Video Stabilization Software from SRI Embedded into Chat Applications
MENLO PARK, Calif. - July 7, 2011 - As tablets allow users to connect with the world, there is increasing demand for new features that match our fast-paced lifestyle. With video chats becoming more common, people want the option to "walk and talk." Yet, picture quality and the viewer experience can be poor. When people are moving and talking during a video chat, the transmitted images can appear shaky and hard to watch.
Now, for the first time, tablet users have access to SRI's 2D video stabilization software, which has been embedded into Google Talk™ applications and is available on Android™ 3.0+ devices.
"Google has selected SRI technology for stabilizing video chats and conferences on Google Talk, making video conversations with a stable picture an anytime, anywhere experience for tablet users," said Norman Winarsky, Ph.D., vice president, SRI Ventures. "As leaders in vision and video research, we continue to enhance consumers' positive user experience. This mobile device innovation is a reflection of SRI's strategic research and development, focused on meeting important market needs."
Video technology researchers at SRI Sarnoff began working on the stabilization problem in the early 1990s, when they developed a way to electronically stabilize and enhance surveillance videos. Their seminal work in motion estimation led to the development of 2D video stabilization software that compensates for motion in a scene by eliminating it and keeping a person's face as the central focus. This patented technology provided the mathematical foundation for SRI Sarnoff's Acadia family of vision products, used in security, surveillance, and car safety applications.
How 2D Video Stabilization Works
Video chat applications capture video from the front-facing camera on smartphones and tablets. Once an image is acquired by a camera, it is compressed before it can be transmitted. In video compression algorithms, the bandwidth used to encode the video increases with the amount of motion in the scene.
By stabilizing the video, SRI's software compensates for scene motion and allows the video compression algorithm to improve image quality by using fewer bits to encode the video. There is increased mobile device efficiency when an image is stabilized before compression, and there is less work for a device's video compression engine to perform.