Fitness Carter: Seattle computer scientists perfect yoga instruction

About Linda

Linda is the morning news anchor and features reporter for KIRO Radio. This is her local news blog, with an emphasis on social media, technology, Northwest companies, education, parenting, and anything else that grabs her attention.

If you have a news tip or story idea, I'd love to hear from you... ^[1]

To leave a voice message for Linda about any of her stories call toll free 1-855-251-2363

Instructor Michelle Demus demonstrates a yoga pose. Go ahead, try it. For the rest of us who are downward-facing-dog-challenged, three UW computer scientists have perfected yoga instruction for the privacy of your home. (AP/Heuichul Kim photo)

October 28, 2013 @ 5:10 pm (Updated: 6:47 pm - 10/28/13 ) There are two kinds of people in the world - those who look amazing doing any yoga pose, and everybody else.

Based on my general lack of sports ability and patience, I assume yoga isn't for me. The one time I attempted a yoga class an instructor asked me to leave.(That could be because I didn't turn off my laptop when asked. I only had a paragraph to finish on a story. Enough said).

For those of us who are downward-facing-dog-challenged, three University of Washington computer scientists have perfected yoga instruction.

They've created a software program that watches a user's movements and gives spoken feedback on what to change to accurately complete a yoga pose.

The program, called Eyes-Free Yoga,^[2] uses Microsoft Kinect software to track body movements and offer audio feedback in real time for six standard yoga poses, including Warrior I and II, Tree and Chair poses.

It gives verbal feedback on how a person should adjust his or her arms, legs, neck or back to complete the pose. For example, the Siri-sounding instructor might say: "Rotate your shoulders left," or "Lean sideways toward your right."

Each of the six poses has about 30 different commands for improvement based on a dozen rules deemed essential for each yoga position.

The UW team, lead by Kyle Rector, worked with a number of yoga instructors in the Seattle area to put together the criteria for reaching the correct alignment in each pose.

The Kinect first checks a person's core and suggests alignment changes, then moves to the head and neck area, and finally the arms and legs. It also gives positive feedback when a person is holding a pose correctly. Color-coded image shows the order of priority for correcting a person's alignment.

While the program could help people who doing feel comfortable going to even a beginning yoga class, it's really designed to be beneficial to people who are blind.

Rector worked with 16 blind and low-vision people around Washington to test the program and get feedback.

By LINDA THOMAS

ATTENTION COMMENTERS: We've changed our comments, but want to keep you in the conversation.

Please login below with your Facebook, Twitter, Google+ or Disqus account. Existing MyNorthwest account holders will need to create a new Disqus account or use one of the social logins provided below. Thank you.