Presented By O’Reilly and Intel AI
Put AI to work
8-9 Oct 2018: Training
9-11 Oct 2018: Tutorials & Conference
London, UK

Enabling traditional vision on specialized deep learning hardware

Paul Brasnett (Imagination Technologies )
16:00–16:40 Thursday, 11 October 2018
Models and Methods
Location: King's Suite - Sandringham
Secondary topics:  Computer Vision, Edge computing and Hardware, Platforms and infrastructure

Who is this presentation for?

  • AI system developers

Prerequisite knowledge

  • A basic understanding of machine learning and deep neural networks

What you'll learn

  • Learn methods for adapting classical vision algorithms to become trainable DNNs

Description

Over the past several decades, the industry has invested heavily in traditional vision algorithms. However, in the past few years, there’s been a major shift from traditional vision algorithms to deep neural network algorithms. While many companies expect to move to deep learning for some or all of their algorithms, they may already have a significant investment in classical vision and likely want to continue to use classical vision algorithms for specific tasks. After all, they don’t want to lose their investment.

When specifying silicon for next-generation products, companies must consider whether to prioritize the hardware needed to support the traditional vision algorithms that they have today or that needed for deep neural network algorithms in the future. There is an increased cost to optimize for both. However, if some of the traditional algorithms can run on deep learning optimized hardware, more area could be allocated for the deep learning hardware.

Paul Brasnett discusses how a company can maximize its existing investment in traditional algorithms while building toward deep learning algorithms. Paul examines the similarities between classical and deep vision and explains how to express and adapt a classical vision algorithm to become a trainable DNN. Along the way, Paul demonstrates how traditional computer vision algorithms (e.g., histograms and morphological operators) can be mapped on to deep learning primitives and explores a case study on mapping a feature point descriptor called Brisk. This enables traditional vision on specialized deep learning hardware, ultimately providing a low-risk path for developers transitioning from traditional vision algorithms to DNN-based approaches and enabling them to maximize their investments.

Photo of Paul Brasnett

Paul Brasnett

Imagination Technologies

Paul Brasnett is a principal research engineer leading a team responsible for imaging, image processing, and computer vision algorithms within the PowerVR Division of Imagination Technologies. Previously, he was a senior research engineer at Mitsubishi Electric, where he was involved in image and video processing and participated in MPEG standardization work. Paul holds a PhD and MEng from the University of Bristol, UK.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)