Frank Brill, Design Engineering Director at Cadence and Chairperson of the Khronos Group's OpenVX Working Group, presents the "OpenVX Computer Vision Library Standard for Portable, Efficient Code" tutorial at the May 2017 Embedded Vision Summit.
OpenVX is an industry-standard computer vision API designed for efficient implementation on a variety of embedded platforms. The API incorporates the concept of a dataflow graph, which enables implementers to apply a range of optimizations appropriate to their architectures, such as image tiling and kernel fusion. Application developers can use this API to create high-performance computer vision applications quickly, without having to perform complex device-specific optimizations for data management and kernel execution, since these optimizations are handled by the OpenVX implementation provided by the processor vendor. This talk describes the current status of OpenVX, with particular focus on the most recent enhancements to it, including a neural network extension. The talk concludes with summary of the currently available implementations and an overview of the roadmap for the OpenVX API and its implementations.