Recognising team activities from noisy data

Recently, vision-based systems have been deployed in professional sports to track the ball and players to enhance analysis of matches. Due to their unobtrusive nature, vision-based approaches are preferred to wearable sensors (e.g. GPS or RFID sensors) as it does not require players or balls to be instrumented prior to matches. Unfortunately, in continuous team sports where players need to be tracked continuously over long-periods of time (e.g. 35 minutes in field-hockey or 45 minutes in soccer), current vision-based tracking approaches are not reliable enough to provide fully automatic solutions. As such, human intervention is required to fix-up missed or false detections. However, in instances where a human can not intervene due to the sheer amount of data being generated - this data can not be used due to the missing/noisy data. In this paper, we investigate two representations based on raw player detections (and not tracking) which are immune to missed and false detections. Specifically, we show that both team occupancy maps and centroids can be used to detect team activities, while the occupancy maps can be used to retrieve specific team activities. An evaluation on over 8 hours of field hockey data captured at a recent international tournament demonstrates the validity of the proposed approach.

Fast line, arc/circle and leg detection from laser scan data in a player driver

A feature detection system has been developed for real-time identification of lines, circles and people legs from laser range data. A new method sutable for arc/circle detection is proposed: the Inscribed Angle Variance (IAV). Lines are detected using a recursive line fitting method.

Representing and discovering adversarial team behaviors using player roles

In this paper, we describe a method to represent and discover adversarial group behavior in a continuous domain. In comparison to other types of behavior, adversarial behavior is heavily structured as the location of a player (or agent) is dependent both on their teammates and adversaries, in addition to the tactics or strategies of the team. We present a method which can exploit this relationship through the use of a spatiotemporal basis model. As players constantly change roles during a match, we show that employing a "role-based" representation instead of one based on player "identity" can best exploit the playing structure. As vision-based systems currently do not provide perfect detection/tracking (e.g. missed or false detections), we show that our compact representation can effectively "denoise" erroneous detections as well as enabe temporal analysis, which was previously prohibitive due to the dimensionality of the signal. To evaluate our approach, we used a fully instrumented field-hockey pitch with 8 fixed high-definition (HD) cameras and evaluated our approach on approximately 200,000 frames of data from a state-of-the-art real-time player detector and compare it to manually labelled data.

Perceiving and acting upon spaces in a VR rugby task: Expertise effects in affordance detection and task achievement

This study used a virtual simulated 3vs3 rugby task to investigate whether gaps opening in particular running channels promote different actions by the ball-carrier player and whether an effect of rugby expertise is verified. We manipulated emergent gaps in three different locations: gap1 in the participant’s own running channel, gap 2 in the 1st receiver's running channel, and gap3 in the 2nd receiver's running channel. Recreational, intermediate, professional and non-rugby players performed the task. They could i) run with the ball, ii) make a short pass, or iii) make a long pass. All actions were digitally recorded. Results revealed that the emergence of gaps in the defensive line with respect to the participant’s own position significantly influenced action selection. Namely, ‘run’ was most often the action performed in gap 1, ‘short pass’ in gap 2, and ‘long pass’ in gap 3 trials. Furthermore, a strong positive relationship between expertise and task achievement was found.

Relevance of the pig stomach for the detection of dietary factors and gut maturation and control

In this thesis two approaches were applied to achieve a double general objective. The first chapter was dedicated to the study of the distribution of the expression of genes of several bitter and fat receptor in several gastrointestinal tracts. A set of 7 genes for bitter taste and for 3 genes for fat taste was amplified with real-time PCR from mRNA extracted from 5 gastrointestinal segments of weaned pigs. The presence of gene expression for several chemosensing receptors for bitter and fat taste in different compartments of the stomach confirms that this organ should be considered a player for the early detection of bolus composition. In the second chapter we investigated in young pigs the distribution of butyrate-sensing olfactory receptor (OR51E1) receptor along the GIT, its relation with some endocrine markers, its variation with age, and after interventions affecting the gut environment and intestinal microbiota in piglets and in different tissues. Our results indicate that OR51E1 is strictly related to the normal GIT enteroendocrine activity. In the third chapter we investigated the differential gene expression between oxyntic and pyloric mucosa in seven starter pigs. The obtained data indicate that there is significant differential gene exression between oxintic of the young pig and pyloric mucosa and further functional studies are needed to confirm their physiological importance. In the last chapter, thymol, that has been proposed as an oral alternative to antibiotics in the feed of pigs and broilers, was introduced directly into the stomach of 8 weaned pigs and sampled for gastric oxyntic and pyloric mucosa. The analysis of the whole transcript expression shoes that the stimulation of gastric proliferative activity and the control of digestive activity by thymol can influence positively gastric maturation and function in the weaned pigs.

Sensitive and selective detection of free FXIII activation peptide: a potential marker of acute thrombotic events

Coagulation factor XIII (FXIII) stabilizes fibrin fibers and is therefore a major player in the maintenance of hemostasis. FXIII is activated by thrombin resulting in cleavage and release of the FXIII activation peptide (AP-FXIII). The objective of this study was to characterize the released AP-FXIII and determine specific features that may be used for its specific detection. We analyzed the structure of bound AP-FXIII within the FXIII A-subunit and interactions of AP-FXIII by hydrogen bonds with both FXIII A-subunit monomers. We optimized our previously developed AP-FXIII ELISA by using 2 monoclonal antibodies. We determined high binding affinities between the antibodies and free AP-FXIII and demonstrated specific binding by epitope mapping analyses with surface plasmon resonance and enzyme-linked immunosorbent assay. Because the structure of free AP-FXIII had been characterized so far by molecular modeling only, we performed structural analysis by nuclear magnetic resonance. Recombinant AP-FXIII was largely flexible both in plasma and water, differing significantly from the rigid structure in the bound state. We suggest that the recognized epitope is either occluded in the noncleaved form or possesses a structure that does not allow binding to the antibodies. On the basis of our findings, we propose AP-FXIII as a possible new marker for acute thrombotic events.

Nutritional intake and body composition of adolescent soccer player of two different levels of performance: a comparative study

Soccer participation worldwide is increasing and every club try to discover new talents. It is well know that there is an important correlation between body composition (BC) and talent detection (TD) and when coaches and selectors choose players, they tend to choose them with optimum BC.

Causality detection on US mutual fund movements using evolutionary subset time-series

In this paper we develop an evolutionary kernel-based time update algorithm to recursively estimate subset discrete lag models (including fullorder models) with a forgetting factor and a constant term, using the exactwindowed case. The algorithm applies to causality detection when the true relationship occurs with a continuous or a random delay. We then demonstrate the use of the proposed evolutionary algorithm to study the monthly mutual fund data, which come from the 'CRSP Survivor-bias free US Mutual Fund Database'. The results show that the NAV is an influential player on the international stage of global bond and stock markets.