Baggage Security Research Articles

Contraband classification method for X-ray security images considering sample imbalance

X-ray security image contraband classification is widely used to assist in maintaining aviation and transportation security. This paper suggests an end-to-end X-ray security inspection image classification method that takes sample imbalance into account in order to address the issues of different scales of contraband in X-ray images, challenging samples, and unbalanced positive and negative samples inherent in passenger baggage security inspection. The feature fusion module is used to enhance the model's ability to express picture edge and texture features while the multi-scale feature extraction network is used to capture the features of numerous sorts of illegal goods with various scales. Based on the cost-sensitive idea, the loss function is designed to solve the problem of dataset imbalance, and improve the classification accuracy of difficult samples. experimental results of the subset constructed on the public dataset SIXray show that the proposed method improves the mean AP index by compared with the current optimal end-to-end classification model, especially for hard-to-classify samples such as scissors, the AP index has a significant improvement effect.

Reduced low-prevalence visual search detriment with increasing age: Implications for cognitive theories of aging and real-world search tasks

When performing multiple successive visual searches, low-prevalence targets are at elevated risk of being missed. This has important implications for real-world visual search tasks, such as diagnostic medical imaging (e.g., searching for a cancer) and airport baggage security screening (e.g., searching for a weapon), which are characterized by low-prevalence targets and potentially dire consequences of target misses. Previous work on low-prevalence visual search indicates that individuals who spontaneously respond more slowly miss fewer targets, which has been attributed to higher quitting thresholds predicting better performance. Previous aging research indicates that older adults typically respond more slowly across multiple task contexts. This has been attributed to both intrinsic limitations in processing speed and a strategic trade-off to prioritize accuracy with increasing age. Synthesizing these two separate lines of research, here we tested whether older adults had a higher quitting threshold and/or slower processing speed in low-prevalence visual search, and the consequences of these for the magnitude of the low-prevalence visual search detriment. We recruited a large sample (N = 380) across a range of ages (20–80 years) and had them search for targets under low- and high-prevalence conditions. Older adults had both slower processing speed and higher quitting thresholds. Older adults were moderately less susceptible to the low-prevalence detriment, and this relationship was mediated by countervailing effects: slower processing speed exacerbated older adults’ low-prevalence detriment, whereas elevated quitting threshold mitigated it. Theoretical implications for cognitive aging and practical implications for professional visual search tasks are discussed.

Multi-Scale Hierarchical Contour Framework for Detecting Cluttered Threats in Baggage Security

Multi-Scale Hierarchical Contour Framework for Detecting Cluttered Threats in Baggage Security

EslaXDET: A new X-ray baggage security detection framework based on self-supervised vision transformers

Deep learning-based X-ray detection of hazardous materials is crucial for public safety, as it can automatically detect them in baggage. However, most existing algorithms for X-ray detection rely on supervised learning, necessitating large amounts of labeled data for training. Obtaining such data is challenging due to the unique nature of X-ray safety images, requiring significant time and money investment from trained staff for accurate labeling. In this paper, we propose a new X-ray dangerous goods detection framework called EslaXDET, whose backbone is trained by a hybrid Self-Supervised Learning (SSL) strategy and whose detection head is designed for a non-multistage backbone. First, the hybrid strategy named ESLA is an abbreviation for Enhanced Self-supervised Learning with masked Autoencoders, which does not require the involvement of labels as it is derived from a hybrid architecture of Contrastive Learning (CL) and Masked Image Model (MIM). Then, the detection head, called Head-Tail Feature Pyramid (HTFP), creates multi-level feature maps comparable to that produced by a multi-level backbone structure by downsampling the output feature of the last stage of the plain Vision Transformers (ViT) multiple times. Finally, the experimental results show that with the backbone of ViT-B, the top-1 accuracy of ESLA on the ImageNet-1K dataset is 77.2%, which is 3% higher than BYOL. Moreover, the average precision (AP, the same evaluation metrics as COCO) of EslaXDET on the PIDray dataset is 69.2%, nearly 8% higher than the original method SDANet, providing a new idea for the subsequent SSL-based X-ray baggage security detection method.

