karate. J. sports sciences. 2017;35:1515–1522. doi: 10.1080/02640414.2016.1223332. [PubMed] [CrossRef] [Google Scholar]

26. Szczęsna A, Błaszczyszyn One thousand, Pawlyta M, 2020. Optical motion capture dataset of selected techniques in beginner and advanced Kyokushin karate athletes. figshare. [CrossRef]

27. Morel 1000, Achard C, Kulpa R, Dubuisson S. Automatic evaluation of sports motion: A generic ciphering of spatial and temporal errors. Prototype Vis. Comput. 2017;64:67–78. doi: 10.1016/j.imavis.2017.05.008. [CrossRef] [Google Scholar]

28. Ma AW, et al. Adapted taekwondo training for prepubertal children with developmental coordination disorder: a randomized, controlled trial. Sci. reports. 2018;8:1–9. [PMC free commodity] [PubMed] [Google Scholar]

29. Petri K, Masik S, Danneberg M, Emmermacher P, Witte M. Possibilities to utilise a virtual opponent for enhancements of reactions and perception of young karate athletes. Int. J. Comput. Sci. Sport. 2019;18:20–33. doi: 10.2478/ijcss-2019-0011. [CrossRef] [Google Scholar]

thirty. Hachaj T, Piekarczyk Chiliad, Ogiela MR. Human actions analysis: templates generation, matching and visualization applied to motion capture of highly-skilled karate athletes. Sensors. 2017;17:2590. doi: 10.3390/s17112590. [PMC gratuitous article] [PubMed] [CrossRef] [Google Scholar]

31. Hachaj T, Ogiela MR, Koptyra 1000. Application of assistive estimator vision methods to oyama karate techniques recognition. Symmetry. 2015;7:1670–1698. doi: 10.3390/sym7041670. [CrossRef] [Google Scholar]

32. Schreiber C, Moissenet F. A multimodal dataset of homo gait at different walking speeds established on injury-complimentary adult participants. Sci. data. 2019;vi:ane–7. doi: ten.1038/s41597-019-0124-4. [PMC free article] [PubMed] [CrossRef] [Google Scholar]

33. Lencioni T, Carpinella I, Rabuffetti One thousand, Marzegan A, Ferrarin M. Human kinematic, kinetic and emg data during different walking and stair ascending and descending tasks. Sci. data. 2019;half-dozen:i–x. doi: 10.1038/s41597-019-0323-z. [PMC free article] [PubMed] [CrossRef] [Google Scholar]

34. Kwolek B, et al. Calibrated and synchronized multi-view video and motion capture dataset for evaluation of gait recognition. Multimed. Tools Appl. 2019;78:32437–32465. doi: 10.1007/s11042-019-07945-y. [CrossRef] [Google Scholar]

35. Roda-Sales A, Vergara M, Sancho-Bru JL, Gracia-Ibáñez V, Jarque-Bou NJ. Human being hand kinematic data during feeding and cooking tasks. Sci. information. 2019;6:1–10. doi: x.1038/s41597-019-0175-6. [PMC free article] [PubMed] [CrossRef] [Google Scholar]

36. Jarque-Bou NJ, Vergara M, Sancho-Bru JL, Gracia-Ibáñez V, Roda-Sales A. A calibrated database of kinematics and emg of the forearm and paw during activities of daily living. Sci. data. 2019;vi:1–xi. doi: 10.1038/s41597-019-0285-ane. [PMC free article] [PubMed] [CrossRef] [Google Scholar]

37. Finocchietti S, Gori M, Oliveira AS. Kinematic profile of visually impaired football players during specific sports actions. Sci. reports. 2019;9:1–8. [PMC free article] [PubMed] [Google Scholar]

38. Müller, Grand. et al. Documentation mocap database hdm05. Tech. Rep. CG-2007-2, Universität Bonn (2007).

39. Terlemez, O. et al. Master motor map (mmm) - framework and toolkit for capturing, representing, and reproducing man move on humanoid robots. In IEEE/RAS International Conference on Humanoid Robots (Humanoids), 894–901 (2014).

xl. Mandery, C., Terlemez, Ö., Exercise, 1000., Vahrenkamp, N. & Asfour, T. The kit whole-body man motility database. In 2015 International Conference on Advanced Robotics(ICAR), 329–336 (IEEE, 2015).

41. Hachaj, T., Ogiela, G. R. & Piekarczyk, M. The open up online repository of karate motion capture information: A tool for scientists and sport educators. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI), one–5 (IEEE, 2017).

42. Kolykhalova, K. et al. A multimodal dataset for the analysis of movement qualities in karate martial art. In 2015 7th International Conference on Intelligent Technologies for Interactive Amusement (INTETAIN), 74–78 (IEEE, 2015).

43. Niewiadomski R, et al. Assay of move quality in total-body physical activities. ACM Transactions on Interact. Intell. Syst. (TiiS) 2019;ix:1–20. doi: ten.1145/3132369. [CrossRef] [Google Scholar]

44. Zhang West, Liu Z, Zhou L, Leung H, Chan AB. Martial arts, dancing and sports dataset: A challenging stereo and multi-view dataset for 3d human pose estimation. Image Vis. Comput. 2017;61:22–39. doi: 10.1016/j.imavis.2017.02.002. [CrossRef] [Google Scholar]

45. Tits M, Laraba S, Caulier Due east, Tilmanne J, Dutoit T. Umons-taichi: A multimodal move capture dataset of expertise in taijiquan gestures. Information brief. 2018;19:1214–1221. doi: 10.1016/j.dib.2018.05.088. [PMC gratis article] [PubMed] [CrossRef] [Google Scholar]

46. Liu Ten, et al. Gait can reveal slumber quality with machine learning models. PloS i. 2019;14:e0223012. doi: 10.1371/journal.pone.0223012. [PMC free article] [PubMed] [CrossRef] [Google Scholar]

47. Pazhoumand-Dar H, Lam C-P, Masek M. Articulation movement similarities for robust 3d action recognition using skeletal information. J. Vis. Commun. Image Correspond. 2015;30:x–21. doi: 10.1016/j.jvcir.2015.03.002. [CrossRef] [Google Scholar]

48. Barre A, Armand S. Biomechanical toolkit: Open-source framework to visualize and procedure biomechanical information. Comput. methods programs biomedicine. 2014;114:lxxx–87. doi: x.1016/j.cmpb.2014.01.012. [PubMed] [CrossRef] [Google Scholar]

49. Urribarri, D. Thousand., Larrea, M. L., Castro, South. 1000. & Puppo, E. Visualization to compare karate motion captures. In XXV Congreso Argentino de Ciencias de la Computacion (CACIC 2019, Universidad Nacional de Rio Cuarto). (2019).

---

Articles from Scientific Data are provided here courtesy of Nature Publishing Group

---

hicksobscou.blogspot.com

Source: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7813879/

Share this post