Non-Invasive Performance Measurement in Combat Sports

Abstract

Abstract.Computer vision offers a growing capacity to detect and classify actions in a large range of sports. Since combat sports are highly dynamic and physically demanding, it is difficult to measure features of performance from competition in a safe and practical way. Also, coaches frequently wish to measure the performance characteristics of other competitors. For these reasons it is desirable to be able to measure features of competitive performance without using sensors or physical devices. We present a non-invasive method for extracting pose and features of behaviour in boxing using vision cameras and time of flight sensors. We demonstrate that body parts can be reliably located, which allow punching actions to be detected. Those data can then visualised in a way that allows coaches to analysis behaviour.

Herramientas tecnológicas para la medición y registro de movimiento objetivo de la hiperactividad

“…Una de las grandes ventajas de este dispositivo es su elevada precisión y frecuencia de muestreo. Por este motivo se ha utilizado para realizar investigaciones en campos tan diversos como el deporte [39], la rehabilitación [40], el reconocimiento de gestos [41], etc. Sin embargo, su elevado precio que ronda los 4000$ no lo hace asequible para todos los proyectos.…”

AI-based, automated longitudinal performance monitoring of multiple boxers in large scale videos

“…Soudeh, Stuart, and Clinton in 2016 [11] employed depth sensors for locating boxers within the ring. They formed each boxer's contour by extracting the normalized histogram of the foreground contour at various depths.…”