Real-time YOLO pose estimation
Track body keypoints and skeletons in live video with Ultralytics YOLO26 pose models. Build fitness, sports analytics, safety, and ergonomics applications with one fast training and deployment workflow.
YOLO26 pose models
YOLO26-pose models detect people and predict body keypoints in one pass, fast enough for live video on modest hardware. Five sizes cover edge devices through accuracy-critical analysis, and custom keypoint sets train through the standard Ultralytics workflow.
pip install ultralyticsfrom ultralytics import YOLO
# Load a YOLO26 pose model
model = YOLO("yolo26n-pose.pt")
# Run inference
results = model("image.jpg")| Model | Size (px) | mAP pose (e2e) | mAP pose 50 (e2e) | CPU ONNX (ms) | T4 TensorRT (ms) | Params (M) | FLOPs (B) |
|---|---|---|---|---|---|---|---|
| YOLO26n-pose | 640 | 57.2 | 83.3 | 40.3 ± 0.5 | 1.8 ± 0.0 | 2.9 | 7.5 |
| YOLO26s-pose | 640 | 63.0 | 86.6 | 85.3 ± 0.9 | 2.7 ± 0.0 | 10.4 | 23.9 |
| YOLO26m-pose | 640 | 68.8 | 89.6 | 218.0 ± 1.5 | 5.0 ± 0.1 | 21.5 | 73.1 |
| YOLO26l-pose | 640 | 70.4 | 90.5 | 275.4 ± 2.4 | 6.5 ± 0.1 | 25.9 | 91.3 |
| YOLO26x-pose | 640 | 71.6 | 91.6 | 565.4 ± 3.0 | 12.2 ± 0.2 | 57.6 | 201.7 |
YOLO26 pose benchmarks from the Ultralytics docs.
Trusted by the world's leading organizations
Our models' impact
Streamline processes across industries with our cutting-edge vision AI models. Speed, accuracy and ease-of-use powered by Ultralytics.
The evolution of Ultralytics YOLO models
See how Ultralytics YOLO evolved from the practical YOLOv5 workflow to edge-ready YOLO26 inference.
Label up to 10x faster with smart annotation
Ultralytics Platform gives you the image annotation tool to build high-quality datasets faster. From smart annotation to precise manual editing, these features are designed to reduce image labeling time without sacrificing quality.
- SAM-powered smart annotation: Masks and bounding boxes in one click.
- Full AI task coverage: Detection, instance segmentation, semantic segmentation, classification, pose, OBB.
- Universal format support: Your choice of YOLO, COCO, and more.
- Team review and versioning: Clear collaboration at every step.
Train on the Best GPUs for Less
26 NVIDIA GPUs starting at $0.24/hr — from Ampere to Blackwell. No markup, no minimums, no commitment.
Explore industry solutions
See how teams apply Ultralytics computer vision across production environments.
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Frequently asked questions
Pose estimation detects people or objects and predicts the location of their keypoints — for humans, typically 17 body joints such as shoulders, elbows, and knees. Connecting the keypoints yields a skeleton that describes posture and movement. Ultralytics YOLO pose models detect and estimate keypoints in a single pass, fast enough for live video.
Common applications include exercise-form analysis and repetition counting in fitness, technique analysis in sports, fall detection and ergonomic monitoring in workplace safety, and gesture-driven interfaces. Because Ultralytics pose models run in real time, these applications work on live camera streams, including on edge devices.
Ultralytics YOLO26 pose models are the recommended starting point, pretrained on COCO keypoints and available from nano to extra-large sizes. YOLO11 pose models remain supported with the identical API.
Yes. The keypoint set is defined by your dataset, so you can train models for animals, machinery, or any structure with consistent landmarks. Annotate keypoints, configure their number and skeleton in the dataset file, and run train mode, or manage the whole workflow on Ultralytics Platform.
Export pose models with export mode to ONNX, TensorRT, CoreML, OpenVINO, LiteRT, and more. Keypoint outputs are part of the exported model, so mobile and edge apps consume poses directly without extra post-processing libraries.
Build pose estimation with Ultralytics
Annotate keypoints, train YOLO26 pose models, and deploy them anywhere with Ultralytics Platform.