Leveraging Business Optimization Technology to Enhance Airport Security and Prohibited Item Detection through AI-Driven YOLO in Baggage Scans
DOI:
https://doi.org/10.32628/IJSRST251261Keywords:
YOLO, Object Detection, Airport Security, AI, Prohibited Items, Baggage Scan, Business Optimization, Computer Vision, Deep LearningAbstract
Modern airport security depends on automated baggage screening technology to warrant passengers safety and need to stop the movement of forbidden items. This work investigates real-time object detection using YOLO (You Only Look Once) to find forbidden objects in baggage. Ideal for real-time applications, YOLO, a deep learning-based object recognition system, identifies and localizes items in a single pass. In terms of airport security, YOLO may be taught to spot firearms, explosives, liquids, and other hazardous things from X-ray luggage scans.Flagging questionable items for human verification, the system runs real-time processing on every frame of the scan.The automated method can help security staff members quickly find dangers by using YOLO's speed and accuracy, hence lowering the need for manual inspection.This strategy keeps great throughput and reduces passenger delays while dramatically enhancing security.
📊 Article Downloads
References
Ambati & Borthakur (2023) – A Study on Tiny YOLO for Resource Constrained X ray Threat Detection. Examines Tiny YOLO variants for edge-deployable X-ray threat detection using the CLCXray dataset. DOI: https://doi.org/10.1145/3639856.3639899
Suraj et al. (2023) – Analysis on airport security of baggage screening using deep learning. Applies deep learning (likely YOLO-family) in baggage screening operations. DOI: https://doi.org/10.54254/2755-2721/4/20230462
X Ray Baggage Object Detection Using Neural Networks (Smart Manufacturing Conf., Mar 22, 2023) – Develops CNN methods for X-ray baggage object detection to support safety enhancements.
Deep Learning for Detecting Dangerous Objects in X-rays of Luggage (MDPI, 2023) – Combines YOLO with VGG architecture, boosting recall in luggage screening.
EM YOLO (MDPI Sensors, 2023) – Edge & material-informed prohibited-item detection network leveraging YOLO for complex X-ray imagery.
ScanGuard YOLO (MDPI Sensors 2024) – Optimizes YOLOv5 to detect prohibited X-ray items, outperforming baseline on OPIXray and HiXray data.
Fine YOLO (MDPI Sensors 2024) – Uses feature aggregation and Wasserstein distance in X-ray detection, referencing cooperative distillation strategies.
SC YOLOv8 (MDPI Electronics, 2024) – Introduces attention and deformable conv with YOLOv8 to inspect prohibited items in X-ray images using the LSIray dataset.
Improved YOLOv8n GEMA (MDPI Electronics, 2024) – Enhances YOLOv8n with attention, GELAN, and Inner-CIoU loss for dangerous goods detection.
DT YOLO (MDPI Sensors, Jun 2024) – Modified YOLOv5 detects staff and aircraft components in airport apron scenes for security monitoring
STING BEE (arXiv Apr 2025) – Vision-language assistant for X-ray baggage inspection using cross-modal learning to improve threat localization
Chen et al. – Research on airport baggage anomaly retention detection based on vision, edge computing & blockchain (2025) – YOLOv5-based system flags retained luggage anomalies with blockchain-secured logs
A System for Real Time Detection of Abandoned Luggage (Sensors 2025) – Compares YOLOv8 & YOLOv11 for abandoned-luggage detection in real-time surveillance
Tracking Passengers & Baggage with Overhead Cameras (arXiv Dec 2022; influential through 2023+) – Employs CNN+multi-camera tracking notably used in baggage/passenger flow analysis .
Over sampling De occlusion Attention Network (2021) – Pioneering attention modules for occluded X-ray detection, underpinning later YOLO modifications
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Science and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
https://creativecommons.org/licenses/by/4.0
