脱空和不密实是隧道衬砌最常见的两种病害。在这两种病害长期作用下会导致隧道出现破裂、渗漏水、钢筋锈蚀,最终造成隧道塌方等问题,严重威胁行车安全。采用探地雷达对隧道进行无损探测是发现这些病害或缺陷的常见方式,但大量雷达数据...脱空和不密实是隧道衬砌最常见的两种病害。在这两种病害长期作用下会导致隧道出现破裂、渗漏水、钢筋锈蚀,最终造成隧道塌方等问题,严重威胁行车安全。采用探地雷达对隧道进行无损探测是发现这些病害或缺陷的常见方式,但大量雷达数据的人工识别存在着工作量大、效率低、强烈依赖人员的专业素养等问题。本文提出一种基于深度学习的隧道衬砌缺陷的自动检测方法——自监督多尺度池化区域卷积神经网络方法(Self-monitoring Multi-scale ROI Align Region Convolutional Neural Network,SMR-RCNN),以提高缺陷识别的效率,并减少主观因素的影响。在雷达探测隧道衬砌的实践中,数据量巨大,但缺陷样本却很少,这对训练神经网络是一个相当大的挑战。为此,设计了一种数据增强的方法来增加缺陷的样本数量,且使用一种自监督对比学习的网络模型来提取雷达数据的特征,然后将其迁移到改进后的Faster-RCNN网络模型中;最后,使用有标签的样本对改进的Faster-RCNN网络进行细调训练。实验结果表明,相较于传统的Faster-RCNN方法,本文提出的算法增强了神经网络对脱空和不密实两类缺陷的自动识别能力,在检测精度上得到了显著提高,mAP值提升了12%。展开更多
针对小目标水漂垃圾形态多变、分辨率低且信息有限,导致检测效果不理想的问题,提出一种改进的Faster-RCNN(Faster Regions with Convolutional Neural Network)水漂垃圾检测算法MP-Faster-RCNN(Faster-RCNN with Multi-scale feature an...针对小目标水漂垃圾形态多变、分辨率低且信息有限,导致检测效果不理想的问题,提出一种改进的Faster-RCNN(Faster Regions with Convolutional Neural Network)水漂垃圾检测算法MP-Faster-RCNN(Faster-RCNN with Multi-scale feature and Polarized self-attention)。首先,建立黄河兰州段小目标水漂垃圾数据集,将空洞卷积结合ResNet-50代替原来的VGG-16(Visual Geometry Group 16)作为主干特征提取网络,扩大感受野以提取更多小目标特征;其次,在区域生成网络(RPN)利用多尺度特征,设置3×3和1×1的两层卷积,补偿单一滑动窗口造成的特征丢失;最后,在RPN前加入极化自注意力,进一步利用多尺度和通道特征提取更细粒度的多尺度空间信息和通道间依赖关系,生成具有全局特征的特征图,实现更精确的目标框定位。实验结果表明,MP-Faster-RCNN能有效提高水漂垃圾检测精度,与原始Faster-RCNN相比,平均精度均值(mAP)提高了6.37个百分点,模型大小从521 MB降到了108 MB,且在同一训练批次下收敛更快。展开更多
The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided diagnosis.However,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are ...The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided diagnosis.However,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are complex,the edges are blurred,and the sample numbers are unbalanced.To solve these problems,this paper proposes a Multi-branch Cross-scale Interactive Feature fusion Transformer model(MCIF-Transformer Mask RCNN)for PET/CT lung tumor instance segmentation,The main innovative works of this paper are as follows:Firstly,the ResNet-Transformer backbone network is used to extract global feature and local feature in lung images.The pixel dependence relationship is established in local and non-local fields to improve the model perception ability.Secondly,the Cross-scale Interactive Feature Enhancement auxiliary network is designed to provide the shallow features to the deep features,and the cross-scale interactive feature enhancement module(CIFEM)is used to enhance the attention ability of the fine-grained features.Thirdly,the Cross-scale Interactive Feature fusion FPN network(CIF-FPN)is constructed to realize bidirectional interactive fusion between deep features and shallow features,and the low-level features are enhanced in deep semantic features.Finally,4 ablation experiments,3 comparison experiments of detection,3 comparison experiments of segmentation and 6 comparison experiments with two-stage and single-stage instance segmentation networks are done on PET/CT lung medical image datasets.The results showed that APdet,APseg,ARdet and ARseg indexes are improved by 5.5%,5.15%,3.11%and 6.79%compared with Mask RCNN(resnet50).Based on the above research,the precise detection and segmentation of the lesion region are realized in this paper.This method has positive significance for the detection of lung tumors.展开更多
