In this study, we aimed to analyse goalball players time-motion variables (distance covered, time spent, maximum and average velocities) in official goalball match attacks, taking into account the attack phases (preparation and throwing), player position (centres and wings) and throwing techniques (frontal, spin and between the legs). A total of 365 attacks were assessed using a video based method (2D) through manual tracking using the Dvideo system. Inferential non-parametric statistics were applied for comparison of preparation vs. throwing phase, wings vs. centres and, among the throwing techniques, frontal, spin and between the legs. Significant differences were found between the attack preparation versus the throwing phase for all player time-motion variables: distance covered, time spent, maximum player velocity and average player velocity. Wing players performed most of the throws (85%) and covered longer distances than centres (1.65 vs 0.31 m). The between the legs and the spin throwing techniques presented greater values for most of the time-motion variables (distance covered, time spent and maximum player velocity) than did the frontal technique in both attack phases. These findings provide important information regarding players' movement patterns during goalball matches that can be used to plan more effective training.

Sports complexity must be investigated at competitions; therefore, non-invasive methods are essential. In this context, computer vision, image processing, and machine learning techniques can be useful in designing a non-invasive system for data acquisition that identifies players' positions in official basketball matches. Here, we propose and evaluate a novel video-based framework to perform automatic 3D localization of multiple basketball players. The introduced framework comprises two parts. The first stage is player detection, which aims to identify players' heads at the camera image level. This stage is based on background segmentation and on classification performed by an artificial neural network. The second stage is related to 3D reconstruction of the player positions from the images provided by the different cameras used in the acquisition. This task is tackled by formulating a constrained combinatorial optimization problem that minimizes the re-projection error while maximizing the number of detections in the formulated 3D localization problem.

No abstract

El objetivo de este estudio fue verificar cuales son los indicadores técnicos que diferencian a los equipos ganadores de perdedores en el baloncesto de Brasil Nueva (NBB) y en cada una de las siete temporadas analizadas.  El objetivo específico fue verificar en el análisis discriminante el efecto de la normalización de los indicadores técnicos por el número de ataques.  La muestra fue de 1912 partidos de temporadas entre 2008 y 2015 de la NBB.  La tasa de éxito de la función discriminante fue de cerca de 82%, sin diferencia sustancial entre el análisis con los indicadores técnicos normalizados y no normalizados.  Los indicadores que discriminan el equipo ganador del perdedor en todos los juegos fueron los rebotes defensivos y asistencias.  No se encontraron otros indicadores relacionados con el rodaje de dos y tres puntos en las diferentes estaciones.

Em busca por melhores condições de vida, evitando problemas locomotores, muitas vezes acometidos devido a questões posturais, são realizados inúmeros estudos relativos à baropodometria, a qual auxilia nos diagnósticos de problemas da distribuição da pressão plantar, responsável por inúmeras patologias posturais. Entre as variáveis obtidas nestes estudos está a curva da força de reação do solo em função do tempo, obtida a partir do protocolo de marcha, aplicando repetições do ciclo da marcha. Esse trabalho discute, portanto, a estabilidade das curvas médias da força de reação do solo em função do número de repetições do ciclo.