Lattice Semiconductor, a leading supplier of low-power programmable devices, today announced its latest roadmap of low-power, AI/ML solutions that can help extend battery life and deliver innovative user experiences for edge-of-network applications such as client computing devices. Built with the award-winning Lattice sensAITM solution set and running on Lattice Nexus FPGAs, they can help OEMs develop smart, real-time-online, low-power and hardware-accelerated AI-enabled devices that can also be upgraded in the field to support more AI algorithms in the future.
Client computing devices increasingly require fast-response and context-aware user experiences, high-quality video conferencing, and collaborative applications. The Lattice Nexus FPGA and sensAI solution set is an ideal platform for developing computer vision and sensor fusion applications that enhance user engagement and collaboration and protect user privacy. For example, client devices can analyse image data captured by a camera to determine if a person behind it is getting too close to the user, as well as blur the screen to protect privacy when the user's attention is diverted elsewhere, or dim the screen to extend battery life.
AI applications based on vision, sound and other sensors will revolutionise the client computing experience,’ said Matt Dobrodziej, vice president of marketing and business development at Lattice. Our sensAI supports a wide range of network edge AI solutions, empowering client devices with the contextual awareness to know when, where and how they are being used. Our Nexus FPGAs then enable this with industry-leading low power consumption.’
AI computing devices developed with sensAI and running on Lattice FPGAs have up to 28 per cent longer battery life compared to devices using CPUs to power AI applications. sensAI also supports field software updates to keep AI algorithms evolving, and also provides OEMs with the flexibility to choose different sensors and SoC technologies to adapt to their devices.
Lattice is working with leading AI ecosystem partners to develop a roadmap for the evolution of Lattice's client computing AI experience.
Our Glance by Mirametrix attention sensing software captures the user's face, eyes and gaze movements to understand the user's awareness and attention,’ said Stephen Morganstein, vice president of Mirametrix. This unique technology develops smart devices that provide a more natural and immersive user experience and device interaction. Lattice's sensAI solution set and low-power FPGAs help developers implement novel AI capabilities and improve device battery life.’
The latest version (v4.1) of the sensAI solution collection is now available to support Lattice's AI-based application roadmap with enhanced features and new features including:
● Client computing AI experience reference design
o User detection: client devices are automatically activated or shut down when a user approaches or leaves the device
o Attention tracking: reduces the screen brightness of the device when the user's attention is not on the screen, saving power and extending usage time
o Face Framing: Enhances the video experience in video conferencing applications.
o Sidekick detection: detects potential peepers standing behind the device, blurring the screen to protect data privacy
● More Application Support - The performance and accuracy improvements in sensAI version 4.1 help expand its target applications, including high-precision target detection and defect detection used in automated industrial systems. The solution set features a new hardware platform with an on-board image sensor, two I2S microphones, and expansion connectors for adding more sensors, powering the development of speech- and vision-based machine learning applications.
● Easy-to-use tools - sensAI has also updated its neural network compiler to support Lattice sensAI Studio, a GUI-based tool with AI model libraries that can be configured and trained for a wide range of mainstream application scenarios. sensAI Studio now supports AutoML functionality, which enables the creation of machine learning modules based on the goals of the application and dataset. Machine Learning Modules. Some of the models based on the Mobilenet machine learning inference training platform are optimised for the latest Nexus series product, Lattice CertusPro-NX. sensAI is also compatible with other widely used machine learning platforms, including the latest versions of Caffe, Keras, TensorFlow and TensorFlow Lite. Lite.
wechat/whatsapp:
+86-181-4410-0983
Email: kongjiangauto@163.com
Copyright © 2009 - 2024 Cld , All Rights Reserved K-JIANG All rights reserved