Vision-based tracking for sports performance analysis

With the world of professional sports shifting towards employing better sport analytics, the demand for vision-based performance analysis is growing increasingly in recent years. In addition, the nature of many sports does not allow the use of any kind of sensors or other wearable markers attached to players for monitoring their performances during competitions. This provides a potential application of systematic observations such as tracking information of the players to help coaches to develop their visual skills and perceptual awareness needed to make decisions about team strategy or training plans. My PhD project is part of a bigger ongoing project between sport scientists and computer scientists involving also industry partners and sports organisations. The overall idea is to investigate the contribution technology can make to the analysis of sports performance on the example of team sports such as rugby, football or hockey. A particular focus is on vision-based tracking, so that information about the location and dynamics of the players can be gained without any additional sensors on the players. To start with, prior approaches on visual tracking are extensively reviewed and analysed. In this thesis, methods to deal with the difficulties in visual tracking to handle the target appearance changes caused by intrinsic (e.g. pose variation) and extrinsic factors, such as occlusion, are proposed. This analysis highlights the importance of the proposed visual tracking algorithms, which reflect these challenges and suggest robust and accurate frameworks to estimate the target state in a complex tracking scenario such as a sports scene, thereby facilitating the tracking process. Next, a framework for continuously tracking multiple targets is proposed. Compared to single target tracking, multi-target tracking such as tracking the players on a sports field, poses additional difficulties, namely data association, which needs to be addressed. Here, the aim is to locate all targets of interest, inferring their trajectories and deciding which observation corresponds to which target trajectory is. In this thesis, an efficient framework is proposed to handle this particular problem, especially in sport scenes, where the players of the same team tend to look similar and exhibit complex interactions and unpredictable movements resulting in matching ambiguity between the players. The presented approach is also evaluated on different sports datasets and shows promising results. Finally, information from the proposed tracking system is utilised as the basic input for further higher level performance analysis such as tactics and team formations, which can help coaches to design a better training plan. Due to the continuous nature of many team sports (e.g. soccer, hockey), it is not straightforward to infer the high-level team behaviours, such as players’ interaction. The proposed framework relies on two distinct levels of performance analysis: low-level performance analysis, such as identifying players positions on the play field, as well as a high-level analysis, where the aim is to estimate the density of player locations or detecting their possible interaction group. The related experiments show the proposed approach can effectively explore this high-level information, which has many potential applications.

Analysis of the "Sonar Hopf" Cochlea

The "Sonar Hopf" cochlea is a recently much advertised engineering design of an auditory sensor. We analyze this approach based on a recent description by its inventors Hamilton, Tapson, Rapson, Jin, and van Schaik, in which they exhibit the "Sonar Hopf" model, its analysis and the corresponding hardware in detail. We identify problems in the theoretical formulation of the model and critically examine the claimed coherence between the described model, the measurements from the implemented hardware, and biological data.

Sensory gating and its modulation by cannabinoids: electrophysiological, computational and mathematical analysis

Gating of sensory information can be assessed using an auditory conditioning-test paradigm which measures the reduction in the auditory evoked response to a test stimulus following an initial conditioning stimulus. Recording brainwaves from specific areas of the brain using multiple electrodes is helpful in the study of the neurobiology of sensory gating. In this paper, we use such technology to investigate the role of cannabinoids in sensory gating in the CA3 region of the rat hippocampus. Our experimental results show that application of the exogenous cannabinoid agonist WIN55,212-2 can abolish sensory gating. We have developed a phenomenological model of cannabinoid dynamics incorporated within a spiking neural network model of CA3 with synaptically interacting pyramidal and basket cells. Direct numerical simulations of this model suggest that the basic mechanism for this effect can be traced to the suppression of inhibition of slow GABAB synapses. Furthermore, by working with a simpler mathematical firing rate model we are able to show the robustness of this mechanism for the abolition of sensory gating.

