Document Type
Article
Publication Title
arXiv
Abstract
Automated systems designed for screening contraband items from the X-ray imagery are still facing difficulties with high clutter, concealment, and extreme occlusion. In this paper, we addressed this challenge using a novel multi-scale contour instance segmentation framework that effectively identifies the cluttered contraband data within the baggage X-ray scans. Unlike standard models that employ region-based or keypoint-based techniques to generate multiple boxes around objects, we propose to derive proposals according to the hierarchy of the regions defined by the contours. The proposed framework is rigorously validated on three public datasets, dubbed GDXray, SIXray, and OPIXray, where it outperforms the state-of-the-art methods by achieving the mean average precision score of 0.9779, 0.9614, and 0.8396, respectively. Furthermore, to the best of our knowledge, this is the first contour instance segmentation framework that leverages multi-scale information to recognize cluttered and concealed contraband data from the colored and grayscale security X-ray imagery.
DOI
doi.org/10.48550/arXiv.2108.09603v2
Publication Date
9-21-2021
Keywords
Aviation security, Baggage X-ray scans, Instance segmentation, Structure tensors
Recommended Citation
T. Hassan, S. Akçay, M. Bennamoun, S. Khan, and N. Werghi, “Tensor pooling-driven instance segmentation framework for baggage threat recognition,” 2021, arXiv:2108.09603v2
Additional Links
Published version on Springer
Comments
Preprint: arXiv