LETTER FROM THE EDITOR |
Dear Brian, Next Thursday, August 22, 2024 at 9 am PT, BDTI will deliver the free webinar “Silicon Slip-Ups: The Ten Most Common Errors Processor Suppliers Make (Number Four Will Amaze You!)” in partnership with the Edge AI and Vision Alliance. For over 30 years BDTI has provided engineering, evaluation and advisory services to processor suppliers and companies that use processors in products. The company has seen a lot, including some classic mistakes. (You know, things like: the chip has an accelerator, but no easy way to program it… or you can only program it using an obscure proprietary framework. Or the development tools promise a lot but fall far short. Or the device drivers don’t work. Or or or… you get the idea.) Join Phil Lapsley, Co-Founder and Vice President of BDTI, for a fun and fast-paced review of some of the most common processor provider errors, ones seen repeatedly at BDTI. If you’re a processor provider, you’ll learn things you can do to avoid these goofs—and if you’re a processor user, you’ll learn about things to watch for when selecting your next processor! A question-and-answer session will follow the presentation. For more information and to register, please see the event page. Brian Dipert |
LLMs and VISION LANGUAGE MODELS AT THE EDGE |
Deploying Large Language Models on a Raspberry Pi In this presentation, Pete Warden, CEO of Useful Sensors, outlines the key steps required to implement a large language model (LLM) on a Raspberry Pi. He begins by outlining the motivations for running LLMs on the edge and exploring practical use cases for LLMs at the edge. Next, he provides some rules of thumb for selecting hardware to run an LLM. Warden then walks through the steps needed to adapt an LLM for an application using prompt engineering and LoRA retraining. He demonstrates how to build and run an LLM from scratch on a Raspberry Pi. Finally, he shows how to integrate an LLM with other edge system building blocks, such as a speech recognition engine to enable spoken input and application logic to trigger actions. |
Challenges and Solutions of Moving Vision LLMs to the Edge OEMs, brands and cloud providers want to move LLMs to the edge, especially for vision applications. What are the benefits and challenges of doing so? In this talk, Costas Calamvokis, Distinguished Engineer at Expedera, explores how edge AI is evolving to encompass massively increasing LLM model sizes, the use cases of local LLMs and the performance, power and chip area considerations that system architects should consider when utilizing vision-based LLMs. |
Optimized Vision Language Models for Intelligent Transportation System Applications In the rapidly evolving landscape of intelligent transportation systems (ITSs), the demand for efficient and reliable solutions has never been greater. In this presentation, Tae-Ho Kim, Co-founder and CTO of Nota AI, shows how an innovative approach—optimized vision language models—can dramatically enhance the accuracy and robustness of computer vision solutions for ITSs. Kim also illustrates how optimized vision language models can be implemented in real time at the edge, enabling intelligent decision-making for applications such as traffic management, vehicle recognition and pedestrian safety. Finally, he explains how Nota AI is utilizing optimized vision language models to revolutionize numerous ITS applications, leading to safer, more efficient and environmentally friendly transportation systems. |
ACCELERATING ENTERPRISE VISUAL AI DEVELOPMENT |
A New Enterprise Operating System for Video and Visual AI In most software domains, developers don’t write code at the bare-metal level; they build applications on top of operating systems, which provide commonly needed functionality. Yet, today, developers of video and AI applications are effectively writing their applications at the bare-metal level, building the “plumbing” themselves to handle basics like device discovery, storage management, security and model deployment. These developers need an operating system that supports their applications so they can focus on what really matters: the core functionality of their product. Nx EVOS is the world’s first enterprise video operating system. EVOS revolutionizes video management, offering device discovery, bandwidth optimization and security features—in cloud and on device. Its support for AI pipelines and user management enables scalable deployment of AI applications across environments and platforms, and it’s trusted by leading organizations such as SpaceX. In this presentation from Nathan Wheeler, Co-founder and CEO of Network Optix, you’ll learn how Nx EVOS can save you time and effort in building your next vision product. |
UPCOMING INDUSTRY EVENTS |
Silicon Slip-Ups: The Ten Most Common Errors Processor Suppliers Make (Number Four Will Amaze You!) – BDTI Webinar: August 22, 2024, 9:00 am PT Leveraging Synthetic Data for Real-time Visual Human Behavior Analysis Using the SKY ENGINE AI Platform – SKY ENGINE AI Webinar: September 26, 2024, 9:00 am PT Delivering High Performance, Low Power Complete Edge-AI Applications with the SiMa.ai One Platform MLSoC and Toolset – SiMa.ai Webinar: October 17, 2024, 9:00 am PT Embedded Vision Summit: May 20-22, 2025, Santa Clara, California |
FEATURED NEWS |
e-con Systems Launches New 120 dB HDR Low-light USB Camera, Delivering High Detail in Low Light Allegro DVT Announces First Real-time VVC/H.266 Encoder IP Qualcomm’s Snapdragon X Series Platform Powers the Next Generation of Windows PCs with Copilot+ Basler Presents a New Programmable CXP-12 Frame Grabber and the dart M Modular Board Level Camera MIPI Cameras with GMSL2 and Miniature Vision Systems for Smart and Autonomous Devices Lead Vision Components’ Latest Product Introductions |
EDGE AI AND VISION PRODUCT OF THE YEAR WINNER SHOWCASE |
Ambarella Central 4D Imaging Radar Architecture (Best Edge AI Software or Algorithm) Ambarella’s central 4D imaging radar architecture is the 2024 Edge AI and Vision Product of the Year Award Winner in the Edge AI Software and Algorithms category. It is the first centralized 4D imaging radar architecture that allows both central processing of raw radar data and deep low-level fusion with other sensor inputs—including cameras, lidar and ultrasonics. The central 4D imaging radar architecture combines Ambarella’s highly efficient 5nm CV3-AD AI central domain controller system-on-chip (SoC) and the company’s Oculii adaptive AI radar software. This architecture’s optimized hardware and software provides the industry’s best AI processing performance per watt, for the lowest possible energy consumption, along with the most accurate and comprehensive AI modeling of a vehicle or robot’s surroundings. Ambarella’s Oculii AI radar algorithms uniquely adapt radar waveforms to the environment, achieving high angular resolution (0.5 degrees), an ultra-dense point cloud (10s of thousands of points/frame), and a long 500+ meters detection range, while using an order-of-magnitude fewer antennas for reduced data bandwidth and power consumption versus competing 4D imaging radars. Likewise, this architecture enables processor-less edge radar heads, further reducing both upfront costs and post-accident expenses (most radar modules are located behind the vehicle’s bumpers). Please see here for more information on Ambarella’s central 4D imaging radar architecture. The Edge AI and Vision Product of the Year Awards celebrate the innovation of the industry’s leading companies that are developing and enabling the next generation of edge AI and computer vision products. Winning a Product of the Year award recognizes a company’s leadership in edge AI and computer vision as evaluated by independent industry experts. |