Simpler. Smarter. Further.
Joined February 2014
- Tweets 4,312
- Following 61
- Followers 8,876
- Likes 6,609
1,718 Photos and videos
Pinned Tweet
Jun 11
Monitor parking lots in real time with Ultralytics YOLO26! π
Track vehicle occupancy, detect available spots, and analyze parking activity to optimize space usage and improve traffic flow.
Explore more β‘οΈ bit.ly/3Nb2s8D
#Ultralytics #YOLO26 #MachineLearning #Research
12
123
5,319
Ultralytics retweeted
Plants detection using @ultralytics YOLO26π±
Hereβs how I did it:
β
Collected plant images (you can generate datasets from videos too).
β
Annotated them in bounding box format using Ultralytics Platform.
β
Trained YOLO26 on the detection dataset
#plants #agriculture #MachineLearning
1
21
88
3,028
Jun 12
Train Ultralytics YOLO26 on the TT100K dataset! π¦
Detect traffic signs across diverse road scenes, ideal for autonomous driving research, road safety systems, and intelligent transportation applications.
Start training β‘οΈ bit.ly/4cvNXpY
#Ultralytics #YOLO26 #AutonomousDriving #Research
1
4
37
1,122
Jun 13
Code π
""""""""
from ultralytics import YOLO
# Load a pretrained model
# Recommended for training
model = YOLO("yolo26n.pt")
# Train the model
results = model.train(data="TT100K.yaml", epochs=100, imgsz=640)
""""""""
3
193
Jun 12
New tutorial | Forklift detection with Ultralytics Platform π
Learn how to train YOLO26 on a forklift dataset, run video inference, and deploy a detection pipeline for warehouse and industrial monitoring.
Watch here β‘οΈ youtu.be/sg11dONsKf8
#Ultralytics #YOLO26 #ComputerVision
1
13
678
Jun 11
The Retail Stall Segmentation dataset is live on Ultralytics Platform, and it's a fascinating one! ποΈ
1,200 images. 2,867 annotations. Full instance segmentation support.
This is the kind of dataset that powers real retail intelligence, space utilization, vendor placement & foot traffic analysis.
Though not a proof-of-concept, it is commercially-ready data for the backbone of modern retail operations.
Thank you juan-uriel-legaria-pena, for building this and sharing it openly with the community. Contributions like this raise the bar for everyone. π
Ready to put it to work?
π Explore the Retail Stall Segmentation dataset on Ultralytics Platform:
bit.ly/4v6MyNh
#ComputerVision #RetailAI #InstanceSegmentation #Ultralytics #OpenData #SmartRetail
1
31
1,525
Jun 10
New tutorial | LightOn-OCR: VLM-based OCR π
Explore a vision-language-model OCR system, compare speed vs accuracy, and evaluate text extraction across real document examples.
Watch here β‘οΈ youtube.com/watch?v=TrFhivGZβ¦
#OCR #AI #ComputerVision
4
32
1,577
Jun 10
Estimate human poses with Ultralytics YOLO26! πΊ
Detect keypoints and joint locations in images or videos, ideal for fitness tracking, sports analytics, physiotherapy, and human-motion analysis.
Learn more β‘οΈ bit.ly/3Np1tkP
#Ultralytics #YOLO26 #PoseEstimation #MachineLearning
1
2
24
906
Jun 10
Ultralytics Live Session: Vision AI for aerospace π
Join us on June 23rd at 16:00 CEST to learn how aerospace teams are using Ultralytics YOLO to improve inspection, quality control, and maintenance operations.
Register now β‘οΈ bit.ly/4v1EEEV
3
16
721
Ultralytics retweeted
Animals segmentation & tracking using @ultralytics YOLO26 π«
How I created this demo:
- Data annotation using Ultralytics Platform.
- YOLO26 model training using Platform.
- Downloaded the trained model.
- Run Inference on video files locally.