Network Construction and Graph Theoretical Analysis of Functional Language Networks in Pediatric Epilepsy

This dissertation introduces a new approach for assessing the effects of pediatric epilepsy on the language connectome. Two novel data-driven network construction approaches are presented. These methods rely on connecting different brain regions using either extent or intensity of language related activations as identified by independent component analysis of fMRI data. An auditory description decision task (ADDT) paradigm was used to activate the language network for 29 patients and 30 controls recruited from three major pediatric hospitals. Empirical evaluations illustrated that pediatric epilepsy can cause, or is associated with, a network efficiency reduction. Patients showed a propensity to inefficiently employ the whole brain network to perform the ADDT language task; on the contrary, controls seemed to efficiently use smaller segregated network components to achieve the same task. To explain the causes of the decreased efficiency, graph theoretical analysis was carried out. The analysis revealed no substantial global network feature differences between the patient and control groups. It also showed that for both subject groups the language network exhibited small-world characteristics; however, the patient’s extent of activation network showed a tendency towards more random networks. It was also shown that the intensity of activation network displayed ipsilateral hub reorganization on the local level. The left hemispheric hubs displayed greater centrality values for patients, whereas the right hemispheric hubs displayed greater centrality values for controls. This hub hemispheric disparity was not correlated with a right atypical language laterality found in six patients. Finally it was shown that a multi-level unsupervised clustering scheme based on self-organizing maps, a type of artificial neural network, and k-means was able to fairly and blindly separate the subjects into their respective patient or control groups. The clustering was initiated using the local nodal centrality measurements only. Compared to the extent of activation network, the intensity of activation network clustering demonstrated better precision. This outcome supports the assertion that the local centrality differences presented by the intensity of activation network can be associated with focal epilepsy.

The influence of actions on auditory perception: cognitive and neural mechanisms

It is well known that self-generated stimuli are processed differently from externally generated stimuli. For example, many people have noticed since childhood that it is very difficult to make a self-tickling. In the auditory domain, self-generated sounds elicit smaller brain responses as compared to externally generated sounds, known as the sensory attenuation (SA) effect. SA is manifested in reduced amplitudes of evoked responses as measured through MEEG, decreased firing rates of neurons and a lower level of perceived loudness for self-generated sounds. The predominant explanation for SA is based on the idea that self-generated stimuli are predicted (e.g., the forward model account). It is the nature of their predictability that is crucial for SA. On the contrary, the sensory gating account emphasizes a general suppressive effect of actions on sensory processing, regardless of the predictability of the stimuli. Both accounts have received empirical support, which suggests that both mechanisms may exist. In chapter 2, three behavioural studies concerning the influence of motor activation on auditory perception were presented. Study 1 compared the effect of SA and attention in an auditory detection task and showed that SA was present even when substantial attention was paid to unpredictable stimuli. Study 2 compared the loudness perception of tones generated by others between Chinese and British participants. Compared to externally generated tones, a decrease in perceived loudness for others generated tones was found among Chinese but not among the British. In study 3, partial evidence was found that even when reading words that are related to action, auditory detection performance was impaired. In chapter 3, the classic SA effect of M100 suppression was replicated with MEG in study 4. With time-frequency analysis, a potential neural information processing sequence was found in auditory cortex. Prior to the onset of self-generated tones, there was an increase of oscillatory power in the alpha band. After the stimulus onset, reduced gamma power and alpha/beta phase locking were found. The three temporally segregated oscillatory events correlated with each other and with SA effect, which may be the underlying neural implementation of SA. In chapter 4, a TMS-MEG study was presented investigating the role of the cerebellum in adapting to delayed presentation of self-generated tones (study 5). It demonstrated that in sham stimulation condition, the brain can adapt to the delay (about 100 ms) within 300 trials of learning by showing a significant increase of SA effect in the suppression of M100, but not M200 component. Whereas after stimulating the cerebellum with a suppressive TMS protocol, the adaptation in M100 suppression disappeared and the pattern of M200 suppression reversed to M200 enhancement. These data support the idea that the suppressive effect of actions on auditory processing is a consequence of both motor driven sensory predictions and general sensory gating. The results also demonstrate the importance of neural oscillations in implementing SA effect and the critical role of the cerebellum in learning sensory predictions under sensory perturbation.

