| 注册
首页|期刊导航|软件导刊|面向挤奶机器人的轻量化奶牛乳头检测算法

面向挤奶机器人的轻量化奶牛乳头检测算法

宋甲宁 王宏 尹理 丁涛 李子阳

软件导刊2026,Vol.25Issue(6):195-201,7.
软件导刊2026,Vol.25Issue(6):195-201,7.DOI:10.11907/rjdk.251169

面向挤奶机器人的轻量化奶牛乳头检测算法

Lightweight Detection Algorithm of Cow Nipple for Milking Robot

宋甲宁 1王宏 1尹理 1丁涛 1李子阳1

作者信息

  • 1. 东北大学 机械工程与自动化学院,辽宁 沈阳 110819
  • 折叠

摘要

Abstract

Aiming at the adaptability of the traditional detection model in the environment of limited computing resources,a lightweight object detection algorithm based on enhanced YOLOv8n was proposed for the accurate detection of cow nipple by intelligent milking robot.Firstly,the structure of YOLOv8n is optimized,and context guidance module is introduced to reduce parameter redundancy and improve feature extrac-tion capability.At the same time,a large separable kernel attention module is used to expand the receptive field and enhance the ability of the model to express key features.In addition,the simple attention module is combined to strengthen the model's attention to important features,and the integrated separated and enhancement attention module in the detection head can further improve the ability of feature extraction and information fusion.The experimental results show that the improved model is superior to the original YOLOv8n in both detection accuracy and computational efficiency.Compared with the benchmark model,the accuracy,recall rate and average accuracy are improved by 2.6%,1.5%and 1.4%,respectively,while the computational complexity and the number of parameters are reduced by 39.3%and 27.8%,respectively,achieving a better lightweight effect.In comparison experiments,the improved model outperforms mainstream target detection algorithms such as YOLOv5,YOLOv6,YOLOv7 and YOLOv11 in several key indicators,showing better detection performance and model efficiency.

关键词

奶牛乳头检测/YOLOv8n/注意力机制/轻量化/挤奶机器人

Key words

cow nipple detection/YOLOv8n/attention mechanism/lightweight/milking robot

分类

信息技术与安全科学

引用本文复制引用

宋甲宁,王宏,尹理,丁涛,李子阳..面向挤奶机器人的轻量化奶牛乳头检测算法[J].软件导刊,2026,25(6):195-201,7.

基金项目

东北大学杰出创新人才研究与培养计划项目(201806) (201806)

软件导刊

1672-7800

访问量0
|
下载量0
段落导航相关论文