• 4 min read
How to Build a Real-Time Computer Vision Web App
Learn how to build a real-time computer vision web app. Webcam detection over WebRTC, drawn on a canvas overlay.
• 4 min read
YOLO-Face Detection with Custom Models
Discover YOLO-Face, a collection of open-source face detection datasets and models. Learn how to build and train custom face detectors with Roboflow.
• 29 min read
Pick and Place Robot Model & Prototyping
Learn to quickly prototype a vision-guided pick-and-place robot using synthetic data, Roboflow RF-DETR, and PyBullet, then move it to real hardware.
• 5 min read
The Evolution of the Industrial Internet of Things
Discover how Edge IIoT and computer vision transform smart factories. Learn to process massive visual data loads at the edge with Roboflow's AI1 camera.
• 4 min read
How to Build Jersey Number Recognition for Sports
Learn how jersey number recognition identifies players in sports video.
• 3 min read
Detecting and Counting Symbols on Construction Plans
Learn how to automate construction takeoffs with computer vision. Build an object detection pipeline to find and count blueprint symbols.
• 7 min read
Vision Token Counts: What does it cost to process an image with a frontier vision model?
Understand the cost, per-provider tokenization rules, and a comparison across image sizes for Claude, GPT, and Gemini.
• 7 min read
Best Object Detection Models
Object detection has entered a new era in 2025. Next-generation models are combining transformer efficiency and real-time speed to power breakthroughs in automation, robotics, and visual intelligence across every industry. See the best models.
• 6 min read
Shipping Label Extraction with Qwen 3.5 VL in Roboflow Workflows
Extract structured shipping label data using Qwen 3.5 VL in Roboflow Workflows on free GPU.
• 10 min read
Lights-Out Manufacturing: Vision AI in Automation
Discover how lights-out manufacturing enables 24/7 autonomous production.
• 6 min read
Understanding OEE vs OOE vs TEEP
Understand the difference between OEE, OOE, and TEEP. Learn how to calculate each metric and how computer vision can improve your OEE Quality score.
• 4 min read
How to Use the Detectron2 Model Zoo for Object Detection
Use the Detectron2 model zoo: train Faster R-CNN from a COCO checkpoint, swap architectures with a one-line config change, and evaluate mAP.
• 5 min read
AI Swimmer Tracking
Learn how to build an automated aquatic monitoring pipeline using RF-DETR and ByteTrack in Roboflow.
• 11 min read
Vision Banana: Google DeepMind's Generalist Model
Discover how DeepMind's Vision Banana uses generative pretraining to unify 2D and 3D computer vision tasks, outperforming specialized models like SAM 3.
• 9 min read
Azure Custom Vision Is Retiring: Deprecation Migration Guide
Azure Custom Vision retires September 25, 2028. Here is what happens to your models, every migration option compared, and how to move your dataset in an afternoon.
• 4 min read
Latency vs Accuracy Tradeoff in Object Detection, Solved
Solve the latency vs accuracy tradeoff in object detection. Watch NAS search thousands of models and map the curve.
• 5 min read
Introducing AI1: Turn Visual Intelligence Into Business Intelligence
AI1 puts camera, compute, lighting, and the full Roboflow stack in one device, turning every part on your line into a structured business event.
• 8 min read
The Manufacturer’s Guide to Nondestructive Testing with Vision AI
Discover how Vision AI automates Nondestructive Testing (NDT) in manufacturing. Learn to detect defects and build a Visual QMS using Roboflow.
• 4 min read
Bringing Street Murals to Life with Computer Vision
How a Brooklyn engineer used computer vision to identify the women honored in a street mural, from labeled photos to a working Android app.
• 2 min read
How Cocoparks Accelerated Their Development with Roboflow
Cocoparks trained a 93% mAP traffic monitoring model and shipped an MVP in 30 days with Roboflow, saving weeks of engineering time.
• 11 min read
What is Mean Average Precision (mAP) in Object Detection?
What is mean average precision? How do we calculate mAP?
• 13 min read
How to Train a YOLO26 Oriented Bounding Box (OBB) Model
Learn how to train a YOLO26 Oriented Bounding Boxes model with a dataset labeled on Roboflow.
• 11 min read
Computer Vision in Manufacturing Automation: Use Cases, ROI, and How to Deploy
Learn how computer vision can be used in manufacturing.
• 12 min read
Luxonis OAK-D: Deploy a Custom Object Detection Model with Depth
Train a custom object detection model and deploy it to the Luxonis OAK-D: RF-DETR on the host, depth per detection, and on-device options.
Stay Connected