Introduction to Computer Vision

Published: 08/21/2018  

Last Updated: 08/20/2018

Computer Vision is a fast growing technology being deployed in nearly every industry from factory floors to amusement parks to shopping malls, smart buildings, and smart homes. It is also driving the evolution of machine learning and human interactions with intelligent systems. This increased need for computer vision solutions has helped to drive the development of the Intel® Distribution of OpenVINO™ toolkit.

This SDK brings incredible functionality to developers working on a wide range of solutions. However, if you’re not fully versed in computer vision you may want to explore some of the resources below before diving into the Intel® Distribution of OpenVINO™ toolkit.

Intel® Distribution of OpenVINO™ toolkit

If you wish to engage in a Deep Learning training session that involves both presentation and hands on workshop, we have this option for you as well.

Once you have reviewed these basic resources you should be better prepared to understand and learn more from the Smart Video and Intel® Distribution of OpenVINO™ toolkit.

Please see the below resources for more detail. 



Computer Vision at the Edge     Video that describes the methods of running a computer vision application at the edge using OpenCV.
OpenCV Code Samples These code samples are a good starting point for developers, across a wide range of markets, who wish to develop more robust computer vision and analytic solutions.
Counting People: Use OpenCV for Edge Detection This article explores the counting people using an edge device useful for retail stores, security monitoring, and a variety of other purposes. In this ‘Computing at the Edge’ project, the gateway uses Open Source Computer Vision (OpenCV) to analyze an Internet Protocol (IP) camera web stream to count the number of people crossing the frame.
Machine Learning Intel® AI Academy

Reviewing the types of problems that can be solved including:

Understanding building blocks
Learning the fundamentals of building models in machine learning
Exploring key algorithms

By the end of this course, students will have a firm understanding of:

Supervised learning algorithms
Key concepts like under- and over-fitting, regularization, and cross-validation
How to identify the type of problem to be solved, choose the right algorithm, tune parameters, and validate a model

Deep Learning Intel® AI Academy 

This course provides an introduction to Deep Learning on modern Intel® architecture. Deep Learning has gained significant attention in the industry by achieving state of the art results in computer vision and natural language processing. By the end of this course, students will have a firm understanding of:

Techniques, terminology, and mathematics of deep learning
Fundamental neural network architectures, feedforward networks, convolutional networks, and recurrent networks
How to appropriately build and train these models
Various deep learning applications
How to use pre-trained models for best results

The course is structured around 12 weeks of lectures and exercises. Each week requires three hours to complete. 

Smart Video Workshop Featuring the Intel® Distribution of OpenVINO™ toolkit This workshop will walk you through a computer vision workflow using the latest Intel® technologies and comprehensive toolkits including support for deep learning algorithms that help accelerate smart video applications. You will learn how to optimize and improve performance with and without external accelerators and utilize tools to help you identify the best hardware configuration for your needs. This workshop will also outline the various frameworks and topologies supported by Intel® accelerator tools.
Computer Vision Glossary of Technical Terms This guide is to provide a starting point to understanding some of the terminology used in computer vision and the Intel® Distribution of OpenVINO™ toolkit


Intel® Distribution of OpenVINO™ toolkit

Product and Performance Information


Performance varies by use, configuration and other factors. Learn more at