首页|基于改进注意力模块的船舶涂装缺陷检测方法

基于改进注意力模块的船舶涂装缺陷检测方法

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
针对人工检测船舶缺陷效率低、传统检测网络准确率差的问题,提出一种基于改进注意力模块(improved convolu-tional block attention module,ICBAM)的船舶涂装缺陷检测方法.首先,YOLOv4 在路径聚合网络中将深度可分离卷积代替常规卷积形成IYOLOv4,减少模型计算量;其次,将ICBAM融入IYOLOv4 的路径聚合网络Route层后形成ICBAM-IYOLOv4,ICBAM在通道上构建多频率通道改善全局平均池化,利用一维卷积代替全连接层聚合相邻通道间的信息,减少模型参数;然后,在空间上融合Inception v3 思想和特征分层思想改善空洞卷积;最后,在船舶涂装缺陷样本数据增强的基础上,对IC-BAM-IYOLOv4 进行测试.实验结果表明:ICBAM-IYOLOv4 相比其他算法,其损失值更低、收敛更快;平均精度均值(mean average precision,MAP)在训练集和测试集上分别提高了 1.89%和 1.91%.
Ship painting defect detection method based on improved attention module
To address the problems of low efficiency of manual detection of ship defects and poor accuracy of tra-ditional detection networks,a ship painting defect detection method based on Improved Convolutional Block At-tention Module(ICBAM)is proposed.Firstly,YOLOv4 replaces the conventional convolution with depthwise separable convolution in the path aggregation network to form IYOLOv4,which reduces the model computation;secondly,ICBAM is incorporated into the Route layer of the path aggregation network of IYOLOv4 to form IC-BAM-IYOLOv4,ICBAM builds multi-frequency channels on the channels to improve global average pooling,and one-dimensional convolution is used instead of the fully connected layer to aggregate information between ad-jacent channels and reduce model parameters;then,the idea of Inception v3 and the idea of feature layering were spatially fused to improve the dilated convolution;finally,ICBAM-IYOLOv4 is tested on the basis of en-hanced data from ship painting defects samples.The experimental results show that ICBAM-IYOLOv4 has lower loss values and faster convergence than other algorithms,and the mean average precision(MAP,Mean Average Precision)is improved by 1.89%and 1.91%on the training and test sets,respectively.

ship paintingdefect detectionfeature stratificationmulti-frequency channelsattention moduledepthwise separable convolutionone-dimensional convolution

庞博、卜赫男、李磊、周宏根、景旭文

展开 >

江苏科技大学 机械工程学院,镇江 212100

船舶涂装 缺陷检测 特征分层 多频率通道 注意力模块 深度可分离卷积 一维卷积

工信部高技术船舶科研项目工信部高技术船舶科研项目国防基础科研攻关项目

MC-202003-Z01-02CJ07N20JCKY2021414B011

2024

10.20061/j.issn.1673-4807.2024.03.001

江苏科技大学学报(自然科学版)
江苏科技大学

江苏科技大学学报(自然科学版)

影响因子：0.373
ISSN：1673-4807
年,卷(期)：2024.38(3)