Lattice Blog

Share:

Latest Industrial/Automotive News from Lattice

Q2 2019 Industrial and Automotive Newsletter
Posted 09/27/2019 by Lattice Semiconductor

Posted in

Enhanced Technology Stack Packs 10X Performance Boost

Demand is booming for edge applications like presence detection in smart homes, object counting in retail and object detection, and presence detection in smart factories that need ever-higher performance requirements. But to solve these problems users need solutions that not only operate off low power and in a small footprint but do so without compromising performance or relying on the cloud. Can designers meet these challenges? The answer is yes. Key to that achievement is a new enhanced version of Lattice’s sensAI technology stack that delivers up to a 10X performance improvement over the original stack by taking advantage of optimized memory access, updated neural network IP and a new neural network compiler. Check out the new White Paper that explains how this technology stack can help you.

Integrate AI into Your Smart Application

Want to quickly and easily integrate AI-enabled vision systems into your products? Lattice’s sensAI and Embedded Vision Development Kit (EVDK) offer you a shortcut to market. The revolutionary sensAI technology stack offers developers an FPGA-based solution that combines the hardware kits, software tools, neural network IP cores, reference designs and custom design services needed for a typical design. Whether you’re developing a smart oven sensor that tells you when the holiday turkey is ready to eat or a door bell that warns you when a package has been dropped off on your front porch, sensAI helps you develop any product you can image by leveraging an advanced neural network engine that is far more accurate than any traditional algorithm.

At the same time Lattice’s EVDK offers embedded vision designers a smart, highly modular way to build prototype systems quickly. You can now use Lattice’s EVDK and sensAI stack to create precision object detection solutions in your own smart sensor environment. Image solutions where all detection processing happens locally on the edge, latency is minimized, and expensive cloud connectivity is eliminated. Using Lattice’s low power FPGAs and software solutions, you can accelerate application development with flexible inferencing at the edge while consuming as little as 800 mW of power. Finally, indicative of what the embedded electronics industry believes, sensAI and the EVDK have together won eight major industry awards over the last three years.

CrossLink FPGAs Simplify Use of Embedded Vision

Want to learn how to add support for the Mobile Industry Processor Interface (MIPI) in Embedded Vision in applications like smart cars, industrial robotics and drones? Check out Lattice’s latest webinar entitled “Supporting MIPI in Embedded Vision System Designs Using FPGAs.” This overview tells you all you need to know about the challenges you’ll face. At the same time, it lays out how you can use Lattice’s CrossLink FPGAs, its easy-to-use software and hardware tools, and its pre-verified IP blocks and reference designs to quickly get up to speed. The webinar is available in English, Chinese and Japanese.

Lattice Team Showcases sensAI Capabilities at Hackathon 2019

A team of Lattice members recently returned from a trip to Redmond, Washington where they participated in Microsoft’s global Hackathon, the world’s largest private hackathon event. With more than 27,000 participants at 45 sites around the world, Hackathon 2019 is an ideal place to sharpen engineering skills by developing technology-based solutions for real world problems. The Lattice team sponsored the sensors’ hack, a part of the Hackathon event that focused on potential use cases for AI and sensors. What kind of feedback did the Lattice team receive? That sensAI is an excellent platform for enabling AI inferencing in a small form factor and at very low power, two key requirements for developing always-on devices operating at the network edge. Read the blog now.

Share:

Like most websites, we use cookies and similar technologies to enhance your user experience. We also allow third parties to place cookies on our website. By continuing to use this website you consent to the use of cookies as described in our Cookie Policy.