Embedded Vision Summit is an annual industry conference focussed on computer vision and machine learning for embedded devices.
This year it will be held in Santa Clara, California between May 20-23. The keynote speakers talking at the conference are Dr. Ramesh Raskar, Associate Professor at MIT Media Labs, and Pete Warden, Staff Research Engineer at Google.
It is an exciting conference with 100+ speakers from different industries and about 1200 attendees.
For the past several years organizers of this conference have invited members of the OpenCV Foundation to give talks because OpenCV is the most popular computer vision library in the world and is widely used in embedded systems.
The following two events in the conference will be of special interest to the OpenCV community
1. OpenCV: Current Status and Future Plans [Talk]
Wednesday, May 22, 12:55 PM – 1:25 PM
In this talk, Dr. Satya Mallick (Interim CEO, OpenCV.org) will provide a technical update on OpenCV: What’s new in OpenCV 4.0? What is the Graph API? Why are we so excited about the Deep Neural Network (DNN) module in OpenCV? (Short answer: It is one of the fastest inference engines on the CPU.)
We will also share plans for the future of OpenCV, including new algorithms that we plan to add through the Google Summer of Code this year.
We will also briefly share info on the new Open Source Vision Foundation (OSVF), and on OpenCV’s sister organizations, CARLA and Open3D, and some of the initiatives planned by these organizations.
2. Computer Vision Applications with OpenCV [ Full day training ]
Monday, May 20, 2019 from 9:00 am to 5:00 pm
In this day-long training course, we will start with the basics of OpenCV, the world’s most popular open source computer vision library. We will learn many algorithms implemented in OpenCV and how they are used to build real-world applications like image classification, object detection, face recognition, and many more.
This is a workshop for engineers and programmers. We will learn enough theory to understand the ideas behind the algorithms, but we will not drown ourselves in complex mathematical equations.
Pre-Requisites
The workshop is designed for beginners in mind. The only pre-requisite is an intermediate level of knowledge in Python3. If you are rusty on Python, check python.org/3/tutorial/.
No knowledge of computer vision, machine learning, or Al is required.
I hope to have the chance to assist Embedded Vision Summit this year!