• 7 min read
Pool Table Analytics Using Object Detection
In this guide, Abirami Vina shows how to build a pool table analytics system with object detection.
• 7 min read
Using Computer Vision for Online Exam Proctoring
SUMMARY
This tutorial builds an online exam proctoring system that uses a webcam and Roboflow Inference to detect when a student picks up a phone during a remote assessment. A pre-trained phone detection model from Roboflow Universe is deployed via the Inference API, and the live webcam feed is
• 6 min read
How to Use Computer Vision to Monitor Inventory: Inventory Management AI
SUMMARY
This tutorial builds an inventory monitoring pipeline that extracts video frames at defined time intervals, runs each frame through Roboflow Inference Server against a model trained on packaged shelf items, and outputs structured CSV files (per-object detections, counts per interval, counts by class) along with bar charts showing
• 7 min read
Floor Plan Analysis with Computer Vision
Learn how to analyze floor plans with computer vision.
• 8 min read
How to Reduce Dataset Size Without Losing Accuracy
Learn how to reduce the size of your computer vision dataset without losing accuracy.
• 5 min read
Preventing Treadmill Injuries with an Automated Stopping Mechanism
In this blog post, I walk through how I built a system to prevent treadmill injuries with a computer vision powered automated stopping mechanism.
• 10 min read
How to Use Computer Vision for Environment Monitoring
SUMMARY
Satellite and drone imagery analyzed by computer vision models can measure environmental change at a scale and frequency that manual scientific monitoring cannot match, turning pixel data into quantifiable ESG metrics like built-up area, deforestation extent, water coverage, and crop health. This guide walks through building a remote
• 5 min read
Detect and Segment Oil Spills Using Computer Vision
SUMMARY
Drone footage of an oil spill carries enough information to determine spill volume, thickness, and spatial extent, but only if the imagery is analyzed with a model trained to distinguish those properties. This post walks through building an instance segmentation model that labels oil spill regions by thickness class,
• 7 min read
Build a Chess Game Recorder with Computer Vision
SUMMARY
Clio, built by the team at A1H1, is a portable chess recording device that uses computer vision instead of embedded sensors to digitize over-the-board games, bringing the cost well below the roughly $500 USD of sensor-equipped commercial sets. The system handles two distinct problems: detecting the
• 5 min read
Prompting Google Bard with Images & How it Compares to Bing
SUMMARY
Google Bard's image input capabilities, tested against counting, object detection, and classification tasks using datasets from Roboflow Universe, fall short of Bing/GPT-4 for structured computer vision work. Bard refuses images containing human faces entirely rather than blurring them, and it undercounts objects even in straightforward
• 5 min read
Improve Accuracy: Polygon Annotations for Object Detection
SUMMARY
Polygon annotations consistently outperform bounding boxes for object detection when objects have irregular shapes, because polygons eliminate background noise that bounding boxes include. An experiment comparing both annotation types, combined with augmentations (rotation, saturation, cutout, bounding box shear) and pretrained weight initialization, showed meaningful mAP gains at each step.
• 5 min read
How to Use Generative AI to Augment Computer Vision Data
Dive deep into Kopikat.co, a tool for generative data augmentation created by OpenCV.ai to improve the quality of datasets.
• 4 min read
Detecting Objects with DETIC vs Custom Training
Learn how to evaluate large foundation models and how custom model training can improve performance.
• 6 min read
From Novice to Knowledge: My Journey Building a Gesture Recognition Model with Roboflow
This guide shows how Eli, a Sales Development Representative at Roboflow, made a computer vision model to recognize hand gestures.
• 5 min read
Auto-Label Classification Datasets Using CLIP
SUMMARY
OpenAI's CLIP model can auto-label image classification datasets by computing cosine similarity between image embeddings and text embeddings for each class name, then assigning the best-matching label. This tutorial walks through the full pipeline in a Jupyter notebook using the Roboflow Art Classification Dataset, covering
• 8 min read
Automated Computer Vision Inspection of Physical Pipelines
In this guide, we show how to identify various types of pipeline defects using computer vision.
• 8 min read
Not All mAPs are Equal and How to Test Model Robustness
Learn how to stress-test the robustness of computer vision models.
• 11 min read
Automatic Habit Disruption with Computer Vision
Learn how a Roboflow user built a tool to disrupt a Trichotillomania habit with computer vision.
• 10 min read
No Code Computer Vision with Roboflow + Zapier
Learn how to use the Roboflow Zapier integration to implement no-code computer vision workflows.
• 4 min read
Resume OCR: How to Use YOLOv5 for Automated Resume Parsing
In this post, learn how computer vision was used to segment columns in a resume for use in resume parsing.
• 12 min read
From Idea to Reality: Building a Computer Vision Scavenger Hunt for SXSW
Learn about how we built a scavenger hunt app in two weeks and got 200 strangers to play in celebration of SXSW 2023.
• 3 min read
Announcing the Roboflow SXSW Scavenger Hunt
Play the computer vision-powered Roboflow SXSW Scavenger Hunt for a chance to earn a $1,000 prize.
• 7 min read
Represent Chess Boards Digitally with Computer Vision
In this guide, learn how Shai Nisan used computer vision to translate a photo of a chess board into FEN notation.
• 8 min read
How to Build a Stable Diffusion Image-to-Image Pipeline
In this article, we discuss how to build a Stable Diffusion image generation pipeline using SageMaker Studio Labs, Hugging Face, and Roboflow.
Stay Connected