Singapore Aquatics adopts drone technology and artificial intelligence in training
Prof Kenneth Goh, President of the Singapore Aquatics and Associate Professor of Strategy and Entrepreneurship at Singapore Management University, facilitated collaboration between the Singapore Aquatics, Singapore Management University, and the Singapore University of Technology and Design, showcasing how academia and industry can work together to solve problems.
Casting a watchful eye over the pool, Singapore Aquatics’ (SAQ) latest addition to the coaching team immediately saw exactly when and how much the swimmer’s speed dropped, and how his right knee and ankle angles increased over the same period.
But SAQ’s latest recruitment is not here to replace national swimming coach Gary Tan. Instead, it is a system, developed by researchers from the Singapore Management University (SMU) and the Singapore University of Technology and Design (SUTD), which combines drone technology and artificial intelligence (AI).
The system – comprising a drone, gaming laptop and tablet – segments an athlete’s body into 17 different points and helps human coaches like Tan to optimise training programmes and improve performance by identifying, in real time, critical factors that influence a swimmer’s speed.
Following a demonstration at the OCBC Aquatic Centre on March 4, Tan said that he has been trying out the system once a month. He intends to use it more frequently in a bid to push the national swimmers to set personal bests and national records at the July 11-Aug 3 World Aquatics Championships in Singapore and the Dec 9-20 SEA Games in Thailand.
He said: “From where coaches stand on the side of the pool, we can’t get a top view of certain things like the hands in different angles. This system gives us a more enhanced view during our practices to see if a kid is swimming in a symmetrical or non-symmetrical way.
“The real-time feedback is fantastic as it helps our training become more intentful and smarter.
“As we advance into the next phase of the National Training Centre’s development, this partnership will help us refine training strategies and stay competitive on the world stage. By leveraging research-driven insights, we can fine-tune our athlete’s performance, where every marginal gain matters.”
The idea for the computer vision algorithms and analytics system surfaced in 2024 following a discussion about real-time data in high-performance fields between SMU professor of computer science, Rajesh Krishna Balan, and SAQ president Kenneth Goh, who is also an associate professor of strategy and entrepreneurship (education) at the university.
Goh said: “To innovate and integrate digital solutions effectively, we need to overcome regulatory and practical hurdles, which often involve close collaboration and building trust with regulators and stakeholders.
“This project is a great opportunity to foster collaboration and elevate aquatics in Singapore as well as showcase an interdisciplinary approach across academia and industry to solve real-world problems.”
The software for the system was built by Tran Ngoc Doan Thu, a research scientist and recent SMU computer science PhD graduate who is part of a team led by Prof Balan, and advised by Assistant Professor Kenny Choo from SUTD’s information systems technology and design pillar as well as design and artificial intelligence programme.
The team took six months to produce a prototype and a further six months to refine it.
During the demonstration, SUTD’s engineering product development (EPD) pillar research fellow Shane Kyi Hla Win operated the drone, which comes with a high-resolution camera, to fly about eight metres above the swimmers.
Without requiring an internet connection, the video images of the swimmers are downloaded and analysed by the custom analytics and user interface software, which uses AI models and computer vision algorithms to recognise human poses and swimming events based on the coaches’ expertise.
Meanwhile, the custom user interface on the tablet allows coaches to visualise the results and gain a deeper understanding of the athlete’s swimming technique, through the body’s symmetry and balance, stroke duration and swimming velocity in real time, as well as how these performance factors differ between training and competition.
For example, the distance between the wrist and head may be stretched further to improve the swimmer’s speed.
Prof Balan said: “This exciting research can potentially elevate our sporting performance by making coaching more precise, efficient and cost-effective without huge investments in computing hardware.
“Real-time insights from video analytics are proving to be a valuable tool in helping coaches to fine-tune their training strategies with greater accuracy. To fully benefit from this technology, coaches need tailored video analytics that align with their coaching methods – allowing them to explore and test key performance hypotheses with confidence.”
While elaborate analytics systems can cost up to hundreds of thousands of dollars, the Singaporean set-up can be assembled for just a few thousand dollars. The project was supported by the Ministry of Education and funded through the SMU-SUTD internal research grant call.
Associate Professor Foong Shaohui from SUTD’s EPD pillar shared that the system can also be used for other aquatics sports like diving, as well as sailing. He said: “Drones are cost-effective and portable, offering a fraction of the expenses of specialised training facilities.
“They give an unobstructed overhead view of swimmers, capturing the movement of all limbs from both sides during strokes… (and) they remove the need for multiple underwater or poolside cameras to calculate swimming parameters.
“In addition, this system is not restricted to any specific facility and can be deployed to any swimming pool rapidly with no set-up time, making it a valuable training aid for swimmers at every level.”
Straits Times: https://www.straitstimes.com/sport/singapore-aquatics-adopts-drone-technology-and-artificial-intelligence-in-training
