algorithms predict sports teams' moves with 80% accuracy
Credit: Cornell University

Algorithms developed in Cornell’s Laboratory for Intelligent Systems and Controls can predict the in-game actions of volleyball players with more than 80% accuracy, and now the lab is collaborating with the Big Red hockey team to expand the research project’s applications.

The algorithms are unique in that they take a holistic approach to action anticipation, combining visual data—for example, where an athlete is located on the court—with information that is more implicit, like an athlete’s specific role on the team.

“Computer vision can interpret visual information such as jersey color and a player’s position or body posture,” said Silvia Ferrari, the John Brancaccio Professor of Mechanical and Aerospace Engineering, who led the research. “We still use that real-time information, but integrate hidden variables such as team strategy and player roles, things we as humans are able to infer because we’re experts at that particular context.”

Ferrari and doctoral students Junyi Dong and Qingze Huo trained the algorithms to infer hidden variables the same way humans gain their sports knowledge—by watching games. The algorithms used machine learning to extract data from videos of volleyball games, and then used that data to help make predictions when shown a new set of games.

The results were published Sept. 22 in the journal ACM Transactions on Intelligent Systems and Technology, and show the algorithms can infer players’ roles—for example, distinguishing a defense-passer from a blocker—with an average accuracy of nearly 85%, and can predict multiple actions over a sequence of up to 44 frames with an average accuracy of more than 80%. The actions included spiking, setting, blocking, digging, running, squatting, falling, standing and jumping.


Algorithms developed in Cornell’s Laboratory for Intelligent Systems and Controls can predict the in-game actions of volleyball players with more than 80% accuracy, and now the lab is collaborating with the Big Red hockey team to expand the research project’s applications. Credit: Ryan Young/Cornell University

Ferrari envisions teams using the algorithms to better prepare for competition by training them with existing game footage of an opponent and using their predictive abilities to practice specific plays and game scenarios.

Ferrari has filed for a patent and is now working with the Big Red men’s hockey team to further develop the software. Using game footage provided by the team, Ferrari and her graduate students, led by Frank Kim, are designing algorithms that autonomously identify players, actions and game scenarios. One goal of the project is to help annotate game film, which is a tedious task when performed manually by team staff members.

“Our program places a major emphasis on video analysis and data technology,” said Ben Russell, director of hockey operations for the Cornell men’s team. “We are constantly looking for ways to evolve as a coaching staff in order to better serve our players. I was very impressed with the research Professor Ferrari and her students have conducted thus far. I believe that this project has the potential to dramatically influence the way teams study and prepare for competition.”

Beyond sports, the ability to anticipate human actions bears great potential for the future of human-machine interaction, according to Ferrari, who said improved software can help autonomous vehicles make better decisions, bring robots and humans closer together in warehouses, and can even make video games more enjoyable by enhancing the computer’s artificial intelligence.

“Humans are not as unpredictable as the machine learning algorithms are making them out to be right now,” said Ferrari, who is also associate dean for cross-campus engineering research, “because if you actually take into account all of the content, all of the contextual clues, and you observe a group of people, you can do a lot better at predicting what they’re going to do.” More information: Junyi Dong et al, A Holistic Approach for Role Inference and Action Anticipation in Human Teams, ACM Transactions on Intelligent Systems and Technology (2022). DOI: 10.1145/3531230 Provided by Cornell University Citation: Algorithms predict sports teams’ moves with 80% accuracy (2022, October 5) retrieved 5 October 2022 from https://techxplore.com/news/2022-10-algorithms-sports-teams-accuracy.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

TECH NEWS RELATED

3D printing can help produce valuable radiopharmaceuticals

Irradiation container placed in the MARIA reactor core. Credit: National Centre for Nuclear Research Without accurate diagnostics, it is difficult to talk about effective treatment of patients, especially in the case of cancer. Today, as much as 80% of diagnostic procedures using radiopharmaceuticals require the use of molybdenum-99. In ...