文摘脱空和不密实是隧道衬砌最常见的两种病害。在这两种病害长期作用下会导致隧道出现破裂、渗漏水、钢筋锈蚀,最终造成隧道塌方等问题,严重威胁行车安全。采用探地雷达对隧道进行无损探测是发现这些病害或缺陷的常见方式,但大量雷达数据的人工识别存在着工作量大、效率低、强烈依赖人员的专业素养等问题。本文提出一种基于深度学习的隧道衬砌缺陷的自动检测方法——自监督多尺度池化区域卷积神经网络方法(Self-monitoring Multi-scale ROI Align Region Convolutional Neural Network,SMR-RCNN),以提高缺陷识别的效率,并减少主观因素的影响。在雷达探测隧道衬砌的实践中,数据量巨大,但缺陷样本却很少,这对训练神经网络是一个相当大的挑战。为此,设计了一种数据增强的方法来增加缺陷的样本数量,且使用一种自监督对比学习的网络模型来提取雷达数据的特征,然后将其迁移到改进后的Faster-RCNN网络模型中;最后,使用有标签的样本对改进的Faster-RCNN网络进行细调训练。实验结果表明,相较于传统的Faster-RCNN方法,本文提出的算法增强了神经网络对脱空和不密实两类缺陷的自动识别能力,在检测精度上得到了显著提高,mAP值提升了12%。
文摘针对小目标水漂垃圾形态多变、分辨率低且信息有限,导致检测效果不理想的问题,提出一种改进的Faster-RCNN(Faster Regions with Convolutional Neural Network)水漂垃圾检测算法MP-Faster-RCNN(Faster-RCNN with Multi-scale feature and Polarized self-attention)。首先,建立黄河兰州段小目标水漂垃圾数据集,将空洞卷积结合ResNet-50代替原来的VGG-16(Visual Geometry Group 16)作为主干特征提取网络,扩大感受野以提取更多小目标特征;其次,在区域生成网络(RPN)利用多尺度特征,设置3×3和1×1的两层卷积,补偿单一滑动窗口造成的特征丢失;最后,在RPN前加入极化自注意力,进一步利用多尺度和通道特征提取更细粒度的多尺度空间信息和通道间依赖关系,生成具有全局特征的特征图,实现更精确的目标框定位。实验结果表明,MP-Faster-RCNN能有效提高水漂垃圾检测精度,与原始Faster-RCNN相比,平均精度均值(mAP)提高了6.37个百分点,模型大小从521 MB降到了108 MB,且在同一训练批次下收敛更快。
基金funded by National Natural Science Foundation of China No.62062003Ningxia Natural Science Foundation Project No.2023AAC03293.
文摘The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided diagnosis.However,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are complex,the edges are blurred,and the sample numbers are unbalanced.To solve these problems,this paper proposes a Multi-branch Cross-scale Interactive Feature fusion Transformer model(MCIF-Transformer Mask RCNN)for PET/CT lung tumor instance segmentation,The main innovative works of this paper are as follows:Firstly,the ResNet-Transformer backbone network is used to extract global feature and local feature in lung images.The pixel dependence relationship is established in local and non-local fields to improve the model perception ability.Secondly,the Cross-scale Interactive Feature Enhancement auxiliary network is designed to provide the shallow features to the deep features,and the cross-scale interactive feature enhancement module(CIFEM)is used to enhance the attention ability of the fine-grained features.Thirdly,the Cross-scale Interactive Feature fusion FPN network(CIF-FPN)is constructed to realize bidirectional interactive fusion between deep features and shallow features,and the low-level features are enhanced in deep semantic features.Finally,4 ablation experiments,3 comparison experiments of detection,3 comparison experiments of segmentation and 6 comparison experiments with two-stage and single-stage instance segmentation networks are done on PET/CT lung medical image datasets.The results showed that APdet,APseg,ARdet and ARseg indexes are improved by 5.5%,5.15%,3.11%and 6.79%compared with Mask RCNN(resnet50).Based on the above research,the precise detection and segmentation of the lesion region are realized in this paper.This method has positive significance for the detection of lung tumors.
