Real-time Analytics
TRACAB needed more scalable compute and lower-latency data delivery for computer-vision sports tracking as its features became more complex and its on-premises arena-based setup limited deployment speed and accuracy.
Reported impact
TRACAB increased collected data to more than 255 million data points per match, achieved average latency of 0.85 seconds, reduced manual work by shifting from two onsite operators to one remote operator, and expanded to nearly 200 stadiums running more than 2,000 matches per year.
TRACAB migrated its sports-tracking platform from on-premises arena servers to AWS so it could scale computer-vision processing and deliver richer match insights in near real time. Video and tracking data from multiple cameras is sent to AWS, where deep-learning models run on Amazon EC2 G4, G5, and G6 GPU instances to identify players, the ball, and new skeleton-tracking signals. Low-latency state and event access is supported by Amazon ElastiCache for Redis and Amazon DynamoDB, letting downstream consumers such as broadcast teams, referees, coaches, and fans use the data quickly. The cloud architecture also let TRACAB automate work that once required two onsite operators, support a remote operator model, and continuously deploy new features such as semi-automated offside technology and virtual cameras across nearly 200 stadiums.
Multi-camera match video and tracking data is streamed to AWS, processed by deep-learning models on GPU-backed Amazon EC2 instances, stored for low-latency access in Amazon DynamoDB and Amazon ElastiCache for Redis, and then delivered as near-real-time insights to broadcasters, officials, coaches, players, and fans.
By sending tracking data to the cloud, TRACAB could use AI powered by advanced deep learning models on AWS to perform the task with a single remote operator.
TRACAB can collect more than 255 million data points per match while achieving an average latency of 0.85 seconds.
TRACAB has rolled out its solution to nearly 200 stadiums, which collectively run more than 2,000 matches per year.
TRACAB next enhanced its solution in 2023 with near real-time skeleton tracking.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
The public company page lists 'Total employees' as '75' and 'Country' as 'Sweden'.
Related
AWS Sample Est. · Dec 18, 2025 Pinterest Pinterest needed to scale AI-powered visual discovery to 600 million monthly active users while keeping the platform a positive, trusted, and safe experience differentiated from competitors who optimize for viral… 10 million AI-powered recommendations per second Amazon Bedrock · Amazon EC2 · Amazon EC2 G5 instances AWS Sample Oct 1, 2024 Swimming Australia To maintain its legacy on the world stage, Swimming Australia sought to transform the vast amounts of raw performance data it had on its athletes into actionable, real-time insights. Amazon QuickSight · Amazon SageMaker AWS Sample Jul 1, 2024 NAGRA Using AWS and services such as Amazon Bedrock means both faster development of new services and features, and the ability to ramp up to meet demand. “Working with AWS gives us the certainty that we’re able to scale to… Its customers include content providers, pay-TV operators, and telcos, who choose NAGRA to protect their… Amazon Bedrock · Anthropic Claude 