Application for Teaching Sports Technique

A new way to learn golf, track and field, and football

Project Background

Our client has a Ph.D in Biomechanics and is a former professional athlete, an Olympic silver prize winner. He developed an algorithm that constructs custom stick-figure models with precise body parameters to represent an athlete’s optimal performance.

Sibers was asked to transform the algorithm into a golf application, and in a second phase adapt it for a track and field and a football teaching application.

One year after development, the application was successfully used to win an Olympic gold medal and set a new world record.

Solution

The Sibers team developed a video analysis system that processes human motion data. Two 60fps synchronized cameras, one placed behind the athlete and one to the side, film the athlete’s movements and transmit the data for analysis.

While researching golf swing mechanics, hundreds of videos of top golfers were analyzed. Their swings were subsequently digitized, and each body part was tracked for its individual movement.

The application employs statistics to evaluate the maximum possible effort for each body part, resulting in a representation of how the user’s performance compares to that of an elite player. The user’s personalized model is then overlaid on an elite player’s video, showing all the posture errors the user makes during his swing.

The model is so sophisticated that it can consider factors such as club type (wood, iron, hybrid), preset swing speed and the athlete’s physique.

Every recording can be sent to a web repository, where it’s available for immediate review. A teacher can add his/her voice to the recording, providing feedback and suggestions.

Tech highlights

  • ManageIt
  • C#
  • .NET Framework
  • DirectShow
  • Visual Studio
  • VSS
  • Turbine Video Engine SDK
  • HyCam2
  • C++
  • Managed C++
  • BayerConvert
  • FrameDropper
  • MP4Splitter
  • TimeStampSaver
  • wavdes
  • Allied Vision Technologies Convert/DirectStream/Interop
  • DirectShowLib + DirectShowLibUtils
  • Microsoft.Office.Interop
  • Payflow.NET
  • Turbine.TVE

Cameras supported:

  • AVT Marlin
  • PTGrey Flea2
  • AVT Stringray

Adapters used for camera connection:

  • FireRepeater 800™
  • Belkin FireWire 800 ExpressCard™

Results

The solution, based on biomechanical principles, data mining, and statistics, provides athletes with a uniquely effective training tool that is now used in more than 70 sports facilities worldwide.

And in more good news, the training application was featured in The Washington Post, which wondered if the technology could help win an Olympic gold. It not only did just that, but also helped set a new world record!

Customer Says

Sibers has been instrumental in helping us develop our Sports based video analysis system. We have been working together for over a year and they have demonstrated excellent development skills in a complex, evolving project. In addition, their attention to customer service and satisfaction has been very welcome. I give them an excellent overall rating. (September 2008)

Dr. Ralph Mann — President at SwingModel LLC

Similar case studies

Set-Top Box and TV Content Delivery Applications

Toronto, ON, Canada

Our client, a globally-active Internet and TV provider, offering channels packages for US, Canadian, European and Asian audience. He asked Sibers to build several digital tools for content delivery to end-users, as well as facilitate discovery.

Case study in details

History Educational Application

Copenhagen, Denmark

Currently selling in the App Store, this iPad application was a good investment for its founders, having generated popularity amongst students and casual American history fans alike.

Case study in details

Connexiti: A Massive Financial Analysis System

Atlanta, GA, USA

Connexiti is a massive financial analysis system that Sibers developed for a client which has since been acquired by Bloomberg L.P. The Connexiti platform allows its users to create customized portfolios, organize and upload company models and research, and filter and tag relevant news articles from thousands of global sources. This helps investors better understand money flows between companies on a global basis and make predictive stock calls.

Case study in details