基于通道和空间注意力的机场道面地下目标自动检测

Automatic detection of targets under airport pavement based on channel and spatial attention

针对机场道面地下目标检测任务中,探地雷达(GPR)生成的B-scan图背景复杂、包含大量噪声,尤其是单个B-scan图不能反映地下目标的完整信息等问题,构建一种三维通道和空间注意力的UNet(3D-CSA-UNet)模型对地下目标进行自动检测。首先,设计三维通道和空间注意力并行模块(3D-CS-Block),使模型重点关注雷达C-scan中的地下目标信息,抑制背景和噪声的干扰;其次,设计多尺度的三维分割模型从雷达C-scan中提取不同大小的特征图,以增强3D-CS-Block提取目标特征的能力;最后,使用交叉熵损失函数计算每个尺度下特征图的损失值,从而提高模型的检测精度。在采集的实际机场道面地下目标数据集上,相较于3D-FCN、3D-UNet等模型,3D-CSA-UNet对于脱空、钢筋和钢筋平行目标预测的平均F1至少提高12.33、9.05、11.05个百分点。实验结果表明,3D-CSA-UNet可以较好地满足工程实际要求。

In the task of detecting targets under airport pavement,B-scan maps generated by Ground Penetrating Radar(GPR)have complex backgrounds and lots of noise,especially a single B-scan map cannot reflect the complete information of an underground target.To solve these problems,a Three-Dimensional Channel and Spatial Attention UNet(3D-CSAUNet)model was established to automatically detect the underground targets.Firstly,a Three-Dimensional Channel and Spatial parallel attention Block(3D-CS-Block)was designed to make the model focus on the underground target information in radar C-scan and suppress the interference of backgrounds and noise.Secondly,in order to enhance the capability of 3DCS-Block in feature extraction,a multi-scale 3D segmentation model was designed to extract feature maps of different sizes from the radar C-scan.Finally,the cross-entropy loss function was employed to calculate the loss value of feature map under each scale to improve the detection accuracy of the model.On a real dataset of targets under airport pavement,compared with 3D-Fully Convolutional Network(3D-FCN),3D-UNet and other algorithms,3D-CSA-UNet has the average F1 score in terms of the pixel level segmentation for void,rebar and parallel rebar targets increased by at last 12.33,9.05 and 11.05 percentage points.Experimental results show that 3D-CSA-UNet can meet the real engineering requirements well.