The Khronos Group ratified and publicly released the final OpenVX 1.0 specification standards for cross platform acceleration of computer vision applications.
Image processing otherwise also called vision analytics is being increasingly used in wide range of applications in video surveillance, automated car driving such as driver assistance systems (ADAS), machine vision, object recognition, scene reconstruction, augmented reality, and in robots.
The standards such as these are designed to help vision processing software to work across platforms and systems.
Khronos has also developed a full set of conformance tests and an Adopters Program, that enables implementers to test their implementations and use the OpenVX trademark if conformant.
Khronos said it plans to ship an open source, fully-conformant CPU-based implementation of OpenVX 1.0 before the end of 2014. The full OpenVX 1.0 specification and details about the OpenVX Adopters Program are available at www.khronos.org/openvx.
“Increasingly powerful and efficient processors and image sensors are enabling engineers to incorporate visual intelligence into a wide range of systems and applications,” said Jeff Bier, founder of the Embedded Vision Alliance. “A key challenge for engineers is efficiently mapping complex algorithms onto the processor best suited to the application. OpenVX is an important step towards easing this challenge.”
OpenVX complements OpenCV open source vision library that is also used for application prototyping but is not so tightly defined and lacks OpenVX graph optimizations. Khronos said it has defined the VXU utility library to enable developers to call individual OpenVX nodes as standalone functions for efficient code migration from traditional vision libraries such as OpenCV.
OpenVX is extensible to enable nodes to be defined and deployed to meet customer needs, ahead of being integrated into the core specification.