Analisis Penanganan Operasional Baggage Handling System Dalam Meningkatkan Keamanan Bagasi Penumpang Di Bandar Udara Sultan Muhammad Kaharuddin Sumbawa Nusa Tenggara Barat

Baggage handling has a very important role in supporting the safety and comfort of passengers while traveling by airplane, then processing the baggage according to existing procedures until the baggage arrives at its destination using the same aircraft as the passenger. To find out the handling of BHS in improving passenger baggage security, as well as solutions in handling BHS operational operations so as to improve passenger baggage security, baggage handling at Operations (BHS) at Sultan Muhammad Kaharuddin Airport, Sumbawa. It is carried out through a system that has several gradual processes. The process begins when passengers check-in and hand over their baggage to the check-in officer, then the baggage is given a special coded label as baggage identity. Then the baggage will enter the system with the conveyor belt as the path, then the baggage will go through several stages or levels of security and several stages of automatic sorting. After all stages of the process, both at the security level check and at the baggage sorting stage, are deemed safe, the baggage will go to the make up area of each airline or to the destination on the baggage identity tag which the system has read during the sorting process. Each stage of operations (BHS) is able to guarantee the safety and movement of the baggage is always maintained and monitored through a system that is connected to one another. The existence of a connection from the system guarantees that the baggage is in a safe condition, both the contents and physical condition of the baggage and the baggage handling process becomes faster and more efficient in terms of time and effort.

Subjective assessments of cognition and affect and their relationship with objective performance: Individuals with high levels of cognitive failures or negative affect miss more rare visual targets.

The detection of particular targets is critical in applied contexts, such as identifying cancers in diagnostic medical imaging and finding weapons in airport baggage security screening. Missed targets can have dire consequences in such contexts. These contexts are also typically characterized by low prevalence or rare targets such that most searched-through images do not contain targets. A substantive body of evidence demonstrates that humans are much more likely to miss targets when they are rare. Therefore, it is critical to understand the factors that may mitigate or exacerbate this general tendency to miss rare targets. The present study considered the relative role of individual differences in cognitive failures, cognitive empathy, and negative affect (i.e., depression, anxiety, and stress) in predicting the detection of rare targets. Across two experiments, there was evidence that individuals experiencing elevated cognitive failures were more likely to miss the rare targets. In Experiment 1, negative affect was also related to performance, but it was only cognitive failures that made a unique contribution to explaining target-present accuracy when they were pitted against one another. There was no evidence that cognitive empathy was linked to performance. These findings have important theoretical implications and also highlight potential avenues for intervention to improve the detection of rare targets. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

The WACDT, a modern vigilance task for network defense.

Vigilance decrement refers to a psychophysiological decline in the capacity to sustain attention to monotonous tasks after prolonged periods. A plethora of experimental tasks exist for researchers to study vigilance decrement in classic domains such as driving and air traffic control and baggage security; however, the only cyber vigilance tasks reported in the research literature exist in the possession of the United States Air Force (USAF). Moreover, existent cyber vigilance tasks have not kept up with advances in real-world cyber security and consequently no longer accurately reflect the cognitive load associated with modern network defense. The Western Australian Cyber Defense Task (WACDT) was designed, engineered, and validated. Elements of network defense command-and-control consoles that influence the trajectory of vigilance can be adjusted within the WACDT. These elements included cognitive load, event rate, signal salience and workload transitions. Two forms of the WACDT were tested. In static trials, each element was adjusted to its maximum level of processing difficulty. In dynamic trials, these elements were set to increase from their minimum to their maximum values. Vigilance performance in static trials was shown to improve over time. In contrast, dynamic WACDT trials were characterized by vigilance performance declines. The WACDT provides the civilian human factors research community with an up-to-date and validated vigilance task for network defense accessible to civilian researchers.

Recent Advances in Baggage Threat Detection: A Comprehensive and Systematic Survey

X-ray imagery systems have enabled security personnel to identify potential threats contained within the baggage and cargo since the early 1970s. However, the manual process of screening the threatening items is time-consuming and vulnerable to human error. Hence, researchers have utilized recent advancements in computer vision techniques, revolutionized by machine learning models, to aid in baggage security threat identification via 2D X-ray and 3D CT imagery. However, the performance of these approaches is severely affected by heavy occlusion, class imbalance, and limited labeled data, further complicated by ingeniously concealed emerging threats. Hence, the research community must devise suitable approaches by leveraging the findings from existing literature to move in new directions. Towards that goal, we present a structured survey providing systematic insight into state-of-the-art advances in baggage threat detection. Furthermore, we also present a comprehensible understanding of X-ray-based imaging systems and the challenges faced within the threat identification domain. We include a taxonomy to classify the approaches proposed within the context of 2D and 3D CT X-ray-based baggage security threat screening and provide a comparative analysis of the performance of the methods evaluated on four benchmarks. Besides, we also discuss current open challenges and potential future research avenues.

Design of civil aviation security check passenger identification system based on residual convolution network

INTRODUCTION: A civil aviation security check passenger identification system based on residual convolution network is designed to improve the efficiency of airport passenger security check service. OBJECTIVES: The system uses the basic resource layer to provide communication and configuration services, collects the basic information of passengers, the images of passengers' faces and whole body, and the images of baggage security X-ray machine through the data layer, and stores the collected results in the unstructured database; METHODS: The image processing module of the business service layer calls the data in the database, and takes the STM32F103VBT6 microprocessor as the image processing control chip to complete the image data processing. The person, baggage, X-ray machine image and passenger basic information are associated through the person, baggage and X-ray machine information binding service module, and the association results are uploaded to the person and certificates integration unit of the client application layer. RESULTS: The face recognition module identifies the passenger identity through the residual convolution network with the attention mechanism, and realizes the ReID identification of passengers and baggage and the association of people and baggage through the transmission control unit. CONCLUSION: The experimental results show that the system can accurately identify the identity of civil aviation security passengers, and the identification efficiency of security passengers can reach more than 27 frames per second.

