Develop Multiplatform Computer Vision Solutions

Explore the Intel® Distribution of OpenVINO™ toolkit

Make your vision a reality on Intel® platforms—from smart cameras and video surveillance to robotics, transportation, and more.

Your Computer Vision Apps...Now Faster

Develop applications and solutions that emulate human vision with the Intel® Distribution of OpenVINO™ toolkit. Based on convolutional neural networks (CNN), the toolkit extends workloads across Intel® hardware (including accelerators) and maximizes performance.

  • Enables CNN-based deep learning inference on the edge
  • Supports heterogeneous execution across computer vision accelerators—CPU, GPU, Intel® Movidius™ Neural Compute Stick, and FPGA—using a common API
  • Speeds time to market via a library of functions and preoptimized kernels
  • Includes optimized calls for OpenCV and OpenVX*

Get Started

Discover the Capabilities

Deep Learning for Computer Vision

Accelerate and deploy CNNs on Intel® platforms with the Intel® Deep Learning Deployment Toolkit (Intel® DLDT) that's available in the Intel Distribution of OpenVINO toolkit.

Hardware Acceleration

Harness the performance of Intel®-based accelerators: CPUs, GPUs, FPGAs, VPUs, and IPUs.

Who Needs This Product

Software developers and data scientists who:

  • Work on computer vision, neural network inference, and deep learning deployment capabilities
  • Want to accelerate their solutions across multiple platforms, including CPU, GPU, VPU, and FPGA


Medical Imaging, Powered by AI

Intel teamed up with Philips to show that servers powered by Intel® Xeon® Scalable processors and the Intel® Distribution of OpenVINO™ toolkit could be used to efficiently perform deep learning inference on patients’ X-rays and computed tomography (CT) scans, without the need for accelerators.

What's New in the 2018 R4 Release

Supported Hardware

  • Intel® Vision Accelerator Design with Intel® Arria® 10 FPGA (preview) is a PCIe add-in card that can be used with other Intel® processors. This card supports multiple video streams, boosts high performance, provides low power consumption, and runs at low-latency.
    More Information
  • The Intel® Neural Compute Stick (Intel® NCS) 2 is a deep learning USB device for easy testing, tuning and prototyping inference applications on edge devices. Based on Intel® Movidius™ Myriad™ X VPU, it includes a DNN inference hardware accelerator for increased performance.
    More Information
  • Intel Distribution of OpenVINO toolkit is now the default SDK for Intel® NCS 2. To smoothly transition from NCSDK to this toolkit, see the tutorial.

Deep Learning Enhancements

  • A low precision, 8-bit integer (Int8) inference is a preview feature for Intel CPUs to achieve optimized runs. A calibration tool with built-in samples saves calibrated intermediate representation (IR) files with embedded statistics on the Int8 profile.
  • TensorFlow*, MXNet*, and ONNX* operations have enhanced support. Popular TensorFlow topologies such as the region-based fully convolutional network (R-FCN), Yolo version 3, and OpenPose help with deployment across Intel platforms.
  • Three pretrained models to build compelling features in vision applications: facial landmarks, human pose estimation, and image super resolution.

Traditional Computer Vision Updates

  • The toolkit includes OpenCV version 4.0 and supports the Graph API module for optimized image processing functions.
  • The code base default is now the C++11 standard.

Release Notes

Product Brief

System Requirements

Case Studies

Intel and GE* brought the power of AI to clinical diagnostic scanning and other healthcare workflows.

GeoVision sped up its facial recognition solution using Intel® System Studio and the Intel Distribution of OpenVINO toolkit.

This toolkit is the centerpiece of Agent Vi*, which provides next-generation vision technology.

NexCOBOT offers a flexible, modular robotics solution that integrates AI with machine vision using tools from Intel.

Open-Source Software

The OpenVINO™ toolkit is available as an open-source product. This version contains the Deep Learning Deployment Toolkit (DLDT) for Intel® processors (for CPUs), Intel® Processor Graphics (for GPUs), and heterogeneous support. It includes an open model zoo with pretrained models, samples, and demos.

OpenVINO™ Toolkit

GitHub* for DLDT

GitHub for an Open Model Zoo