• 6 min read
A LLaMa 2, Midjourney & Autodistill Computer Vision Pipeline
Combine the use of Midjourney, Autodistill, LLaMa 2 and Roboflow to create a object detection model without data collection or labeling.
• 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
• 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
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.
• 9 min read
Pose Estimation Algorithms: History and Evolution
SUMMARY
Pose estimation, the computer vision task of detecting key body joints in images and video, has progressed from hand-crafted geometric methods in the 1990s through graphical models in the 2000s to convolutional neural network approaches that now dominate the field. This overview traces that arc, covering traditional methods,
• 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.
• 4 min read
How to Train DETR on a Custom Dataset
Learn how to train a DETR model on a custom dataset.
• 5 min read
How to Deploy YOLOv8 Using Intel's OpenVINO and Amazon SageMaker
Learn how to deploy an Ultralytics yOLOv8 model using OpenVINO and AWS SageMaker.
• 6 min read
How to Train a YOLOv8 Classification Model
In this guide, we walk through how to train a classification model using YOLOv8 and a dataset hosted on Roboflow.
• 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.
• 7 min read
How to Train YOLO-NAS on a Custom Dataset
YOLO-NAS is the latest state-of-the-art real-time object detection model. Learn how to train YOLO-NAS on your custom data.
• 5 min read
Zero-Shot Image Annotation with Grounding DINO and SAM - A Notebook Tutorial
In this comprehensive tutorial, discover how to speed up your image annotation process using Grounding DINO and Segment Anything Model. Learn how to convert object detection datasets into instance segmentation datasets, and use these models to automatically annotate your images.
• 5 min read
Synthetic Data Generation with NVIDIA and Roboflow
Learn how to build computer vision models that leverage synthetic data using NVIDIA Omniverse and Roboflow.
• 6 min read
Grounding DINO : SOTA Zero-Shot Object Detection
Most object detection models are trained to identify a narrow predetermined collection of classes. Zero-shot detectors like Grounding DINO want to break this status quo by making it possible to detect new objects without re-training a model.
• 4 min read
How to Code Non-Maximum Suppression (NMS) in Plain NumPy
SUMMARY
Double detection, where an object detection model fires multiple overlapping bounding boxes on the same object, is a common issue that breaks downstream analytics like counting and tracking. Non-Maximum Suppression (NMS) resolves this by computing Intersection over Union (IoU) across all predicted boxes and discarding lower-confidence duplicates
• 4 min read
Building a Computer Vision Assisted Pill Inspection System
SUMMARY
Detecting damaged pills and foreign matter on a production line requires a computer vision model that runs at inspection speed and with high recall, since incorrect pills reaching consumers pose direct health and compliance risks. This tutorial builds a two-class detection system (damaged pills, foreign matter) using the
• 4 min read
Track and Count Objects Using YOLOv8
Counting moving objects is one of the most popular use cases in computer vision. It is used, among other things, in traffic analysis and as part of the automation of manufacturing processes. That is why understanding how to do it well is crucial for any CV engineer.
• 9 min read
How to Train YOLOv8 Object Detection on a Custom Dataset
In this article, we walk through how to train a YOLOv8 object detection model using a custom dataset.
• 8 min read
Computer Vision Assisted Structural Damage Inspection Using Drones
In this post, Timothy Malche walks through how to inspect structural damage with computer vision and drones.
• 3 min read
Launch: Roboflow Integration with Ultralytics HUB
SUMMARY
Roboflow and Ultralytics HUB now support a direct integration that connects dataset management with model training and model-assisted labeling. Users can export any Roboflow dataset to Ultralytics HUB for custom YOLOv5 training, then bring the trained model weights back into Roboflow to power Label Assist for annotating under-
• 4 min read
Track Football Players with Computer Vision
In this post, we use a YOLOv5 detection model and state-of-the-art tracker ByteTRACK to track football players.
• 6 min read
📸 Roboflow 100: A Multi-Domain Object Detection Benchmark
Roboflow 100 (RF100) is a crowdsourced object detection benchmark. The dataset consists of 100 datasets, 7 imagery domains, 224,714 images, and 829 class labels with over 11,170 labeling hours.
• 5 min read
Using Computer Vision to Save Sea Lions
SUMMARY
Steller sea lion numbers in Alaska's western Aleutian Islands have dropped 94% over 30 years, and NOAA researchers studying the cause generate thousands of remote camera images that must be reviewed manually. A computer vision tool called Steller Sight automates the triage step, classifying each image as
Stay Connected