Performance Monitoring

Introduction

Technological innovation has made it possible to monitor athlete performance (other-tracking) in unobtrusive ways (Dhruv Seshadri et al., 2017) and develop athlete management systems. The growth in personal fitness and well-being devices has made it possible to track one's own performance (self-tracking) too (Gina Neff and Dawn Nafus, 2016). Shona Halson (2014) provides an overview of a range of approaches that combine other- and self-tracking measures of training load. She contributes to the discussion of the use made in the monitoring of performance of objective and subjective measures of well-being (Anne Saw, Luana Main & Paul Gastin, 2015).

Some of the resources for this topic can be found in this mindmap and in the recommended and suggested reading shared here on this page.

There are three components to this theme:

Background
Wearable technologies
Motion and Video Tracking

These components raise some fundamental philosophical, as well as logistical, issues to do with the Quantified Self, Algorithmic Skin and the Transparent Self.

As we engage in the process of monitoring other and self performance, we must consider how we: acquire performance data; (pre)process and transform the data; develop models about personal and collective performance; and share these data with a range of audiences. A consensus statement about monitoring athlete training loads (Pitre Bourdon et al, 2017:S2-167) concluded "we acknowledge that the decision on which monitoring tools or techniques to use should remain with the professionals working in sport".

As we contemplate the quantification of performance in training and competition, we should be mindful of the debate about the validity, reliability and sensitivity of measures of sporting performance (see, for example, Kevin Currell & Asker Jeukendrup, 2008; Anna Saw, Luana Main & Paul Gastin, 2015).

Background

Some of the issues raised by the monitoring of performance are discussed in these five papers.

Roland Tharp and Ronald Gallimore (1976) on the basketball coach, John Wooden.
Ian Franks and Gary Miller (1991) on training coaches to observe and remember.
Andrew Borrie, Gudberg Jonsonn and Magnus Magnusson (2002) on temporal pattern analysis.
Jürgen Edelmann-Nusser, Andreas Hohmann and Bernd Henneberg (2002) on swimming performance.
Muneaki Ohshima, Ning Zhong, Y Yao and Sinchi Murata (2004) on video tracking.

These papers give a feel for how the observation and analysis of performance changed over three decades.

Wearable Technologies

Antonio Salazar and his colleagues (2010) observed:

Monitoring technology has experienced a boom in the past decade. Not only have sensors, mixed-signal components, transceivers become smaller, more powerful and more energy efficient; so have the contributions in communication protocols, textile electronics, and the general interest for body-centric devices for fields such as ... sports.

This boom is accelerating in pace (see, for example, Shona Halson, 2014; Thomas Page, 2015; Ryan Li et al., 2016; Dhruv Seshadri et al., 2017).

This is one view of the presence of wearable technologies in sport (location and inertial sensing).

As you explore this topic you might like to consider the benefits pervasive computing brings to the monitoring performance (through the combination of informatics and analytics) whilst reflecting on the validity and reliability of data acquired through observation and remote sensing (Macfarlane Scott, Tannath Scott & Vincent Kelly, 2016; James Malone et al., 2016; Thomas Haugen & Martin Buchheit, 2016; Ryu Nagahara et al., 2016; Matthew Varley et al., 2017). You might consider some of the ethical issues about surveillance too.

Motion and Video Tracking

Sian Barris and Chris Button (2008) provided a state of the art review of vision-based motion analysis in sport (publications in the years 1970-2007). They distinguish:

Manual vision-based tracking systems
Automated vision-based tracking systems
Commercially available vision-based analysis systems

Their paper concludes with the observation "a wealth of fascinating information related to multiple player interaction will soon become available that has the potential to enhance understanding of sports performance to a new level" (2008: 1041).

João Serrano, Shakib Shahidian & Orlando Fernandes (2014) provide an example of a mixed methods approach to motion tracking. Their study presents "a validation protocol using a global positioning system with real-time differential correction to assess the validity and the reliability of a semi-auto tracking software used to quantify the movement patterns of football players".

Julian Castellano, David Alvarez-Pastor & Paul Bradley (2014) reviewed two commercially available vision-based systems in football. They note:

Current Computerised tracking systems in elite soccer still provide adequate detail on the physical and technical performances of players but must develop further to compete with the array of additional parameters offered by new technologies such as global or local positioning system technology.

Robert Rein & Daniel Memmert (2016) discuss how the increasing amount of data from such systems (tracking technologies and physiological training data collected through miniature sensor technologies) might be used.

Dominic Southgate, Joe Prinold & Robert Weinert-Aplin (2016) have provided a recent review of motion analysis in sport.

This is an example (from the Disney Research Hub, 2017) of where some of this work produced by vision tracking is taking practice:

Another illustration of the rich data available from tracking technologies is MAProgress. Their service uses live GPS tracking systems. This is an example of the functionality available in a case study of a coast to coast bicycle race in New Zealand.

MAProgress provide details of the resources they use to deliver their service to events such as the Indian Pacific Wheel Race 2017.

Jun Burden and his colleagues (2010) report the development of an automated video tracking system to track changeovers in team pursuit cycling races.Their system used a single camera in burst mode, and employed background subtraction, edge detection and predictive tracking. The system was implemented in Python and OpenCV.

Marco Beato & Mikael Jamil (2017) consider the intra-system reliability of a digital tracking system for performance analysis in football. The conclude "actions of high intensity, high speed, and power data are usually associated with low levels of reliability, but this study revealed that the Digital.Stadium® VTS is more than capable of recording this data accurately".

Employment Examples

Sport Scientist

In October 2017, the Crusaders rugby union team advertised for a sport scientist. The job description included the following:

Reporting to the Crusaders’ Head Strength and Conditioning Coach, you will be responsible for overseeing and coordinating all aspects of the Crusaders’ performance monitoring systems including further enhancement of data collection, processing and reporting methods.
You will also be responsible for collating and reporting on all performance monitoring data to ensure optimal player loading for conditioning and recovery.
In addition, you will undertake research projects to support the Medical, Strength and Conditioning and Performance Analysis Departments to ensure they remain best practice leaders in elite sport.
To be successful in this role, you will need to be appropriately qualified by training and/or experience, including a proven ability in research, data analysis and reporting including an outstanding level of understanding of performance monitoring and analysis tools ideally in a rugby environment.
You will also need to demonstrate extensive experience in the use of GPS Technology both hardware and software and a deep understanding and love of rugby including the position specific demands it places on professional athletes.
You will be a team player and have the ability to develop strong working relationships and effectively communicate analytical information.
Prior experience in an elite sports team environment would be an advantage.