#animal #ai #MachineLearning
11
34
351
20,910
Jun 9
Detect power line tower components with Ultralytics YOLO26! β‘
Identify insulator strings, crossarms, and crossarm turrets in real time to support power grid inspections, predictive maintenance, and safer monitoring of energy infrastructure. This enables utility teams to detect issues earlier, reduce manual inspection efforts, and improve overall grid reliability.
Read more β‘οΈ bit.ly/4wa8how
#Ultralytics #YOLO26 #AI #Energy
2
30
157
8,047
Jun 9
Edge AI in action: DEEPX and Ultralytics at COMPUTEX π
Last week, we showcased our partnership at COMPUTEX, featuring live demos of Ultralytics YOLO running on DEEPX NPUs. Attendees saw real-world AI applications across multiple industries, highlighting the performance and efficiency of edge AI in action.
Learn more β‘οΈ bit.ly/4uUE0sF
24
1,056
Jun 8
Run promptable segmentation with Ultralytics YOLOE-26! π§
Use text or visual prompts to segment objects dynamically without retraining, ideal for open-vocabulary vision, interactive labeling, and flexible AI workflows.
Learn more β‘οΈ bit.ly/46X0QpJ
#Ultralytics #YOLO26 #Segmentation #ComputerVision
1
3
31
1,038
Jun 9
Code π
""""""
from ultralytics import YOLOE
# Initialize a YOLOE model
model = YOLOE("yoloe-26l-seg.pt") # or yoloe-26s/m-seg.pt for different sizes
# Set text prompt to detect person and bus. You only need to do this once after you load the model.
model.set_classes(["person", "bus"])
# Run detection on the given image
results = model.predict("path/to/image.jpg")
# Show results
results[0].show()
""""""
4
347
Jun 8
How can Vision AI advance marine conservation? π
Project Ocean Oasis is deploying AI-powered buoys to monitor reef biodiversity in real-time.
Powered by Ultralytics YOLO, learn how AI helps detect fish species in a fraction of the time, shipping structured data instead of raw footage.
Read the full case study β‘οΈ bit.ly/4e8sXET
#VisionAI #marineconservation
6
461
Jun 8
New tutorial | Drowsiness detection with Ultralytics Platform π΄
Learn how to train Ultralytics YOLO26 on the Platform to detect awake and drowsy states, then combine detection with tracking for more stable monitoring.
Watch here β‘οΈ bit.ly/4o5Sa7L
#Ultralytics #YOLO26 #SafetyAI
2
14
649
Jun 8
New tutorial | Monocular depth estimation with Depth Anything v3 π
Learn how to generate depth maps from a single RGB image or video frame and explore real-world applications in robotics, navigation, & AR/VR.
Watch here β‘οΈ bit.ly/4vqCGO7
#Ultralytics #DepthEstimation #ComputerVision
1
10
691
Ultralytics retweeted
People counting in zones using @ultralytics YOLO26 π§βπ€βπ§
In this demo, people are moving on elevators. I used a custom-trained YOLO26 model to detect and track each person, then applied the object counting in zones solution to count the number of people within each zone. π
#people #retail #MachineLearning
4
18
164
14,924
Jun 7
#CVPR2026 - Final day! π
We're wrapping up an incredible few days at @CVPR
It's been great connecting with researchers, developers, and innovators from across the computer vision community. We look forward to meeting more of you throughout the day and sharing what's next for vision AI.
Learn more β‘οΈ bit.ly/4vxnyi0
3
17
922
Jun 5
Train Ultralytics YOLO26 on the KITTI dataset! π
Detect cars, pedestrians, and cyclists in real-world driving environments, making it ideal for autonomous driving research, smart traffic monitoring, and urban mobility analysis applications.
Start training β‘οΈ bit.ly/4p41Y1J
#Ultralytics #YOLO26 #AI #AutonomousDriving #MachineLearning
1
1
36
1,564
Jun 6
Code π
"""""""
from ultralytics import YOLO
# Load a pretrained YOLO26 model
model = YOLO("yolo26n.pt")
# Train on kitti dataset
results = model.train(data="kitti.yaml", epochs=100, imgsz=640)
"""""""
3
446