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.

Human resource management reform in the Indonesian civil service : towards strategic fit?

Studies of strategic HRM have dominated HRM research over the last three decades. Focusing on the HRM-organisation performance relationship, researchers take various themes and perspectives in their approach to strategic HRM. Among these themes, two contrasting approaches of strategic HRM continue to flourish: first, the best practice approach suggests that certain HRM practices will have the same effect irrespective of context and, second, the best fit approach suggests that the choice of HRM practices should be designed in accordance with an organisations’ specific context. While there is little consensus on what constitutes strategic HRM, the most common feature agreed in this field is the notion of the strategic integration; aligning HRM practices with organisations’ overall strategic objectives (vertical fit) and with each other (horizontal fit). Utilising the best fit approach as its theoretical framework, this study examines how vertical and horizontal fit is practised in the Indonesian civil service and what factors likely influence the prevalence of vertical and horizontal fit in the Indonesian civil service context. This study is significant for two important reasons. Firstly, the literature suggests that there are limited studies examining the best fit concept in the civil sector despite its implementation in the private sector positively contributing to organisational performance improvement. Secondly, the study provides enlightenment on how the best fit approach could contribute to performance improvement in the Indonesian civil service. This is in line with the fact that negative images of the Indonesian civil service are continuously highlighted although various HRM reform initiatives have been put in place. To achieve the objectives of the study, the qualitative case study approach accompanied by semi-structured interviews was employed involving 53 senior officials and one focus group discussion from eight Indonesian government agencies, consisting of three central agencies mandated to manage human resources, the National Bureaucratic Reform Team and four line agencies from both central and local governments. Thematic analysis was employed for data analyses and NVIVO software was used to manage the data. The study suggests three main findings. First, various HRM initiatives in relation to the HRM reform have been introduced in the Indonesian civil service differentiating them from the old HRM practices. However, the findings indicate that some HRM policies are still contradicting and hinder vertical and horizontal fit. Second, despite the contradictory policies, vertical and horizontal fit can be seen in the line agencies which have been acknowledged as ‘reformed agencies’. This demonstrates that the line agencies play an important role in aligning HRM practices with the line agencies’ goals and objectives and with one another although they are bounded by HRM policies that are unlikely to support the vertical and horizontal fit concept. Third, factors influencing the prevalence of vertical and horizontal fit include knowledge of contemporary HRM in both central agencies and line agencies, commitment from the line agencies’ leaders, devolvement of HRM to the line agencies and the socio-political and economic environments of the Indonesian civil service. The findings of the study raise policy, practical and theoretical implications. In terms of policy implications, the study highlights the importance of fit in HRM policies to support the achievement of the line agencies’ goals. Therefore, when formulating an HRM policy, the central agencies need to ensure that the HRM policy is linked to line agencies’ goals and to other HRM policies. This is to ensure synchronisation among the policies and thus maximising the achievement of the line agencies’ goals. From the practical perspectives, the study highlights important points which can be learned by the central agencies in carrying out their strategic role with regard to the formulation of HRM policies; by the line agencies in maximising the contribution of HRM to the achievement of the goals and objectives of the agencies through the implementation of the best fit concept, and by the leaders of the agencies in providing continuous support to each of the involved parties in the line agencies and involving the HRM department in all agency’s strategic decision-making. In relation to the theoretical implication, it is clear that the best fit approach is not thoroughly applied due to factors discussed previously. However, this does not mean that the best fit concept cannot be implemented. As argued by McCourt & Ramgutty-Wong (2003), instead of adopting the whole concept of best fit, a modulated approach reflecting the best fit concept, such as selecting individual HRM practices and experimenting with devolution, is possible for civil service organisations which still embrace centralised HRM systems. As demonstrated in the findings, some of the line agencies being studied seem to be ready to adopt the best fit approach given that they have knowledge of the best fit concept, strong support from the top leader, less political intervention and less corruption, collusion, and nepotism practices in their HRM practices.