Software for Embedded Vision
Exploring the COCO Dataset
This article was originally published at 3LC’s website. It is reprinted here with the permission of 3LC. The COCO dataset is a cornerstone of modern object detection, shaping models used in self-driving cars, robotics, and beyond. But what happens when we take a closer look? By examining annotations, embeddings, and dataset patterns at a granular
Video Understanding: Qwen2-VL, An Expert Vision-language Model
This article was originally published at Tenyks’ website. It is reprinted here with the permission of Tenyks. Qwen2-VL, an advanced vision language model built on Qwen2 [1], sets new benchmarks in image comprehension across varied resolutions and ratios, while also tackling extended video content. Though Qwen2-V excels at many fronts, this article explores the model’s
Powering IoT Developers with Edge AI: the Qualcomm RB3 Gen 2 Kit is Now Supported in the Edge Impulse Platform
This blog post was originally published at Qualcomm’s website. It is reprinted here with the permission of Qualcomm. The Qualcomm RB3 Gen 2 Development Kit has been designed to help you develop high-performance IoT and edge AI applications. With powerful AI acceleration, pre-validated peripherals, and extensive software support, this kit enables every engineer to move
Intel Accelerates AI at the Edge Through an Open Ecosystem
Intel empowers partners to seamlessly integrate AI into existing infrastructure with its new Intel AI Edge Systems, Edge AI Suites and Open Edge Platform software. What’s New: Intel is unveiling its new Intel® AI Edge Systems, Edge AI Suites and Open Edge Platform initiatives. These offerings help streamline and speed up AI adoption at the edge
NVIDIA Announces Isaac GR00T N1 — the World’s First Open Humanoid Robot Foundation Model — and Simulation Frameworks to Speed Robot Development
Now Available, Fully Customizable Foundation Model Brings Generalized Skills and Reasoning to Humanoid Robots NVIDIA, Google DeepMind and Disney Research Collaborate to Develop Next-Generation Open-Source Newton Physics Engine New Omniverse Blueprint for Synthetic Data Generation and Open-Source Dataset Jumpstart Physical AI Data Flywheel March 18, 2025—GTC—NVIDIA today announced a portfolio of technologies to supercharge humanoid
NVIDIA Announces Major Release of Cosmos World Foundation Models and Physical AI Data Tools
New Models Enable Prediction, Controllable World Generation and Reasoning for Physical AI Two New Blueprints Deliver Massive Physical AI Synthetic Data Generation for Robot and Autonomous Vehicle Post-Training 1X, Agility Robotics, Figure AI, Skild AI Among Early Adopters March 18, 2025—GTC—NVIDIA today announced a major release of new NVIDIA Cosmos™ world foundation models (WFMs), introducing
NVIDIA Unveils Open Physical AI Dataset to Advance Robotics and Autonomous Vehicle Development
Expected to become the world’s largest such dataset, the initial release of standardized synthetic data is now available to robotics developers as open source. Teaching autonomous robots and vehicles how to interact with the physical world requires vast amounts of high-quality data. To give researchers and developers a head start, NVIDIA is releasing a massive,
Build Real-time Multimodal XR Apps with NVIDIA AI Blueprint for Video Search and Summarization
This article was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. With the recent advancements in generative AI and vision foundational models, VLMs present a new wave of visual computing wherein the models are capable of highly sophisticated perception and deep contextual understanding. These intelligent solutions offer a promising
OpenMV Unveils the N6 and AE3: High-performance, Low-power AI Vision Cameras for Makers and Professionals
March 17, 2025, San Francisco, CA – OpenMV is excited to announce the launch of the OpenMV N6 and OpenMV AE3, two groundbreaking machine vision cameras designed to bring real-time AI capabilities to microcontrollers. Backed by years of expertise in embedded vision, OpenMV is making high-performance AI vision accessible to developers, researchers, and hobbyists alike
Navigating the AI Implementation Journey: Buy or Build?
This blog post was originally published at Tryolabs’ website. It is reprinted here with the permission of Tryolabs. Many companies waste millions of dollars and critical time-to-market because they make the wrong decision on a seemingly simple question: should you buy an off-the-shelf AI solution or build your own? If you’re an AI project owner
Optimizing Edge AI for Effective Real-time Decision Making in Robotics
This blog post was originally published at Geisel Software’s website. It is reprinted here with the permission of Geisel Software. Optimizing Edge AI Key Takeaways Instant Decisions, Real-World Impact: Edge AI empowers robots to react in milliseconds, enabling life-saving actions in critical scenarios like autonomous vehicle collision avoidance and rapid search-and-rescue missions. Unshakeable Reliability, Unbreachable
Scalable Video Search: Cascading Foundation Models
This article was originally published at Tenyks’ website. It is reprinted here with the permission of Tenyks. Video has become the lingua franca of the digital age, but its ubiquity presents a unique challenge: how do we efficiently extract meaningful information from this ocean of visual data? In Part 1 of this series, we navigate
Passenger Car ADAS Market 2025-2045: Technology, Market Analysis, and Forecasts
For more information, visit https://www.idtechex.com/en/research-report/passenger-car-adas-market-2025-2045-technology-market-analysis-and-forecasts/1080. Global L2+/L3 feature adoption will exceed 50% by 2035. Over the past few years, Advanced Driver Assistance Systems (ADAS) have become a core competitive factor in the passenger vehicles market. In particular, “Level 2+” has emerged as a term describing advanced Level 2 ADAS with more sophisticated capabilities, such as
Building a Simple VLM-based Multimodal Information Retrieval System with NVIDIA NIM
This article was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. In today’s data-driven world, the ability to retrieve accurate information from even modest amounts of data is vital for developers seeking streamlined, effective solutions for quick deployments, prototyping, or experimentation. One of the key challenges in information retrieval
Productionizing State-of-the-art Models at the Edge for Smart City Use Cases (Part I)
This blog post was originally published at CLIKA’s website. It is reprinted here with the permission of CLIKA. Approaches to productionizing models for edge applications can vary greatly depending on user priorities, with some models not requiring model optimization at all. An organization can choose pre-existing models designed specifically for edge use cases with performance
Qualcomm at Embedded World: Accelerating Digital Transformation with Edge AI
This blog post was originally published at Qualcomm’s website. It is reprinted here with the permission of Qualcomm. An essential partner to the embedded community, Qualcomm Technologies, Inc. strengthens its leadership in intelligent computing with several key announcements The AI revolution is sparking a wave of innovation in the embedded community, spawning a flurry of
AutoML Decoded: The Ultimate Guide and Tools Comparison
This article was originally published at Tryolabs’ website. It is reprinted here with the permission of Tryolabs. The quest for efficient and user-friendly solutions has led to the emergence of a game-changing concept: Automated Machine Learning (AutoML). AutoML is the process of automating the tasks involved in the entire Machine Learning lifecycle, such as data
Zero-Shot AI: The End of Fine-tuning as We Know It?
This article was originally published at Tenyks’ website. It is reprinted here with the permission of Tenyks. Models like SAM 2, LLaVA or ChatGPT can do tasks without special training. This has people wondering if the old way (i.e., fine-tuning) of training AI is becoming outdated. In this article, we compare two models: YOLOv8 (fine-tuning)
