OpenVL is the future of developer-friendly computer vision - existing vision frameworks provide access at a very low level, such as individual algorithm names (often named after their inventor), while OpenVL provides a higher-level abstraction to hide the details of sophisticated vision techniques: developers use a task-centred API to supply a description of the problem, and OpenVL interprets the description and provides a solution.

The OpenVL computer vision abstraction will support hardware acceleration and multiple platforms (mobile, cloud, desktop, console), and therefore also allows vendor-specific implementations. We are committed to making it an open API available to everyone (and hope to make it an open standard); Continue reading...
Face Front
Face Profile

Gregor Miller and Sidney Fels

AMD Fusion Developer Summit (AFDS2012)
Bellevue, Washington, U.S.A., 11th-14th June 2012

Current computer vision frameworks present APIs as lists of specific methods, which requires deep algorithmic knowledge to apply effectively in the real world. We present OpenVL, a high-level abstraction with a task-based interface which does not require extensive knowledge of or experience with vision methods. Instead we require developers to have enough knowledge of a task to accurately describe it using our interface. The description is analysed and used to invoke the appropriate algorithm and provide a solution. The underlying implementation can be optimised on combinations of CPU and GPU. The OpenVL model can describe many tasks, such as segmentation, correspondence, registration, detection, optical flow and tracking, and we will present working examples for each. We believe the adoption of the developer-friendly OpenVL interface and AMD hardware for acceleration will dramatically increase the application of computer vision technology by developers.

We will be demonstrating the latest version of OpenVL at the Summit: if you would like to see the demos or take a look at the code/interface/API, please get in touch!