Contraband Materials Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery
This research addresses the problem of enhancing aviation security screening by automatically detecting prohibited objects for security personnel, specifically focusing on 3D CT baggage imagery where deep learning applications are under-explored.
This paper explores the application of deep neural networks for detecting contraband materials in volumetric 3D Computed Tomography (CT) baggage screening imagery. The authors formulate the problem as 3D semantic segmentation to identify material types for all voxels, demonstrating the effectiveness of 3D U-Net and PointNet++ on the NEU ATR dataset.
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.