Yolo Pose Estimation and Skeleton

Introduction

Make a pose estimator and use it to make a moving skeleton.

Use Yolo from Ultralytics.

• Python 3.7+
• Yolo v11
• A CUDA-enabled GPU (optional but recommended for faster inference).

pip install ultralytics opencv-python numpy

Yolo

There are 17 keypoints. YOLOv11’s pose model outputs:

• (x, y) coordinates for each keypoint and
• confidence scores indicating the model’s certainty in each keypoint’s position.

Image detection

• 

  AN image before and after the code.

from ultralytics import YOLO
import matplotlib.pyplot as plt
import cv2
from PIL import Image

model = YOLO("yolo11n-pose.pt")  # n, s, m, l, x versions available

results = model.predict(source="sample_image.jpg")  

plt.figure(figsize=(10, 10))
plt.title('YOLOv11 Pose Results')
plt.axis('off')
plt.imshow(cv2.cvtColor(results[0].plot(), cv2.COLOR_BGR2RGB))

The results list includes results[0].keypoints.xy and results[0].keypoints.conf data. Printing that gives some general information about what is found and how fast, and a tensor vector which includes the position data.

image 1/1 /home/mol/Documents/python/skeletor/people2.jpg: 512x640 5 persons, 26.0ms
Speed: 1.4ms preprocess, 26.0ms inference, 38.0ms postprocess per image at shape (1, 3, 512, 640)
tensor([[[1608.5103,  516.1241],
         [1600.1213,  497.7412],
         [1613.1257,  497.1426],
         [1568.5618,  506.6950],
         [1648.6650,  505.3312],
         [1556.0571,  614.9849],
         [1692.7899,  615.2242],
         [1540.9780,  763.7505],
         [1755.1765,  773.1780],
         [1548.3131,  886.3889],
         [1795.6322,  892.2405],
         [1588.8513,  896.8289],
         [1680.1824,  896.3278],
         [1574.6792, 1117.8225],
         [1675.2017, 1118.2271],
         [1589.6167, 1317.0865],
         [1671.6086, 1320.7114]],

        [[1097.3536,  432.4247],
         [1086.8494,  405.5817],
         [1092.0603,  402.9798],
         [ 987.7101,  409.1143],
         [1076.7693,  412.7003],
         [ 924.9458,  531.9528],
         [1117.5946,  533.4085],
         [ 875.2901,  720.3015],
         [1186.5740,  715.3069],
         [ 862.7459,  861.0502],
         [1189.9052,  849.3643],
         [ 957.1283,  837.9849],
         [1090.0930,  841.1834],
         [ 920.7561, 1110.6389],
         [1099.1434, 1116.8433],
         [ 925.5239, 1367.9281],
         [1102.7339, 1381.9753]],

References

• https://medium.com/@staytechrich/human-pose-estimation-with-yolov11-96932a5d7159
• https://www.labellerr.com/blog/how-to-perform-yolos-various-task/