基于轻量化YOLOv5s的集装箱锁孔识别算法
Container Lock Hole Recognition Algorithm Based on Lightweight YOLOv5s
李源鑫 1郭忠峰 1杨钧麟1
作者信息
- 1. 沈阳工业大学机械工程学院 沈阳 110870
- 折叠
摘要
为提高现有集装箱的锁孔识别检测效率,减少算法参数量以及减小模型大小,提出了一种基于轻量化YOLOv5s的集装箱锁孔识别算法.该算法将YOLOv5s的Backbone主干特征提取网络部分更换为轻量级神经网络模型MobileNetV3,并对neck部分的特征融合结构进行进一步的优化,减少了模型的参数量和计算量,并提高了检测速度.引入注意力机制SimAM层,提高了检测的准确率和效率.使用不同的改进方法对模型进行重构后,在自建的集装箱锁孔数据集上进行训练和测试,并与改进的YOLOv5s进行对比实验.结果表明,改进后的模型大小仅为2.4MB,每幅图像的平均检测时间仅为5.1ms,平均检测精度达97.3％;与原始目标检测模型相比,该模型的大小减小了82.8％,检测速度提高了39％,在确保高检测精度的前提下展现出了较强的算法实时性.
Abstract
In order to improve the efficiency of container lock hole recognition and reduce the number of algorithm parameters and model size,a container lock hole recognition algorithm based on lightweight YOLOv5s is proposed.This algorithm replaces the Backbone feature extraction network of YOLOv5s with a lightweight neural network model MobileNetV3,and further optimizes the feature fusion structure of the neck part,which reduces the number of parameters and calculation amount of the model and improves the detection speed.The accuracy and efficiency of detection are improved by introducing the attention mechanism Si-mAM layer.After the model is reconstructed with different improvement methods,the training and testing are carried out on the self-built container lock hole data set,and the comparison test is carried out with the improved YOLOv5s.The results show that the size of the improved model is only 2.4MB,the average detection time of each image is 5.1ms,and the average detection accu-racy is 97.3％.Compared with the original target detection model,the size of the model is reduced by 82.8％,and the detection speed is increased by 39％,showing strong real-time algorithm on the premise of ensuring high detection accuracy.
关键词
机器视觉/集装箱锁孔/YOLOv5s/轻量化/深度学习Key words
Machine vision/Container lock hole/YOLOv5s/Lightweight/Deep learning引用本文复制引用
基金项目
辽宁省教育厅科学研究经费面上项目(2021)(LJKZ0114)
出版年
2024
NETL
NSTL
万方数据