Software for Embedded Vision
AI Helps Locate Dangerous Fishing Nets Lost at Sea
This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. Conservationists have launched a new AI tool that can sift through petabytes of underwater imaging from anywhere in the world to identify signs of abandoned or lost fishing nets—so-called ghost nets. Each year, around 2% of the
The SHD Group Releases New Edge AI Processor and Ecosystem Report
Now available for free download from Alliance Member company The SHD Group is their latest market report, Edge AI Market Analysis: Applications, Processors and Ecosystem Guide, developed in partnership with the Edge AI and Vision Alliance. The report provides a detailed exploration of the rapidly evolving edge AI landscape, covering critical insights on emerging applications,
What Is Agentic AI? A Complete Guide to the Future of Autonomous Intelligence
This blog post was originally published at Geisel Software’s website. It is reprinted here with the permission of Geisel Software. What is agentic AI? It refers to intelligent systems that can autonomously set goals, make decisions, and execute tasks without constant human input. It marks a significant shift from reactive chatbots to proactive, mission-oriented AI
SplitQuant: Layer Splitting for Low-bit Neural Network Quantization for Edge AI Devices
This blog post was originally published at Nota AI’s website. It is reprinted here with the permission of Nota AI. This study proposes an AI model preprocessing method for improved quantization accuracies on edge AI devices which do not support advanced quantization methods due to their limitations. By splitting layers based on parameter clustering, the
“State-space Models vs. Transformers for Ultra-low-power Edge AI,” a Presentation from BrainChip
Tony Lewis, Chief Technology Officer at BrainChip, presents the “State-space Models vs. Transformers for Ultra-low-power Edge AI” tutorial at the May 2025 Embedded Vision Summit. At the embedded edge, choices of language model architectures have profound implications on the ability to meet demanding performance, latency and energy efficiency requirements. In… “State-space Models vs. Transformers for
AMD Acquires Brium to Strengthen Open AI Software Ecosystem
News Highlights Brium’s world-class compiler and AI software experience will strengthen AMD’s ability to deliver highly optimized AI solutions across the entire stack Will reduce developer dependencies on specific hardware configurations and enable accelerated out of the box AI performance Brium’s domain-specific expertise will expand AMD’s market reach across industries such as healthcare, life sciences,
“How Qualcomm Is Powering AI-driven Multimedia at the Edge,” a Presentation from Qualcomm
Ning Bi, Vice President of Engineering at Qualcomm Technologies, presents the “How Qualcomm Is Powering AI-driven Multimedia at the Edge” tutorial at the May 2025 Embedded Vision Summit. In this talk, Bi explores the evolution of multimedia processing at the edge, from simple early use cases such as audio and… “How Qualcomm Is Powering AI-driven
“Rapid Development of AI-powered Embedded Vision Solutions—Without a Team of Experts,” a Presentation from Network Optix
Marcel Wouters, Senior Software Engineer at Network Optix, presents the “Rapid Development of AI-powered Embedded Vision Solutions—Without a Team of Experts” tutorial at the May 2025 Embedded Vision Summit. In this presentation, Wouters shows how developers new to AI can quickly and easily create embedded vision solutions that extract valuable… “Rapid Development of AI-powered Embedded
“OAAX: One Standard for AI Vision on Any Compute Platform,” a Presentation from Network Optix
Robin van Emden, Senior Director of Data Science at Network Optix, presents the “OAAX: One Standard for AI Vision on Any Compute Platform” tutorial at the May 2025 Embedded Vision Summit. OAAX, an open accelerator compatibility standard being developed under the Linux Foundation AI & Data project, is key to… “OAAX: One Standard for AI
Nota AI and Wind River Collaborate to Deliver On-device Generative AI for the Intelligent Edge
SEOUL, South Korea and ALAMEDA, CA – May 28, 2025 – Nota AI, a pioneer in on-device AI optimization, and Wind River, a global leader in delivering software for the intelligent edge, have signed a strategic Partner Program Agreement (PPA) to combine Nota AI’s NetsPresso® capabilities into Wind River Studio Developer. “The combination of technologies
UniForm: A Reuse Attention Mechanism for Efficient Transformers on Resource-constrained Edge Devices
This blog post was originally published at Nota AI’s website. It is reprinted here with the permission of Nota AI. Delivers real-time AI performance on edge devices such as smartphones, IoT devices, and embedded systems. Introduces a novel “Reuse Attention” technique that minimizes redundant computations in Multi-Head Attention. Achieves competitive accuracy and significant inference speed
Biometrics in IoT: CyberLink Ports FaceMe to Qualcomm Hexagon NPU for Facial Recognition on Edge Devices
This blog post was originally published at Qualcomm’s website. It is reprinted here with the permission of Qualcomm. If you develop facial recognition software, you spend most of your time and effort maximizing performance, accuracy and precision. Your customers expect high performance, even when running on low-power edge devices like point-of-sale (POS) terminals, kiosks and
AI Blueprint for Video Search and Summarization Now Available to Deploy Video Analytics AI Agents Across Industries
This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. The age of video analytics AI agents is here. Video is one of the defining features of the modern digital landscape, accounting for over 50% of all global data traffic. Dominant in media and increasingly important for
Effortless Edge Deployment of AI Models with Digica’s AI SDK (Featuring ExecuTorch)
This blog post was originally published at Digica’s website. It is reprinted here with the permission of Digica. Deploying AI models on mobile and embedded devices is a challenge that goes far beyond just converting a trained model. While frameworks like PyTorch offer a streamlined way to develop deep learning models, efficiently deploying them on
Build & Deploy AI Vision Models for Windows on Snapdragon: OpenCV Live! Podcast
This blog post was originally published at EyePop.ai’s website. It is reprinted here with the permission of EyePop.ai. Want to deploy AI models to the edge without the cloud? On this special LIVE podcast hosted by OpenCV, Andy Ballester and Blythe Towal show how EyePop.ai is enabling real-time, offline inference with Snapdragon NPUs from Qualcomm.
Seamless Software Development for Qualcomm Platforms with Qualcomm Visual Studio Code Extension
This blog post was originally published at Qualcomm’s website. It is reprinted here with the permission of Qualcomm. To simplify the development of applications for Qualcomm Dragonwing products, Qualcomm Technologies, Inc. has introduced the Qualcomm Visual Studio Code Extension. This innovative extension provides a streamlined, end-to-end environment that enhances your workflow across various tools and
SiMa.ai and Wind River Collaborate to Enable Seamless AI/ML for Intelligent Edge Applications
SAN JOSE, CA and ALAMEDA, CA – May 20, 2025 – SiMa.ai, the software-centric and embedded edge machine learning system-on-chip (MLSoC) company, and Wind River, a global leader in delivering software for the intelligent edge, have collaborated on an integrated hardware and software solution for next-generation edge AI. Delivering a convenient and seamless experience for
Airy3D Announces DepthIQ Support for Qualcomm Dragonwing RB3 Gen 2 and RB5 Platforms
Empowering next-generation 3D vision applications in robotics, industrial, and smart devices. Montreal, Canada – May 20th, 2025 – Airy3D, a leader in 3D sensing solutions, today announced that its DepthIQ™ software development kit (SDK) is now supported on the Qualcomm Dragonwing™ RB3 Gen 2 and RB5 platforms. This milestone enables developers and OEMs to easily
