Ultralytics

Semantic Segmentation is here! 🚀 Assign a class label to every pixel, producing a dense H×W class map of the entire scene. entire scene. Perfect for autonomous driving, medical imaging, and land-cover mapping. Learn more ➡️ bit.ly/4nF4BHa #Ultralytics #semanticsegmentation #computervision

Ultralytics YOLO Vision 2026 returns September 13 🚀 Join our hybrid global event for the next generation of Ultralytics YOLO, major launches, live demos, breakthrough research, and real-world deployments. Open vision, built for the real world. Register now 👉 bit.ly/4fsgH2S

Floor plan segmentation using @ultralytics YOLO26! Architectural floor plans represent rich, unstructured spatial datasets. Applying instance segmentation enables precise identification of structural elements (walls, doors, corridors, and rooms), converting raw CAD images into structured digital assets. These outputs directly support spatial modeling, digital twin integration, and automated facility management. #Construction #AI #MachineLearning

New tutorial | Retail shelf analytics with Ultralytics YOLO26 + SKU-110K dataset 🛒 Learn how to train a custom detection model on the SKU-110K dataset and build AI-powered retail shelf analytics with the Ultralytics Platform. Watch here ➡️ bit.ly/4vETwZ6 #Ultralytics #YOLO26 #RetailAI

Run Ultralytics YOLO26 inference directly through the Ultralytics Platform! ⚡ Upload images, test models, and visualize predictions in real time through a streamlined web interface, ideal for rapid experimentation and deployment workflows. Get started ➡️ bit.ly/4wB1ioA #Ultralytics #YOLO26 #Platform #MLOps

#AI-Powered Crosswalk Safety with Ultralytics YOLO26 by @ultralytics #ArtificialIntelligence #Innovation #FutureTech #TechForGood

Join us tomorrow for our next Ultralytics Live Session! 📢 @intel, Ultralytics and @OversonicR will explain how to enable fast, efficient Ultralytics YOLO inference on Intel® hardware, from export to real-world deployment Register now ➡️ bit.ly/4yhsFoI

Detect shipping containers with Ultralytics YOLO26! 📦 Identify containers in real time from ports, warehouses, or transport hubs to support logistics tracking, inventory visibility, and smarter supply chain operations. Get started ➡️ bit.ly/4pRp9N6 #Ultralytics #YOLO26 #Logistics

For 14+ years, @Raspberry_Pi has made computing accessible to developers everywhere. Now, with @Ultralytics YOLO and OpenVINO, you can run AI vision workloads directly on Raspberry Pi devices, bringing AI closer to where data is generated. Learn more: ms.spr.ly/6016v4tF0

@_Suresh2 True! In this case, maybe you can check Ultralytics YOLO26 instance segmentation. It separates each object individually. 💙

@ultralytics prompt-based segmentation gets messy when both objects match the prompt.

Run SAM3 inference with Ultralytics! 🧠 Segment objects using prompt-based inference for flexible visual understanding, ideal for open-vocabulary segmentation, interactive workflows, and computer vision-powered annotation. Learn more ➡️ bit.ly/49MKOjm #Ultralytics #Segmentation #ComputerVision #SAM3

Code 👇 """"" from ultralytics.models.sam import SAM3SemanticPredictor # Initialize predictor with configuration overrides = dict( conf=0.25, task="segment", mode="predict", model="sam3.pt", quantize=16, # Use FP16 for faster inference save=True, ) predictor = SAM3SemanticPredictor(overrides=overrides) # Set image once for multiple queries predictor.set_image("path/to/image.jpg") # Query with multiple text prompts results = predictor(text=["person", "bus", "glasses"]) # Works with descriptive phrases results = predictor(text=["person with red cloth"]) """""

Detect power line tower components with @ultralytics YOLO26! Identify insulator strings, crossarms, and crossarm turrets in real time to support power grid inspections, predictive maintenance, and safer monitoring of energy infrastructure. #AI #Energy #MachineLearning

@muhammdrizwanmr @ultralytics 这是我的。细微烟雾还差点，置信度调低容易误报

Detect smoke in real time with @ultralytics YOLO26! 🌫️ Identify early signs of smoke in video streams to support fire prevention, environmental monitoring, and rapid emergency response systems. #Smoke #Fire #MachineLearning

Code 👇 """""" from ultralytics import YOLO # Load the YOLO26 model model = YOLO("yolo26n.pt") # Configure the parameters and run the tracker results = model.track( source="youtu.be/LNwODJXcvt4", show=True, conf=0.3, iou=0.5) """"""

Object tracking with Ultralytics YOLO26! 🎯 Assign persistent IDs to objects across video frames using built-in trackers like BoT-SORT or ByteTrack, ideal for traffic analysis, surveillance, sports analytics, and retail monitoring. Learn more ➡️ bit.ly/4ft7lW2 #Ultralytics #YOLO26 #ObjectTracking

New tutorial | Traffic analytics with Ultralytics YOLO26 using the VisDrone dataset 🚗 Learn how to train a custom vehicle detection model on the VisDrone dataset using Ultralytics Platform, then track and count vehicles in real time using the Ultralytics Python package. Watch here ➡️ bit.ly/4vAAIKG #Ultralytics #YOLO26 #TrafficAnalytics #AI

Analyze human movement with Ultralytics YOLO26 pose estimation1🧍 Detect body keypoints in real time to understand posture, motion, and activity, powering applications like construction site monitoring, fitness monitoring, and behavior analysis. #People #Warehouse #MachineLearning

Count potatoes on conveyor belts with Ultralytics YOLO26! 🥔 Track potatoes as they move into boxes or carts in real time, ideal for automating agricultural sorting, packing, and inventory workflows. Read more ➡️ bit.ly/4sPUGAM #Ultralytics #YOLO26 #AgriTech #Manufacturing

Raspberry Pi is a common target for practical computer vision. It can sit next to a camera, inside a prototype, near a machine, on a lab bench, or in a small service that needs to run without a workstation nearby. Friends of ours from @intel and @ultralytics created a guide showing you how to deploy Ultralytics YOLO computer vision models on Raspberry Pi with OpenVINO. Follow the link to learn how the runtime is installed, how models become deployment artefacts, how compilation and caching affect startup, and how builds become repeatable. 👉 raspberrypi.com/news/run-ultra…