论文标题
体积3D计算机断层扫描行李安全筛查图像中的违禁品材料检测
Contraband Materials Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery
论文作者
论文摘要
在文献中已经研究了2D/3D X射线计算机断层扫描（CT）内的自动禁止对象检测，以增强检查点处的航空安全筛选。深度卷积神经网络（CNN）在2D X射线图像中表现出卓越的性能。然而，存在非常有限的证明，证明了在体积3D CT行李筛选图像中如何在材料检测中执行的深度神经网络的表现。我们试图通过基于其材料特征在3D违禁物质检测中应用深度神经网络来缩小这一差距。具体而言，我们将其作为3D语义分割问题提出，以根据可以检测到违禁品材料的所有体素的材料类型。为此，我们首先研究了基于3D CNN的语义分割算法，例如3D U-NET及其变体。与体积3D CT数据的原始致密表示形式相反，我们建议将CT量转换为稀疏点云，该量允许使用点云处理方法（例如PointNet ++）来更有效地处理。公开可用数据集（NEU ATR）的实验结果证明了3D U-NET和PointNet ++在3D CT图像中的材料检测中的有效性，以进行行李安全筛选。
Automatic prohibited object detection within 2D/3D X-ray Computed Tomography (CT) has been studied in literature to enhance the aviation security screening at checkpoints. Deep Convolutional Neural Networks (CNN) have demonstrated superior performance in 2D X-ray imagery. However, there exists very limited proof of how deep neural networks perform in materials detection within volumetric 3D CT baggage screening imagery. We attempt to close this gap by applying Deep Neural Networks in 3D contraband substance detection based on their material signatures. Specifically, we formulate it as a 3D semantic segmentation problem to identify material types for all voxels based on which contraband materials can be detected. To this end, we firstly investigate 3D CNN based semantic segmentation algorithms such as 3D U-Net and its variants. In contrast to the original dense representation form of volumetric 3D CT data, we propose to convert the CT volumes into sparse point clouds which allows the use of point cloud processing approaches such as PointNet++ towards more efficient processing. Experimental results on a publicly available dataset (NEU ATR) demonstrate the effectiveness of both 3D U-Net and PointNet++ in materials detection in 3D CT imagery for baggage security screening.
