BGM: Background Mixup for X-ray Prohibited Items Detection

2024-11-30

arXiv.org

AI Summary

Existing data augmentation methods for prohibited item detection in X-ray security screening images neglect imaging physics and background context. To address this, we propose Background Mixing (BGM), a novel augmentation technique grounded in X-ray transmission imaging principles—specifically, multi-material superposition and pseudo-color material mapping. BGM performs parameter-free, plug-and-play background modeling by fusing luggage contours and material features at the image-patch level. Unlike conventional vision-based augmentations, BGM explicitly leverages background cues to enhance model focus on foreground prohibited items, thereby overcoming limitations of non-reflective imaging scenarios. Evaluated on a multi-source X-ray dataset from diverse security scanners, BGM consistently improves mainstream detectors—including YOLOv8 and RT-DETR—achieving mAP gains of 1.2–2.7 percentage points over strong baselines, with zero additional training overhead.

Technology Category

• Computer Vision: Segmentation
• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Prohibited item detection is crucial for ensuring public safety, yet current X-ray image-based detection methods often lack comprehensive data-driven exploration. This paper introduces a novel data augmentation approach tailored for prohibited item detection, leveraging unique characteristics inherent to X-ray imagery. Our method is motivated by observations of physical properties including: 1) X-ray Transmission Imagery: Unlike reflected light images, transmitted X-ray pixels represent composite information from multiple materials along the imaging path. 2) Material-based Pseudo-coloring: Pseudo-color rendering in X-ray images correlates directly with material properties, aiding in material distinction. Building on a novel perspective from physical properties, we propose a simple yet effective X-ray image augmentation technique, Background Mixup (BGM), for prohibited item detection in security screening contexts. The essence is the rich background simulation of X-ray images to induce the model to increase its attention to the foreground. The approach introduces 1) contour information of baggage and 2) variation of material information into the original image by Mixup at patch level. Background Mixup is plug-and-play, parameter-free, highly generalizable and provides an effective solution to the limitations of classical visual augmentations in non-reflected light imagery. When implemented with different high-performance detectors, our augmentation method consistently boosts performance across diverse X-ray datasets from various devices and environments. Extensive experimental results demonstrate that our approach surpasses strong baselines while maintaining similar training resources.

Problem

• Under-explored data augmentations for X-ray prohibited items detection
• Neglecting background cues in existing X-ray augmentation methods
• Need for domain-specific augmentation in X-ray security imaging

Innovation

• Background Mixup (BGM) for X-ray augmentation
• Mixes background patches for material variation
• Lightweight, plug-and-play solution for detection