摘要
对金属表面细微损伤的检测,传统的目标识别算法泛化能力较弱,而使用深度卷积神经网络的通用检测算法容易丢失小目标特征,其使用的传统正方形结构卷积不适用于处理长条状等不规则损伤。针对以上问题,提出了一种基于注意力机制和可变形卷积的级联神经网络目标检测模型ADC-Mask R-CNN。在ResNet101主干网络中嵌入通道域注意力与空间域注意力,以增强对小损伤目标的检测效果;采用可变形卷积与可变形感兴趣区域池化技术,提升了对不规则损伤的检测效果;通过级联网络实现了检测结果的进一步优化。在金属表面损伤数据集上的对比实验结果表明,ADC-Mask R-CNN模型可以提高金属表面细微不规则损伤的检测性能。
For the detection of minor damages on metal surface,the generalization ability of traditional target recognition algorithms is weak,the general detection algorithms using deep convolution neural network is easy to lose the characteristics of small targets,and the traditional square structure convolution used by these algorithms is not suitable for dealing with irregular damages such as long strips.To solve the above problems,a cascade neural network target detection model based on attention mechanism and deformable convolution,called ADC-Mask R-CNN,is proposed.The model embeds channel domain attention and spatial domain attention in ResNet101 backbone network to enhance the detection effect of minor damage targets,and uses deformable convolution and deformable region of interest pooling technology to improve the detection effect of irregular damages.In addition,the detection results are further optimized by cascaded networks.Comparative experiments on metal surface damage data sets show that the ADC-Mask R-CNN model can improve the detection performance of minor irre-gular damages on metal surface.
作者
邓中港
代刚
吴湘宁
邓玉娇
王稳
陈苗
涂雨
张锋
方恒
DENG Zhong-gang;DAI Gang;WU Xiang-ning;DENG Yu-jiao;WANG Wen;CHEN Miao;TU Yu;ZHANG Feng;FANG Heng(School of Computer Science,China University of Geosciences(Wuhan),Wuhan 430078,China)
出处
《计算机工程与科学》
CSCD
北大核心
2023年第1期127-135,共9页
Computer Engineering & Science
基金
国家自然科学基金(U1711266)
智能地学信息处理湖北省重点实验室开放基金(KLIGIP-2018B14)。
关键词
细微损伤
不规则损伤
注意力机制
可变形卷积
级联神经网络
minor damage
irregular damage
attention mechanism
deformable convolution
cascade neural network
