OpenVX Overview

OpenVX Resources

A collection of OpenVX related tools, documentation, and resources contributed by the community. To contribute, create a pull request to add new resource or update/delete an out of date resource. This resource page lives on GitHub and is open for anyone to issue pull requests to.

Khronos Resources

Commercial and Open Source Implementations

  • AMD OpenVX (AMDOVX) (open-source on GitHub) is a highly optimized implementation of the Khronos OpenVX™ computer vision specification. It is a library that allows for rapid prototyping as well as fast execution on a wide range of computer hardware, including small embedded x86 CPUs and large workstation discrete GPUs. On GitHub: core (OpenVX) and modules (Libraries)
  • Cadence -  Tensilica Vision DSPs for Imaging, Computer Vision, and Neural Networks and the Tensilica OpenVX Application Programming Kit (APK).
  • Imagination - PowerVR GPUs From Imagination pass OpenVX Conformance
  • Synopsys - High-Performance, Energy-Efficient Vision Processors
  • Texas Instruments’ OpenVX (TIOVX) framework and optimized software libraries accelerate and simplify development for automotive applications using TI’s efficient, heterogeneous Jacinto™ ADAS SoCs.
  • VisionWorks - NVIDIA VisionWorks toolkit is a software development package for computer vision (CV) and image processing. VisionWorks™ implements and extends the Khronos OpenVX standard, and it is optimized for CUDA-capable GPUs and SOCs enabling developers to realize CV applications on a scalable and flexible platform.

Frameworks & Libraries

  • AMD OpenVX (open-source on GitHub) is a highly optimized implementation of the Khronos OpenVX™ computer vision specification. It is a library that allows for rapid prototyping as well as fast execution on a wide range of computer hardware, including small embedded x86 CPUs and large workstation discrete GPUs. On Github: core (OpenVX) and modules (Libraries)
  • OpenVINO (The OpenVINO toolkit was formerly known as the Intel Computer Vision SDK) Develop applications and solutions that emulate human vision with the Open Visual Inference & Neural Network Optimization (OpenVINO) toolkit. Based on convolutional neural networks (CNN), the toolkit extends workloads across Intel® hardware and maximizes performance.
  • Texas Instruments’ OpenVX (TIOVX) framework and optimized software libraries accelerate and simplify development for automotive applications using TI’s efficient, heterogeneous Jacinto™ ADAS SoCs.

Tutorials