摘要
针对指针式仪表的小目标图像分割特点以及现有方法存在的局限性,提出融合空间细节与语义特征的双边路深度学习主干网络BiUnet,用于指针式仪表图像分割。该网络以BiSeNet V2算法作为出发点,重新设计其语义支路、细节支路以及双边融合层。首先,利用ConvNeXt卷积模块对细节支路进行调整和优化,提升算法对指针及刻度线边界细节的特征提取能力;其次,结合编码器-解码器U型结构能够融合不同尺度语义信息的优势对语义支路进行重新设计,提高语义支路对指针和刻度这类小目标的分割能力;最后,提出双引导拼接聚合层,用于更好地融合细节支路和语义支路特征。在自制仪表图像分割数据集上的消融实验证实了所提出的网络设计方案的有效性和可行性。在仪表数据集上与不同主干网络进行对比实验,实验结果表明,BiUnet对仪表的平均分割精度mIoU(mean intersection of union)达到了88.66%,相比于BiSeNet V2网络的80.02%提升8.64个百分点,并且这两种网络的分割精度均优于基于Transformer和纯卷积的常见主干网络。
Aiming at the characteristics of small target image segmentation of pointer meter and the limitations of existing methods,a bilateral deep learning backbone network called BiUnet is proposed for pointer meter image segmentation,which combines spatial details and semantic features.Starting from BiSeNet V2 algorithm,the semantic branch,detail branch and bilateral fusion layer are redesigned in this network.First,the ConvNeXt convolution block is used to adjust and optimize the detail branch to improve the feature extraction ability of the algorithm for pointer and scale line boundary details.Second,the semantic branch is redesigned based on the advantages of the Ushape structure of encoder and decoder to integrate different scales of semantic information,which improves the special segmentation ability of the semantic branch for small objects such as pointer and scale.Finally,a bilateralguide splicing aggregation layer is proposed to fuse the detail branch and the semantic branch features.The ablation experiments on the selfmade instrument image segmentation dataset confirm the validity and feasibility of the proposed network design scheme.Comparative experiments with different backbone networks are carried out on the instrument dataset,the experimental results show that the mIoU(mean intersection of union)of BiUnet’s instrument segmentation accuracy reaches 88.66%,which is 8.64 percentage points higher than the BiSeNet V2 network(80.02%).Both of them have better segmentation accuracy than common backbone networks based on Transformer and pure convolution.
作者
朱耀晖
吴志刚
陈敏
Zhu Yaohui;Wu Zhigang;Chen Min(School of Energy and Mechanical Engineering,Jiangxi University of Science and Technology,Nanchang 330013,Jiangxi,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2024年第8期362-369,共8页
Laser & Optoelectronics Progress
基金
江西省教育厅科技项目(GJJ200833)
江西理工大学博士启动基金(A08)。
关键词
指针式仪表
双边路主干网络
深度学习
图像分割
pointer meter
bilateral road backbone network
deep learning
image segmentation
