4.6 Article

Tensor pooling-driven instance segmentation framework for baggage threat recognition

期刊

NEURAL COMPUTING & APPLICATIONS
卷 34, 期 2, 页码 1239-1250

出版社

SPRINGER LONDON LTD
DOI: 10.1007/s00521-021-06411-x

关键词

Aviation security; Structure tensors; Instance segmentation; Baggage X-ray scans

资金

  1. ADEK [AARE19-156]
  2. Khalifa University [CIRA-2019-047]

向作者/读者索取更多资源

This paper introduces a novel multi-scale contour instance segmentation framework to address the challenges of cluttered and concealed contraband data in baggage X-ray scans. The framework outperforms state-of-the-art methods on three public datasets and is the first of its kind to leverage multi-scale information for recognizing contraband data from security X-ray imagery.
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.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据