Sensors embedded in sports equipment could deliver real-time analytics to your smartphone – sciencedaily


Sports analysis – tracking how fast the ball is moving or how players move on the pitch – is becoming a key part of how coaches make decisions and how fans view games. The data for these analyzes currently comes from cameras in stadiums and courts and is incredibly expensive to acquire.

In an effort to make big data analytics more accessible for the sports industry, researchers at the University of Illinois at Urbana-Champaign used IoT devices – low-cost sensors and radios – that can be integrated into sports equipment (eg balls, rackets and shoes), as well as portable devices.

“There is a lot of interest in analyzing sports data through high speed cameras, but a system can cost up to $ 1 million to implement and maintain. It is only accessible to big clubs, ”said Mahanth Gowda, PhD student in computer science and lead author of the“ Bringing IoT to Sports Analytics ”study. “We want to dramatically reduce expenses by replacing cameras with inexpensive IoT devices (costing less than $ 100 in total) to allow many other organizations to use the technology.”

The team – led by Romit Roy Choudhury, associate professor of electrical and computer engineering and computer science in Illinois, together with Sharon Yang of Intel – developed advanced motion tracking algorithms from the various incomplete measurements. and noisy inertial measurement unit (IMU) sensors and wireless radios, installed inside a ball and players’ shoes. If technology gains traction, real-time analysis should be possible anytime, anywhere.

The tiny sensors, which are wrapped in a protective case and evenly distributed throughout the equipment, use inference algorithms that can track movements to within centimeters. They can accurately characterize the movement of the ball in 3D, such as trajectory, orientation and revolutions per second.

“This level of accuracy and accessibility could help players at local clubs read their own performances from their smartphones via Bluetooth, or school coaches could offer quantifiable feedback to their students,” said Roy Choudhury, who is also a research professor at Illinois’ Coordinated Science. Laboratory. The feedback could also help detect and analyze player injuries, such as concussions. The sensor inside a soccer ball, for example, can measure the force with which it hits a player’s head, giving coaches an indication as to whether to treat the player for an injury. the head.

“We have really scratched the surface of applications with these sensors. The algorithms provide extremely fine detail and precision in measurements, but use common measurement tools that can be found in any smartphone,” said Gowda.

The article, which will be published in USENIX NSDI 2017, explores tracking the 3D trajectory and spin parameters of a cricket ball; However, the main techniques for tracking movement can be generalized to many different sports analyzes.

The team, made up of students Ashutosh Dhekne, Sheng Shen, and other Intel collaborators, also developed methods to charge the sensors, including recovering energy from the spinning of the ball.

“We are motivated to develop this technology to help coaches make better decisions on and off the field and to provide better entertainment for viewers,” said Roy Choudhury. “We want to bring advanced yet affordable sports analytics to anyone, anywhere, anytime.”

Find the report at: http://synrg.csl.illinois.edu/papers/cricket-nsdi-2017.pdf


Comments are closed.