Subscribe to RSS Add to Technorati Faves Digg This Page Send to Stumble Upon Bookmark on Delicious

"Automated sports highlights" demo video

posted by Sean Koehl on March 17, 2008

I wanted to share a video of some of the application research we have going on at our Intel China Research Center in the area of video mining. In collaboration with Tsinghua University, Yimin Zhang and his team at ICRC are trying to create improved computer vision algorithms for use on future multi-core hardware. The idea is to allow computers to recognize content in professional or user-generated video so that one can automatically edit (or at least pre-edit) to isolate only the most interesting parts of the video.

In this video you’ll see that the target application in this case is extracting video highlights in a soccer game. Many people can relate to having hours of sports video stored up on their DVRs, especially during a playoff season. You might not actually have the time to watch the all the footage (especially if you’ve already heard the outcome), but you might want to see the highlights — just the players and events that interest you most.

The video has three segments. The first shows the basic capability to recognize some of the features in the game — a player, ball, a goal post, etc. The more cores you have, the more complex the features you can recognize in a reasonable amount of time.

The second segment shows a scalability demo — a “bake-off” between a 1-core an 8-core processor. This was done to show that video analysis is truly a parallel application. The graph at the end shows that the more cores you have the better performance you get.

The final segment is a concept application — a future DVR with the capability to pick scenes from a game depending on what happened.

The idea is to be able to do this on any match video — professional or home brewed (in this case some Intel researchers playing around) without having to manually pre-tag the data. It’s one of the capabilities we’re trying to enable through tera-scale research. In fact, Yimin and team will be presenting the latest results on this and related video mining work at the Intel Developer Forum in Shanghai in just a few weeks.

Comments (1)
del.icio.us StumbleUpon Digg It
tagged: , , , , ,

Comments

Mar 17  |  Brad Fortner said:

It’s great to see that this research is continuing and I never really thought about how multicore could speed this process up.

I’m wondering when this gets tied together with the announcers voice (via voice recognition or closed captioning) so things like goals, penalties etc. can be clearly delineated.

It’s great to see how the mining software can detect the individual players and it can probably identify many of the predictable situations. But sports is always about the unpredictable and tying voice or caption assistance to the mining might make the process much richer.

….brad…. www.bradfortner.com

Post Your Comment




Comment Policy: We welcome your comments, however all comments are moderated. Offensive, off-topic or fraudulent comments will be deleted and not displayed. By submitting a comment to an Intel Blog, you agree to our legal information and privacy policy terms, including having your name displayed with your comment and that you are 13 years old or older. Your name and personal information will not be used for any other purpose, and your e-mail address will not be published.

Disclaimer: Opinions expressed here and in any corresponding comments are the personal opinions of the original authors, and do not necessarily reflect the views of Intel. All Intel names and trademarks are the property of Intel Corporation or its subsidiaries in the United States and other countries. Other names and brands may be claimed as the property of others.