Automatic Markerless Motion Detector Method against Traditional Digitisation for 3-Dimensional Movement Kinematic Analysis of Ball Kicking in Soccer Field Context

Abstract

Kicking is a fundamental skill in soccer that often contributes to match outcomes. Lower limb movement features (e.g., joint position and velocity) are determinants of kick performance. However, obtaining kicking kinematics under field conditions generally requires time-consuming manual tracking. The current study aimed to compare a contemporary markerless automatic motion estimation algorithm (OpenPose) with manual digitisation (DVIDEOW software) in obtaining on-field kicking kinematic parameters. An experimental dataset of under-17 players from all outfield positions was used. Kick attempts were performed in an official pitch against a goalkeeper. Four digital video cameras were used to record full-body motion during support and ball contact phases of each kick. Three-dimensional positions of hip, knee, ankle, toe and foot centre-of-mass (CMfoot) generally showed no significant differences when computed by automatic as compared to manual tracking (whole kicking movement cycle), while only z-coordinates of knee and calcaneus markers at specific points differed between methods. The resulting time-series matrices of positions (r2 = 0.94) and velocity signals (r2 = 0.68) were largely associated (all p < 0.01). The mean absolute error of OpenPose motion tracking was 3.49 cm for determining positions (ranging from 2.78 cm (CMfoot) to 4.13 cm (dominant hip)) and 1.29 m/s for calculating joint velocity (0.95 m/s (knee) to 1.50 m/s (non-dominant hip)) as compared to reference measures by manual digitisation. Angular range-of-motion showed significant correlations between methods for the ankle (r = 0.59, p < 0.01, large) and knee joint displacements (r = 0.84, p < 0.001, very large) but not in the hip (r = 0.04, p = 0.85, unclear). Markerless motion tracking (OpenPose) can help to successfully obtain some lower limb position, velocity, and joint angular outputs during kicks performed in a naturally occurring environment.

Holistic approach to testing ball kicking mechanics and outcome metrics in soccer: methodological aspects, observation and intervention (PhD Academy Award)

“…Extraction of human movement kinematics data based on artificial intelligence (AI) gained rapid popularity in the recent years (eg, OpenPose; https://github.com/CMU-Perceptual-Computing-Lab/openpose); its measurement error to ball kicking is described in a separate technical note article 4. Thus, while the kinematics data of the two first observational articles reported above were obtained using semiautomatic traditional tracking, the later intervention studies (n=15) whose purposes are synthesised in the next paragraph rely on the use of the aforementioned AI-assisted motion analysis algorithm.…”

“…Here I provide a brief overview of six research articles1–6 that were developed to offer data and interpretations into strengths/weaknesses of current soccer kicking biomechanics testing paradigms,1 4 observation2 3 and intervention 5 6. The overall aims of the summarised articles were to investigate, in young academy soccer players, whether interindividual’s characteristics are related to ball kicking performance2 3 and common practice prescriptions and their possible effects5 6 on the movement mechanics and outcome metrics derived from shooting aiming at a far target.…”

“…The rationale supporting each of the articles is presented in a critical appraisal of current literature, which identifies and describes opportunities to design original works 1. The experiments all developed on-field2–6 seem also supported by a common sense that design of a sequence of studies in the area of team sports may not always follow a rigid format,7 including as for example a combination of investigations having distinct formats like observational and intervention 8…”

“…In paper I, the most important findings were that kick testing constraints used in research often lack resemblance with in-game situations 1. Modifying current research paradigms is therefore necessary like including kicks against opponent goalkeeper and/or defender in the experiments/testing sessions; this was considered in the observational articles addressing effects of internal individual constraints 2–4. Paper II revealed that kicking ball velocity and accuracy are both influenced (20–35%) by EEG signalling, mainly those observed, respectively, in the frontal and occipital brain regions 2.…”

Recovery of kicking kinematics and performance following intermittent high-intensity running bouts in young soccer players: can a local cooling intervention help?

“…Afterwards, video files from data collections were downloaded onto a laptop computer (DELL INSPIRON 5590; Dell Inc., Texas–USA). The OpenPose markerless motion detector method in addition to a tracking algorithm previously validated to evaluate ball kicking action (Palucci Vieira et al, 2022c) were used to automatically extract 2-dimensional screen coordinates of seven keypoints derived from the hip (preferred and non-preferred), knee, ankle and foot regions (measurement error = 3.49 cm and 1.29 m/s; Palucci Vieira et al (2022c)). A calibration frame was defined using 49 reference points with absolute 3-dimensional coordinates known (4.11 × 4.05 × 1.30 m).…”