• 3 min read
Improving Cancer Research with Computer Vision
Researcher Mateo Sokac trained an object detection model in Roboflow to count neutrophils in dry microscopy, hitting 0.70 mAP with image tiling and augmentation.
• 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.
• 8 min read
Using Computer Vision to Help Deaf and Hard of Hearing Communities
How an object detection model reads the American Sign Language alphabet from a webcam, reaching 85% mAP on a small dataset built and augmented fast.
• 2 min read
Generating Renaissance Art with Computer Vision
How two high schoolers built GAN art in 24 hours: a DCGAN trained on 300 Renaissance paintings, augmented in Roboflow to win their hackathon.
• 5 min read
Revolutionizing Conidia Counting with Roboflow
Learn how to build an automated microscopy pipeline using Roboflow and Lovable to digitize quality control and scale lab throughput.
• 6 min read
Behind the Design of an Augmented Reality Board Game App
A designer's augmented reality app design process, start to finish: research, three AR iterations, SwiftUI tradeoffs, testing, and neon branding.
• 4 min read
How Transport for Cairo is Improving Commuting for Millions with Computer Vision
Learn how Transport for Cairo is improving commuting for millions with computer vision.
• 3 min read
Porch Box Detection Using Computer Vision
How a developer built local package detection with a $100 Jetson Nano and an IP camera: 15 starter images, iterative retraining, no cloud fees.
• 4 min read
Using Computer Vision to Boost Cities' Efficiency
How a data scientist built traffic violation detection on existing CCTV cameras: NYC webcam data, transfer learning from COCO, 50 fps inference.
• 5 min read
How to Deliver Better Consumer Experiences with Vision AI
Vision AI is transforming how drivers interact with their vehicles, turning static owner’s manuals into dynamic, camera-powered experiences. Learn how Ogily built the Audi Reader.
• 5 min read
How to Build Factory Robots with Vision AI
Learn how to build adaptive factory robots with Vision AI. See how Almond trained robots that identify, sort, and automate complex tasks.
• 6 min read
Scientific Research AI: Unlocking Visual Data
AI is transforming scientific research by automating the slowest parts of discovery: collecting, labeling, and analyzing data. At the Field Museum, researchers used vision AI to digitize 13,500 insect specimens in weeks, showing that with the right tools, decades of work can happen in days.
• 5 min read
Searching for Jetskis, Finding Roboflow
My story of building a vision model to detect jetskis and, in the process, finding Roboflow.
• 9 min read
How Computer Vision Is Reshaping The Restaurant Industry
Learn how computer vision can be used to improve efficiency in the restaurant industry.
• 9 min read
Using Computer Vision to Develop a Robotic Arm Poker Dealer
Learn how the vision system of an acting poker dealer arm was built by the University of Manchester Robotics Society.
• 6 min read
How to Monitor Red Zones with Computer Vision
Learn how to monitor red zones for safety compliance using computer vision.
• 4 min read
Vision AI in Manufacturing: 3 Proven Strategies to Adopt in 2025
Explore how you can use AI in manufacturing to avoid jams and pileups, identify product defects, and more.
• 7 min read
Deploying Machine Learning Models with PyTorch, gRPC, and asyncio
SUMMARY
Serving a machine learning model with gRPC and asyncio gives you a faster, more scalable alternative to HTTP/1 REST endpoints: messages are binary Protobuf rather than JSON, type-safe client and server stubs are generated from a .proto file, and multiple images can be batched into a single
• 6 min read
Rock, Paper, Scissors with AI: How to Make Multiplayer Games
SUMMARY
HandLand is an open-source template for building two-player, gesture-controlled games in the browser using computer vision models from Roboflow Universe. The repo ships three complete games, including Rock Paper Scissors and a standoff game called 007, using WebRTC for peer video and native WebSockets for real-
• 12 min read
Using Computer Vision to Assess Bouldering Performance
Learn how I built a system to assess my bouldering skills using computer vision.
• 9 min read
How to Create a Retail Planogram using Computer Vision
Learn how to create a retail planogram from a photo using computer vision.
• 5 min read
Automatic Stop Sign Violation Detection
SUMMARY
This community-contributed project determines whether a vehicle correctly stops at a stop sign by chaining RF-DETR vehicle detection, a fine-tuned front-wheel detection model, and Roboflow PolygonZone geometry checks across a stop zone and an out zone. Vehicles that fail to stop before the white line
• 8 min read
Camera Calibration in Sports with Keypoints
SUMMARY
Accurate player tracking in sports footage requires mapping pixel coordinates from a moving camera to real-world field positions, and this tutorial covers how to do that by training a YOLOv8 keypoint detection model to recognize characteristic landmarks on a soccer pitch, then using those detections to compute a
Stay Connected