View more: 3D printing can help produce valuable radiopharmaceuticals

For biodiversity to thrive, conservation efforts must be 'nature and people positive,' experts say

Credit: One Earth (2022). DOI: 10.1016/j.oneear.2022.11.013 In a new expert study published in the journal One Earth, an international team of scientists from the Earth Commission, convened by Future Earth, say that efforts to meet new biodiversity targets and goals for the next three decades risk repeating past failures ...

View more: For biodiversity to thrive, conservation efforts must be 'nature and people positive,' experts say

Biologists make case for guiding conservation with a local touch to fight climate change effects

Mariah Meek of Michigan State University studies the genetics that control brook trouts’ tolerance to heat stress. Credit: Michigan State University As nature reels towards a hotter, drier, harsher future, new conservation tools—seed banks and frozen zoos, gene editing and assisted gene flow—hold promise to help struggling animal and ...

View more: Biologists make case for guiding conservation with a local touch to fight climate change effects

Teachers entering the profession from other fields often less satisfied

Standardized regression weights plotted in the proposed conceptual model. Credit: Teaching and Teacher Education (2022). DOI: 10.1016/j.tate.2022.103942 There is a shortage of teachers not only in Germany, but in many countries around the world. For this reason, people without formal teaching degrees are often brought in from other fields ...

View more: Teachers entering the profession from other fields often less satisfied

EU: Twitter faces fines or shutdown if it does not comply with law

Credit: Pixabay/CC0 Public Domain Twitter can be subjected to fines and other measures if it does not comply with EU law, EU Internal Market Commissioner Thierry Breton has said. “It is absolutely clear that if Twitter does not comply with these rules, we can impose fines. And if the ...

View more: EU: Twitter faces fines or shutdown if it does not comply with law

NASA capsule flies over Apollo landing sites, heads home

NASA’s Orion spacecraft flew past the moon on Monday, December 5, 2022. The crew capsule and its test dummies will aim for a Pacific Ocean splashdown on Sunday, December 11, 2022, off the coast of San Diego after a three-week test flight, setting the stage for astronauts on the ...

View more: NASA capsule flies over Apollo landing sites, heads home

Forest resilience linked with higher mortality risk in western U.S., study finds

Comparison of remotely sensed forest resilience and mortality data over decades, revealing higher resilience associated with higher mortality in western forests vs. higher resilience associated with lower mortality in eastern forests. Credit: Xiaonan Tai/NJIT A forest’s resilience, or ability to absorb environmental disturbances, has long been thought to be ...

View more: Forest resilience linked with higher mortality risk in western U.S., study finds

X-rays reveal elusive chemistry for better electric vehicle batteries

From left to right: Brookhaven chemists Sha Tan and Enyuan Hu with beamline scientist Sanjit Ghose at the NSLS-II X-ray Powder Diffraction (XPD) beamline. The team used XPD to reveal the elusive and complex chemical mechanisms of the interphase in lithium metal batteries. Credit: Brookhaven National Laboratory Researchers around ...

View more: X-rays reveal elusive chemistry for better electric vehicle batteries

Robot helps researchers achieve a new record at the world's deepest cave pit

Elizabeth Holmes appeals Theranos fraud conviction

Wine forecast: Britain could be Chardonnay champions by 2050

Image: Hubble spies emission nebula-star cluster duo

Team develops photon-efficient volumetric imaging method with light-sheet scanning fluorescence microscopy

New manufacturing process produces better, cheaper cathodes for lithium-ion batteries

Feline genetics help pinpoint first-ever domestication of cats

Study finds both habitat quality and biodiversity can impact bee health

The Southern Hemisphere is stormier than the Northern, and we finally know why

Sneaky hackers reverse defense mitigations when detected

Foxconn's main iPhone factory could resume full production in late December

New research shows people, wildlife, and marine environment benefit when island-ocean connections are restored

OTHER TECH NEWS

Top Car News Car News