National Olympic teams are using machine learning to gain an edge in competition over their opponents at the Tokyo Olympic Games 2020.
Machine learning technologies are being used at the international sports event from athlete data tracking, coaches’ real-time feedback that can tell athletes when to train and when to stop, to predicting sports injuries with algorithms.
Machine learning algorithms analyze athlete data collected from multiple systems like Alibaba Group and Intel which partnered to run a 3D athlete-tracking system that allows coaches to probe into every minute movement of their Olympic athletes. The system relies on algorithms to understand the biomechanics of the movement of athletes captured by cameras and estimate the position of key body joints. As a field of artificial intelligence, computer vision enables machines to perform image processing tasks with the aim of imitating human vision.
Machine learning analyzes athletes’ performance using video intelligence API to track posture, a machine learning technique analyzes photos or videos of humans and tries to locate their body parts. Using TensorFlow, the person detection feature recognizes body parts, facial features, and clothing and pose detection makes pre-processing steps for training machine learning models.
Coaches are relying on machine learning to see individualized data for each athlete, based on variables like fitness levels and overall capabilities specific to that player. This process takes it to another level beyond just tracking data. Not all athletes are the same, so machine learning is a critical component that learns about each athlete and flags any meaningful, high-risk changes for his/her performance.
Workloading information and other data related to sleep, hydration, diet, mood, stress, and perceived muscle soreness are now working under machine learning algorithms, letting coaches look at the analytics to help drive decision-making related to the amount of training an athlete should be doing.
Olympic teams using Nike’s Vaporfly 4% running shoes, can reduce the energetic cost of running by four percent compared to other marathon shoes. Using analytics with the data it produced has brought more insights and a chance to quantify the performance of the athletes. The “RL COOLING” from Ralph Lauren’s senses body temperature and disperses heat from the wearer’s skin. Prediction of internal body temperature using machine learning models can be used for supervised learning keeping athletes cooler under the competition.
Olympic sports like swimming, gymnastics, and beach volleyball are using Omega’s timekeeper which incorporates computer vision and motion sensors allowing players to track their movements in real time and analyze them directly into the competition.
Teams working with machine learning models are optimizing formations, giving the best chance of winning medals at key competitions.
Credit: Google News