Online Embedded Vision Sessions: Navigating Intelligent Vision at the Edge

In these online sessions, learn about the latest trends in artificial intelligence and computer vision and how to use embedded vision technologies to navigate from concept to successful silicon. You'll get a deep dive into deep learning, embedded vision, and standards-based programming for automotive, mobile, surveillance, and consumer applications.

Below you'll find a few minutes of the sessions to preview, then you can register to watch the full videos.



Dr. Robert Laganiere, Professor, University of Ottawa & Founder & Chief Science Officer at Sensor Cortek & Tempo Analytics

Solving Computer Vision Problems Using Traditional and Neural Network Approaches
Dr. Laganiere describes current trends in deep learning and neural networks and compares them to more conventional vision algorithms. He describes recent approaches for the detection and tracking of objects of interest in the context of autonomous driving and smart visual surveillance.


Tom Michiels, System Architect, Embedded Vision, Synopsys

Architecture and Design Techniques for Embedded Deep Learning 

Embedding deep learning at the edge is challenging due to the huge computational and memory requirements and the algorithmic diversity of modern vision and sensing tasks. Tom describes the techniques Synopsys uses to enable embedded deep learning in its DesignWare EV6x Embedded Vision Processor IP. 


Dr. Bert Moons, Hardware Design Architect, Embedded Vision, Synopsys

Emerging Neural Network Topologies for Vision Applications

Real-life vision systems in VR, AR, autonomous vehicles and industrial automation require real-time understanding of their surroundings. Dr. Moons focuses on novel scene, instance, and panoptic segmentation algorithms emerging into the marketplace, and challenges of implementing the different types of algorithms.


Mike Borza, Principal Security Technologist, Synopsys

What You Don’t Know Can Hurt You: Security 101 for Embedded Vision

ML, AI, and embedded vision are commonly used for biometrics, automotive, healthcare and other sensitive applications. As they emerge, hackers wonder: How can I take control? Mike provides case studies of attacks that could have been prevented with SoC-level security and describes options for SoC designers to consider to mitigate threats.


Dr. Johan Kraft, Founder and CEO, Percepio AB

Tracing OpenVX and CNN Applications on EV6x Embedded Vision Processors

EV6x processors allow for great processing performance, but the performance you get depends on how well your solution takes advantage of the hardware capabilities, especially with parallel and pipelined architectures. Dr. Kraft introduces the Percepio Tracealyzer and its tracing support in the MetaWare EV Development Toolkit.

To view the full sessions, please enter your business contact information and a link to the videos will be emailed to you.

Please register with your professional/business email account.