Team-based invasion sports such as football, basketball and hockey are similar in the sense that the players are able to move freely around the playing area; and that player and team performance cannot be fully analysed without considering the movements and interactions of all players as a group. State of the art object tracking systems now produce spatio-temporal traces of player trajectories with high definition and high frequency, and this, in turn, has facilitated a variety of research efforts, across many disciplines, to extract insight from the trajectories. We survey recent research efforts that use spatio-temporal data from team sports as input, and involve non-trivial computation. This article categorises the research efforts in a coherent framework and identifies a number of open research questions.

Type IIB fast fibres are typically demonstrated in human skeletal muscle by histochemical staining for the ATPase activity of myosin heavy-chain (MyHC) isoforms. However, the monoclonal antibody specific for the mammalian IIB isoform does not detect MyHC IIB protein in man and MyHC IIX RNA is found in histochemically identified IIB fibres, suggesting that the IIB protein isoform may not be present in man; if this is not so, jaw-closing muscles, which express a diversity of isoforms, are likely candidates for their presence. ATPase histochemistry, immunohistochemistry polyacrylamide gel electrophoresis and in situ hybridization, which included a MyHC IIB-specific mRNA riboprobe, were used to compare the composition and RNA expression of MyHC isoforms in a human jaw-closing muscle, the masseter, an upper limb muscle, the triceps, an abdominal muscle, the external oblique, and a lower limb muscle, the gastrocnemius. The external oblique contained a mixture of histochemically defined type I, IIA and IIB fibres distributed in a mosaic pattern, while the triceps and gastrocnemius contained only type I and IIA fibres. Typical of limb muscle fibres, the MyHC I-specific mRNA probes hybridized with histochemically defined type I fibres, the IIA-specific probes with type IIA fibres and the IIX-specific probes with type IIB fibres. The MyHC IIB mRNA probe hybridized only with a few histochemically defined type I fibres in the sample from the external oblique; in addition to this IIB message, these fibres also expressed RNAs for MyHC I, IIA and IIX. MyHC IIB RNA was abundantly expressed in histochemical and immunohistochemical type IIA fibres of the masseter, together with transcripts for IIA and in some cases IIX. No MyHC IIB protein was detected in fibres and extracts of either the external oblique or masseter by immunohistochemistry, immunoblotting and electrophoresis. Thus, IIB RNA, but not protein, was found in the fibres of two different human skeletal muscles. It is believed this is the first report of the substantial expression of IIB mRNA in man as demonstrated in a subset of masseter fibres, but rarely in limb muscle, and in only a few fibres of the external oblique. These findings provide further evidence for the complexity of myosin gene expression, especially in jaw-closing muscles.

A knowledgeable observer of a game of football (soccer) can make a subjective evaluation of the quality of passes made between players during the game. We investigate the problem of producing an automated system to make the same evaluation of passes. We present a model that constructs numerical predictor variables from spatiotemporal match data using feature functions based on methods from computational geometry, and then learns a classification function from labelled examples of the predictor variables. Furthermore, the learned classifiers are analysed to determine if there is a relationship between the complexity of the algorithm that computed the predictor variable and the importance of the variable to the classifier. Experimental results show that we are able to produce a classifier with 85.8% accuracy on classifying passes as Good, OK or Bad, and that the predictor variables computed using complex methods from computational geometry are of moderate importance to the learned classifiers. Finally, we show that the interrater agreement on pass classification between the machine classifier and a human observer is of similar magnitude to the agreement between two observers. Categories and Subject DescriptorsI.5 [Pattern Recognition]: Design Methodology-Feature evaluation and selection * A poster submission has also been made to the Large Scale Sports Analytics workshop at the KDD conference on this work. This submission covers the problem definition and solution framework described in this paper, and also includes preliminary experimental results on the accuracy of the framework.