Roboflow

Maximizing sales is extremely important to all businesses, especially in Retail. However, by leveraging the use of planograms, retailers can ensure compliance with vendor agreements, and measure the effectiveness of price changes, product offers, and more. Using computer vision, we can easily create a retail planogram that updates and outputs important information. Learn how to create your own in the comments.

You can now provision your own dedicated infrastructure to run applications built in Roboflow Workflows, a web-based computer vision application builder. Check out the new release 👇

I'm seeing more of our customers use models and methods like SAM2 or SAHI in production. These techniques unlock a lot of new use cases but they can be a pain to host. Roboflow just launched Dedicated Deployments to make it easy and fast for you to host any deployment pipeline. If you want to learn more, Emily Gavrilenko and Shuyang Dou are hosting a live session tomorrow at 11am ET. Open to everyone, see you there: roboflow.com/webinar

For all those who have been asking: SAM2 is now live in the Roboflow annotation tool 🚀

New YouTube tutorial: Football AI step-by-step guide! ⚽ ⚽ ⚽ I poured 200+ hours into this, and it's finally here! In just 1.5 hours, you'll learn how to: - detecting balls, players, goalkeepers, and referees, including fine-tuning on a custom dataset - tracking players in real-time - assigning teams using SigLIP and embedding analysis - identifying 32 key points on the football field with custom dataset fine-tuning - performing homography perspective transformation with OpenCV - implementing advanced analytics, such as radar view, Voronoi diagrams, and ball trajectory mapping 🔥 🔥 🔥 ⮑ 🔗 tutorial: https://lnkd.in/d4RY4-Zu Find links to related resources and cool visualizations in the comments below 👇🏻 #computervision #objectdetection #sportsanalysis #opensource

⚡️I utilized the latest YOLOv10 model, with the help of Roboflow and Ultralytics, to create a detection system for age-related macular degeneration (ARMD) and drusen (DN) using just 200 fundus camera images. 🔬 Why is this important? Age-related macular degeneration is one of the biggest causes of blindness globally. The only problem is that the much-needed early diagnosis often calls for the use of specialized tools as well as specialists. Utilizing YOLOv10 and employing a machine learning approach I designed a simple and user-friendly solution that if implemented could prove quite beneficial in early-stage detection with relatively little sample data set. This project highlights the potential of AI in healthcare, especially in access to critical diagnostic tools. #AI #HealthcareInnovation #MachineLearning #YOLO #Ophthalmology #Roboflow #Ultralytics #HealthcareAI

How many people are there in this image? 🤔 ... I recently helped a customer with small object detection in a challenging image set, and one key discovery for me was the SAHI (Slicing Aided Hyper Inference) technique. Detecting small objects with CNNs can be tricky because small pixel groups provide fewer features for deeper layers, making details easy to miss. SAHI addresses this by: 1. Image Slicing: Dividing the high-resolution image into smaller, overlapping tiles, allowing the model to “zoom in” on details. 2. Hyper Inference: Aggregating results from all slices into a coherent set of detections. By using SAHI, models like YOLOv8 can greatly improve small object detection, overcoming the usual challenges with feature representation and resolution. Answer: at least 1282 people. Check out these resources from Roboflow to learn more about small object detection: - Detect Small Objects: https://lnkd.in/g92gp-pB - How to Use SAHI to Detect Small Objects: https://lnkd.in/g9-XB79B Paper: https://lnkd.in/gB9tGcmH

Classical Computer Vision is finally on Workflows! Try out different traditional computer vision methods at Roboflow without using a single line of code. 🤯

Have you tried running models with SAHI to improve accuracy on small objects? We just launched SAHI support for workflows. Give it a try and see why Emily Gavrilenko is so excited: roboflow.com/workflows

Ball Trajectory Analysis ⚽ ⚽ ⚽ (part of my upcoming Football AI tutorial) I know many of you are waiting for my Football AI tutorial. It's coming and it's going to be really cool! (I think so) It just took me a lot longer to make it than I imagined. 🙏🏼 In the meantime, check out the Roboflow sports repository. Most of the code is already there. ⮑ 🔗 sports repo: https://lnkd.in/dAXmzafq #computervision #objectdetection #sportsanalysis #opensource