• 8 min read
SOTA Instance Segmentation with RF-DETR Seg (Preview)
Today, we are excited to announce that we are expanding RF-DETR to support instance segmentation with the launch of RF-DETR Seg (Preview).
• 6 min read
Cursor Object Detection: Building Vision Apps with Roboflow
Learn how to build and deploy a custom object counting app in hours using Cursor and Roboflow, combining pre-trained models, simple prompts, and instant hosting to create production-ready vision AI.
• 9 min read
How to Detect, Track, and Identify Basketball Players with Computer Vision
Build a computer vision pipeline that detects, tracks, and identifies NBA players during a game. Using models like RF-DETR, SAM2, SigLIP, SmolVLM2, and ResNet, the system handles motion blur, occlusion, and uniform similarity to reliably map jersey numbers to player identities.
• 3 min read
Roboflow Playground: Try and Compare 30+ Computer Vision Models
We are excited to announce a tool to help you try, compare, and evaluate over 30 popular zero-shot vision models: Roboflow Playground.
• 15 min read
Multimodal Annotation Tools
This blog explores how multimodal annotation enables AI systems to understand and connect images, text, audio, and video. It reviews tools like Roboflow, Labelbox, and SuperAnnotate highlighting their features and includes a practical example of multimodal annotation using Roboflow.
• 10 min read
How to Use GitHub Copilot to Build Vision Apps
Building computer vision apps doesn’t have to mean wrestling with boilerplate code and complex integrations. Learn how GitHub Copilot and Roboflow work together to speed up development - helping you prototype, integrate APIs, and deploy vision apps quickly.
• 17 min read
What Are Vision Inspection Systems?
Understand what is vision inspection system (VIS), its types and applications. Learn how to build PCB defect inspection system using Roboflow.
• 10 min read
Key Computer Vision Tasks
Computer vision tasks such as object detection, image classification, and segmentation are the building blocks of modern AI applications. Learn how to perform them in minutes with Roboflow Workflows.
• 7 min read
Lovable Object Detection: Building Vision Apps with Roboflow
Learn how to how to pair Roboflow with Lovable to create a working object detection app in hours.
• 9 min read
What Is Vertex AI?
Vertex AI is Google Cloud’s unified platform for building, training, and deploying machine learning models at scale. In this blog, we explore how it simplifies computer vision workflows and how to use Roboflow with Vertex AI for dataset preparation, annotation, and model deployment.
• 3 min read
Roboflow Templates: 100+ Computer Vision Starter Apps
Today we are announcing a new tool to build the foundation of computer vision applications faster than ever: Roboflow Templates.
• 14 min read
How to Build a Vision-Language Model Application with Next.js
Vision-Language Models unlock powerful new ways to understand and process images alongside text. In this tutorial, we show how to combine Roboflow Workflows with Next.js to build a production-ready vision app.
• 7 min read
Replit Object Detection: Create Vision Apps with Roboflow
Learn how to build vision apps in hours with Replit and Roboflow - train models, deploy instantly, and count objects.
• 20 min read
Crack Detection with Computer Vision
Learn computer vision techniques for crack detection and use cases. We will walk through creating a real-time crack detection application and measurement of crack size (length and width).
• 11 min read
Spotlight on Upcoming AI & Computer Vision Events and Conferences in 2026
2026 will be a landmark year for AI and computer vision. This guide highlights the top conferences - from NeurIPS to CVPR - where you can discover breakthroughs, connect with industry leaders, and shape the future of AI.
• 6 min read
Real-Time Drinking Detection: Building Hydrovisor
Learn how to use Roboflow Inference.js and MediaPipe to build Hydrovisor - a real-time web app that detects drinking behavior through your webcam and reminds you to stay hydrated. A practical guide to computer vision in action.
• 22 min read
Corrosion Detection with Computer Vision
In this blog, you’ll learn how to build a corrosion detection app with Roboflow and NiceGUI, using computer vision techniques like classification, detection, and segmentation. This approach helps automate inspections and protect critical assets.
• 13 min read
Prompting Tips for Large Language Models with Vision Capabilities
Large multimodal models like Google Gemini and GPT-4o can now analyze both text and images, unlocking powerful computer vision capabilities. This guide shows you how to craft effective prompts and how to quickly build real-world vision applications.
• 7 min read
Create Vision Applications with Roboflow Using Vercel v0
By combining large language models with Roboflow’s API and Vercel v0, you can easily build vision apps. This tutorial shows you how to find pre-trained models on Roboflow Universe, adjust inference settings, and deploy a working application directly to the web.
• 10 min read
Build a PyTorch Custom Dataset
Custom PyTorch datasets give you full control over how data is loaded, transformed, and fed into your model. In this guide, you’ll learn how to build a PyTorch custom dataset step by step.
• 14 min read
Top Visual Inspection Systems
Discover leading visual inspection systems including Roboflow, Zebra, Cognex, Keyence, Basler, and Rockwell, and their key features.
• 15 min read
Automate Marathon Bib Number Recognition with Computer Vision
Timing and photography are the heartbeat of marathon events, but manually spotting bib numbers across hours of video is slow, error-prone, and costly. Learn how to automate bib recognition, accurately recording finish-line times and capturing the exact moment each runner crosses.
• 14 min read
Build Flutter Applications Using Computer Vision with Roboflow
Discover how to combine Flutter’s elegant cross-platform UI framework with Roboflow’s powerful computer vision platform to build AI-driven applications. Learn how to create a Flutter app that detects and counts Canadian coins.
• 11 min read
Build Computer Vision Applications with LLMs and Roboflow
Large language models and Roboflow make it possible to build computer vision apps in hours. This guide shows how to use LLM coding assistants with Roboflow’s API and Universe models to create and deploy vision AI apps.
Stay Connected