摘要
针对太阳能电池片缺陷分割中存在的特征提取能力弱、分割精度低和漏分割等问题,提出了一种改进U^(2)-Net的太阳能电池片缺陷分割方法。为提高RSU内部有效特征的提取能力并减少参数量,利用残差结构将有效的通道注意模块和深度可分离卷积结合起来,组成新的特征提取层;为防止空间信息的丢失,在外层编解码跳跃连接中添加语义嵌入分支结构,并利用CARAFE算子进行上采样,将更多的语义信息引入低层特征以加强级间特征的融合,减少因跳跃连接丢失的空间信息;最后,将所提方法与常用分割网络对比分析。实验结果表明,该方法的类别像素准确率、交并比和平均交并比分别达74.69%、60.68%、80.30%。相较于U-Net、PSPNet及Deeplab v3+,该方法不仅有效提高了缺陷分割的精度,还实现了小目标缺陷的准确分割,有效减少了漏分割。
Aiming at the problems of weak feature extraction ability, low segmentation accuracy and missing segmentation in solar cell defect segmentation, an improved U^(2)-net solar cell defect segmentation method is proposed. To improve the extraction ability of effective features in RSU and reduce the number of parameters, the residual structure is used to combine the effective channel attention module and the depth separable convolution to form a new feature extraction layer. In order to prevent the loss of spatial information, a semantic embedded branch structure is added to the outer codec hop connection, and CARAFE operator is used for upsampling to introduce more semantic information into low-level features to strengthen the fusion of features between levels, and reduce the spatial information lost due to jump connection. Finally, the proposed method is compared with the commonly used segmentation network. The experimental results show that the classification pixel accuracy, IOU and MIOU of this method are 74.69%, 60.68% and 80.30% respectively. Compared with U-Net, PSPNet and Deeplab v3+, this method not only effectively improves the accuracy of defect segmentation, but also realizes the accurate segmentation of small target defects and effectively reduces missing segmentation.
作者
王盛
吴浩
彭宁
宋弘
张欢欢
李宣韩
Wang Sheng;Wu Hao;Peng Ning;Song Hong;Zhang Huanhuan;Li Xuanhan(School of Automation and Information Engineering,Sichuan University of Science and Engineering,Zigong 643000,China;Key Laboratory of Artificial Intelligence in Sichuan Province,Zigong 643000,China;Aba Teachers College,Aba 624000,China;Sichuan qiruike Technology Co.,Ltd.,Mianyang 621000,China)
出处
《国外电子测量技术》
北大核心
2023年第2期177-184,共8页
Foreign Electronic Measurement Technology
基金
四川省科技厅项目(2020YFG0178,2021YFG0313,2022YFS0518,2022ZHCG0035)
人工智能四川省重点实验室项目(2019RYY01)
企业信息化与物联网测控技术四川省高校重点实验室项目(2018WZY01,2019WZY02,2020WZY02)
四川理工学院四川省院士(专家)工作站项目(2018YSGZZ04)资助
