Hilton Head, S.C. — (press release) — Intel Corporation's Microprocessor Research Lab today announced that it is working with a group of computer vision technology researchers to release a new computer vision library and its source code. The computer vision library will provide a wide range of functions, including gesture recognition, object-tracking, face recognition and camera calibration, that will… help researchers develop ways to use “computer vision” as a method for people to interact with computers. The announcement took place at the opening of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).

“We believe that the open source availability of this library will accelerate computer vision research and ultimately hasten the day when computer vision can be used in consumer products,” said Fred Pollack, Director of Intel's Microprocessor Research Lab. “Working with academia has allowed us to consolidate the best known computer vision technology and the latest research into this software library.”

Profound Changes in Human-Computer Interaction at Work, at Home Faster microprocessors, falling camera prices and ten times more video capture bandwidth from technologies like USB 2 are all enabling real-time computer vision algorithms to run on standard PCs. The emergence of computer vision on the PC, in conjunction with new larger wall-mounted displays will profoundly change the way people interact with computers.

Computer vision has already started to receive attention from researchers in advanced home applications. Once a home is “aware” of who you are and where you are, it can provide relevant information and device control wherever you are in the home.

“The open source computer vision library is one of the first steps toward ubiquitous video processing,” said Dr. Irfan Essa, professor of computer science at Georgia Tech. “We believe this software library will provide the infrastructure for processing input from hundreds of cameras in the Georgia Tech Aware Home project.”

Similar advances can be expected in the work environment.

“When the walls of your office become displays, a mouse won't do for navigating from the wall in front of you to the one behind you,” said Mark Holler, manager, Intel Microprocessor Research Lab. “A 'visually aware' office will know which way you are looking and put the cursor where you need it. Hand gestures will open, close and move objects around.”

While this library is intended to encourage research, some of the functions may have immediate value. For example, the camera calibration functions in the software library will allow the use of a wide angle lens to capture a large field of view and correct for the lens distortion that produces unflattering large noses in video conferencing.

Building the Computer Vision Research Community

Intel will facilitate the growth and maintenance of this library by accepting and maintaining submissions of source code content reviewed by a panel of experts from the computer vision community. Reviewers will include representatives from major vision laboratories including:

Jitendra Malik, University of California Berkeley,
Takeo Kanade, Carnegie Melon University,
Pietro Perona, California Institute of Technology,
Irfan Essa, Georgia Institute of Technology,
Carlo Tomasi, Stanford University and
Trevor Darell, Massachusetts Institute of Technology

This open source software release includes C source code for all of the library's functionality and a royalty free redistribution license. The source code was developed and debugged in the Windows(1) environment. A version of the library for the Linux operating system will be released before the end of the year.

Intel's Microprocessor Research Laboratories are the leading developer of microprocessor technology. Its international research facilities are working on various areas including microprocessors (circuits, architecture, compilers, etc.), platform architecture (buses, caches, memory, interconnect, etc.) and core human interface (speech, natural language processing, video, vision, graphics, new devices, etc.).

 
This article was originally published on LinuxDevices.com and has been donated to the open source community by QuinStreet Inc. Please visit LinuxToday.com for up-to-date news and articles about Linux and open source.