广东石油化工学院学报2026，Vol.36Issue(1)：68-73,6.DOI:10.26962/j.cnki.1991.2026.0012
基于YOLOv11n-Pose的人体姿态检测方法
Human Pose Detection Method Based on YOLOv11-Pose
刘玉成 1王甜甜 1刘美 2朱一鑫2
作者信息
- 1. 吉林化工大学 信息与控制工程学院,吉林 吉林 132022||广东石油化工学院 自动化学院,广东 茂名 525000
- 2. 广东石油化工学院 自动化学院,广东 茂名 525000
- 折叠
摘要
Abstract
To address the challenges of key point loss and multi-scale object recognition in human pose estimation in complex scenarios,an improved YOLOv11n-Pose model architecture is proposed.By using Partial Convolution(PConv)to optimize Bottleneck in the C3k2 module,the network's ability to extract and fuse multi-scale features has been significantly enhanced.In addition,using RepViT Block module instead of traditional convolutional structure reduces the number of parameters while improving the recognition accuracy of the model for complex poses.Finally,the introduction of CPAM attention mechanism effectively enhances the ability to capture features and analyze semantics of key parts of the human body.The experiment shows that the improved model outperforms the original YOLOv11n-Pose model in detection accuracy,recall rate,and average accuracy,and significantly improves the recognition performance of targets at different scales.Meanwhile,the number of parameters and model size decreased by 10.1%and 8.2%,respectively.关键词
YOLOv11n-Pose/姿态检测/关键点检测/部分卷积Key words
YOLOv11-Pose/human posture detection/key point detection/partial convolution分类
信息技术与安全科学引用本文复制引用
刘玉成,王甜甜,刘美,朱一鑫..基于YOLOv11n-Pose的人体姿态检测方法[J].广东石油化工学院学报,2026,36(1):68-73,6.
