Sensor-Driven Tripod for Recording Athlete Data
The StarTT project STRADA is a tool that collects, analyses and learns from sports data. The aim is to capture available data streams, such as heart rate monitors, video streams, and lap times in real-time and use all these data streams to automatically detect highlights during training or competition, e.g., an attack of your favorite rider in track cycling, an overtake in short track speed skating, …
The framework generates short, personalized video clips that might attract the broader attention of sports fans and broadcasting companies.
The STRADA project build further on previous projects:
- A Wireless Cycling Network (WCN) has been set up where sensor data from heart rate monitors, cadence meters, and power meters are collected in real-time using WASP devices
- In the PACE IOF project, sensor data is fed to a model determining the remaining energy level of a cyclist based on critical power and the power produced during exercise to avoid exhaustion. This model has already been coupled successfully to the sensor data streams of the WCN project for real-time feedback and shows the potential of a data- driven approach.
- Several algorithms for video analysis for human pose estimation has been studied in the (imec.icon) DAIQUIRI project and can help to determine the position and pose of people (athletes) in view of the camera.
- Camera calibration, motion detection and 3D human pose estimation in low-latency applications have been investigated. The work presented several applications in behavior analysis and human movement analysis.
- Generation of personalized video clips triggered by real-time sensor data. The novelty of producing sensor-driven video clips offers many opportunities for fan engagement in a more personalized interactive form of digital sports experience.
- STRADA incorporates sensor data, which allows to work faster, more accurately and at lower computational cost/requirements. This smart technology increases efficiency/quality of media production, storage, distribution and value creation.
- The technology can also be used in smaller events and permanent settings so that amateur sports enthusiasts can also taste the personalized experience by themselves.
- The inclusion of real-time sensor data of athletes and external sensors creates a richer context in which video clips can be even more personalized by using specific personal sensor metrics.
- Data streams
Capture available data streams, such as heart rate monitors, video streams, and lap times in real-time.
- Detecting highlights
Use all the data streams to automatically detect highlights during training or competition, e.g., an attack of your favorite rider in track cycling, an overtake in short track speed skating, …
- Engagement sports fans
STRADA is the answer to keep sports fans engaged in a time where on-demand information has become mainstream, and viewers are often saturated with an abundance of long live race coverage.
Prof. Dr. Steven Verstockt
Contact us for more information about this project