Raman microscopy of formamide-intercalated kaolinites treated by controlled-rate thermal analysis technology

Raman spectroscopy of formamide-intercalated kaolinites treated using controlled-rate thermal analysis technology (CRTA), allowing the separation of adsorbed formamide from intercalated formamide in formamide-intercalated kaolinites, is reported. The Raman spectra of the CRTA-treated formamide-intercalated kaolinites are significantly different from those of the intercalated kaolinites, which display a combination of both intercalated and adsorbed formamide. An intense band is observed at 3629 cm-1, attributed to the inner surface hydroxyls hydrogen bonded to the formamide. Broad bands are observed at 3600 and 3639 cm-1, assigned to the inner surface hydroxyls, which are hydrogen bonded to the adsorbed water molecules. The hydroxyl-stretching band of the inner hydroxyl is observed at 3621 cm-1 in the Raman spectra of the CRTA-treated formamide-intercalated kaolinites. The results of thermal analysis show that the amount of intercalated formamide between the kaolinite layers is independent of the presence of water. Significant differences are observed in the CO stretching region between the adsorbed and intercalated formamide.

Detailed analysis of a conservative difference approximation for the time fractional diffusion equation

Diffusion equations that use time fractional derivatives are attractive because they describe a wealth of problems involving non-Markovian Random walks. The time fractional diffusion equation (TFDE) is obtained from the standard diffusion equation by replacing the first-order time derivative with a fractional derivative of order α ∈ (0, 1). Developing numerical methods for solving fractional partial differential equations is a new research field and the theoretical analysis of the numerical methods associated with them is not fully developed. In this paper an explicit conservative difference approximation (ECDA) for TFDE is proposed. We give a detailed analysis for this ECDA and generate discrete models of random walk suitable for simulating random variables whose spatial probability density evolves in time according to this fractional diffusion equation. The stability and convergence of the ECDA for TFDE in a bounded domain are discussed. Finally, some numerical examples are presented to show the application of the present technique.

Determination of preventive maintenance lead time using hybrid analysis

The time for conducting Preventive Maintenance (PM) on an asset is often determined using a predefined alarm limit based on trends of a hazard function. In this paper, the authors propose using both hazard and reliability functions to improve the accuracy of the prediction particularly when the failure characteristic of the asset whole life is modelled using different failure distributions for the different stages of the life of the asset. The proposed method is validated using simulations and case studies.

Hydrazine-hydrate intercalated halloysite under controlled-rate thermal analysis conditions

The thermal behaviour of halloysite fully expanded with hydrazine-hydrate has been investigated in nitrogen atmosphere under dynamic heating and at a constant, pre-set decomposition rate of 0.15 mg min-1. Under controlled-rate thermal analysis (CRTA) conditions it was possible to resolve the closely overlapping decomposition stages and to distinguish between adsorbed and bonded reagent. Three types of bonded reagent could be identified. The loosely bonded reagent amounting to 0.20 mol hydrazine-hydrate per mol inner surface hydroxyl is connected to the internal and external surfaces of the expanded mineral and is present as a space filler between the sheets of the delaminated mineral. The strongly bonded (intercalated) hydrazine-hydrate is connected to the kaolinite inner surface OH groups by the formation of hydrogen bonds. Based on the thermoanalytical results two different types of bonded reagent could be distinguished in the complex. Type 1 reagent (approx. 0.06 mol hydrazine-hydrate/mol inner surface OH) is liberated between 77 and 103°C. Type 2 reagent is lost between 103 and 227°C, corresponding to a quantity of 0.36 mol hydrazine/mol inner surface OH. When heating the complex to 77°C under CRTA conditions a new reflection appears in the XRD pattern with a d-value of 9.6 Å, in addition to the 10.2 Ĺ reflection. This new reflection disappears in contact with moist air and the complex re-expands to the original d-value of 10.2 Å in a few h. The appearance of the 9.6 Å reflection is interpreted as the expansion of kaolinite with hydrazine alone, while the 10.2 Å one is due to expansion with hydrazine-hydrate. FTIR (DRIFT) spectroscopic results showed that the treated mineral after intercalation/deintercalation and heat treatment to 300°C is slightly more ordered than the original (untreated) clay.