Latest Posts

19 Aug 2024 • 13 min read

How to Map User Inputs in Video Games with Computer Vision

Gaming is one of the most popular pastimes in the world, offering exciting experiences and endless entertainment from the comfort of your home.  Using computer vision, we are able to analyze our inputs that otherwise would be difficult to track. For example, you could use computer vision to build an

15 Aug 2024 • 8 min read

Measure Fish Size using Computer Vision

Learn how to use computer vision to measure the size of fish.

14 Aug 2024 • 6 min read

How to Create a Workout Pose Correction Tool

0:00 /0:21 1× Introduction Computer vision is a useful tool when it comes to understanding and quantifying real-world activity happening in real-time. Tracking human movements with pose estimation is a common way to evaluate athletics or general body movement to help gain insight into proper form and technique.

14 Aug 2024 • 7 min read

How to Build a Reading Assistant with AI

Readers can face trouble when encountering new, unfamiliar words. With advancements in computer vision, we can develop innovative solutions that can aid readers in overcoming these hurdles. 0:00 /0:05 1× In this article, we cover how to use object detection and optical character recognition (OCR) models to create

12 Aug 2024 • 5 min read

How to Deploy Hugging Face Models with Roboflow

Hugging Face is an online community with AI models available for download. You can deploy select computer vision models hosted on Hugging Face with Roboflow Inference, a high-performance inference server for computer vision applications. This guide will show you how you can download models from Hugging Face and deploy them

8 Aug 2024 • 5 min read

Automatic Stop Sign Violation Detection

This post was contributed by Leonard Persson Norblad This automatic stop sign violation detector utilizes an object detection model fine-tuned in Roboflow, combined with Roboflow’s PolygonZone to identify vehicles that violate stop signs. Video recordings of vehicles that fail to stop are flagged for reporting. For complete code and

8 Aug 2024 • 7 min read

What is Optical Character Verification? A Comprehensive Guide

Optical Character Verification, or OCV, is a technology that verifies the accuracy and quality of printed text on manufactured items. Manufacturers and sellers check the accuracy of information on packages, from food labels to medication packaging, in a fast and automated way using OCV. OCV works with Optical Character Recognition

8 Aug 2024 • 7 min read

Camera Calibration in Sports with Keypoints

Camera calibration is important to accurate vision AI systems that analyse sports. It allows the mapping of their movement on a video frame to real movement on the field, and thus the tracking of the distance they cover, the direction, and the speed at which they move. Homography is commonly

7 Aug 2024 • 8 min read

How to Extract Text From Images

Introduction to Text Extraction Manually working with data in JPG, PNG, or PDF formats can be a hassle, as it takes a lot of time to analyze and these files can’t be managed easily in a programmatic way. We can use tools, either online or offline, to convert images

7 Aug 2024 • 6 min read

How to Build a Computer Vision Active Learning Workflow

Learn how to build an active learning pipeline for computer vision projects with Roboflow Workflows.

6 Aug 2024 • 7 min read

Ball Tracking in Sports with Computer Vision

Ball tracking is crucial for AI systems to analyze sports effectively, but it's challenging due to factors like the ball's small size, high velocity, complex backgrounds, similar-looking objects, and varying lighting. This tutorial will teach you how to overcome these challenges.

2 Aug 2024 • 2 min read

How to Import Hugging Face Datasets to Roboflow

Learn how to import a Hugging Face dataset into Roboflow for labeling, training, and deployment.

2 Aug 2024 • 5 min read

Inspecting Solar Panels with Thermal Drones

Learn how to use computer vision to identify hot spots on solar panels.

1 Aug 2024 • 7 min read

How to Use SAM 2 for Video Segmentation

Segment Anything Model 2 (SAM 2) is a unified video and image segmentation model. Video segmentation presents unique challenges compared to image segmentation. Object motion, deformation, occlusion, lighting changes, and other factors can vary dramatically from frame to frame. Videos are often lower quality than images due to camera motion,

31 Jul 2024 • 6 min read

How to Label Data with Grounded SAM 2

Learn how to use Grounded SAM 2 with Autodistill to auto-label data for image segmentation models.

30 Jul 2024 • 9 min read

Automating Water Meter Reading using Computer Vision

Learn how to read the digits on a water meter using computer vision.

30 Jul 2024 • 7 min read

What is Segment Anything 2 (SAM 2)?

Learn about Meta AI's new Segment Anything 2 model and how you can use it for image and grounded image segmentation.

25 Jul 2024 • 6 min read

Monitor Assembly Line Throughput with Computer Vision

Learn how to monitor assembly line throughput with computer vision.

25 Jul 2024 • 5 min read

Identify Solar Panel Locations with Computer Vision

Learn how to identify solar panel locations with computer vision.

25 Jul 2024 • 5 min read

How to Build a CPG Inventory Cataloging System

Learn how to build a Consumer Packaged Goods inventory management system with computer vision.

25 Jul 2024 • 5 min read

How to Build an Automated License Plate Reading Application

Learn how to build an automated license plate reading application with computer vision.

22 Jul 2024 • 3 min read

How to use MobileNetV4 for Classification

Learn how to use the MobileNetV4 architecture to classify images using pre-trained model weights.

22 Jul 2024 • 7 min read

How to OCR Hand-Written Notes with GPT-4

Learn how to OCR hand-written notes with GPT-4.

22 Jul 2024 • 5 min read

Launch: Deploy PaliGemma Models with Roboflow

Learn how to deploy PaliGemma models with Roboflow.