MFA-net: Object detection for complex X-ray cargo and baggage security imagery.

Deep convolutional networks have been developed to detect prohibited items for automated inspection of X-ray screening systems in the transport security system. To our knowledge, the existing frameworks were developed to recognize threats using only baggage security X-ray scans. Therefore, the detection accuracy in other domains of security X-ray scans, such as cargo X-ray scans, cannot be ensured. We propose an object detection method for efficiently detecting contraband items in both cargo and baggage for X-ray security scans. The proposed network, MFA-net, consists of three plug-and-play modules, including the multiscale dilated convolutional module, fusion feature pyramid network, and auxiliary point detection head. First, the multiscale dilated convolutional module converts the standard convolution of the detector backbone to a conditional convolution by aggregating the features from multiple dilated convolutions using dynamic feature selection to overcome the object-scale variant issue. Second, the fusion feature pyramid network combines the proposed attention and fusion modules to enhance multiscale object recognition and alleviate the object and occlusion problem. Third, the auxiliary point detection head adopts an auxiliary head to predict the new keypoints of the bounding box to emphasize the localizability without requiring further ground-truth information. We tested the performance of the MFA-net on two large-scale X-ray security image datasets from different domains: a Security Inspection X-ray (SIXray) dataset in the baggage domain and our dataset, named CargoX, in the cargo domain. Moreover, MFA-net outperformed state-of-the-art object detectors in both domains. Thus, adopting the proposed modules can further increase the detection capability of the current object detectors on X-ray security images.

Anchor-Free Weapon Detection for X-Ray Baggage Security Images

Considering the real-time and high-precision requirements of image processing in X-ray baggage security screening; and problems such as the inflexibility and complex computation of anchor-based object detection, this paper introduces an anchor-free mode convolutional neural network object detection method for detecting weapons (knives and handguns) in X-ray baggage security images. The advantage of the anchor-free method over the anchor-based method is that the size of the anchor box does not have to be set, and the generalization ability is strong; the absence of the anchor box reduces the number of computations, and solves the problem of unbalanced positive and negative samples in the anchor-based method. To fully evaluate the effectiveness of the anchor-free method for X-ray baggage screening image detection, a large number of images containing knives and handguns were collected and annotated in the early stages of this work to produce a dataset that could be used for training. Six mainstream anchor-free methods (CornerNet, CenterNet, CornerNet-Lite, ExtremeNet, Objects as Points and You Only Look Once(YOLOx)) are introduced. For experimental integrity, this paper adds an anchor-based comparison experiment, using Faster-RCNN, YOLOv3 and YOLOv5 to perform the same work. The experimental results show that the YOLOx, Objects as Points and ExtremeNet anchor-free methods used in this paper have excellent performance in weapon detection in X-ray baggage security images. Among them, the mean average precision (mAP) of YOLOx combined with the CSPDarknet53 network reached 0.905, and the mAP of ExtremeNet combined with the Hourglass-104 network reached 0.900; the performance of the Objects as Points method was also good. All these methods performed better than the anchor-based methods compared in this paper. Therefore, we believe that the anchor-free method has a practical effect in weapon detection for X-ray luggage images.

Generative adversarial networks and faster-region convolutional neural networks based object detection in X-ray baggage security imagery

X-ray images have now been widely used in public transportation security. However, the ever-increasing number of dangerous object types, along with the complexity of the baggage's contents, makes it unsuitable for clearly displaying various baggages and hazards on X-ray images obtained directly from the inspection system. This article aims to improve the detection of dangerous objects by proposing a data augmentation method for enriching the X-ray prohibited item images using a Generative Adversarial Networks(GANs) based approach. Using the improved GANs model, a new X-ray images were generated with better quality and diversity, and the performance of the proposed method was evaluated using FID(Fréchet Inception Distance) score and Faster R-CNN (Region-based Convolutional Neural Network). Experimental results show that the new augmented X-ray security inspection image dataset can improve the detector performance. If other representative training datasets are utilized, we believe that our methodology could aid in the detection of other kinds of threat objects.

Multi-criteria group decision-making approach to the modernization of hold baggage security screening system at an airport

The decisions on the modernization of a hold baggage screening system (HBSS) at an airport require taking into account multiple assessment criteria of the considered variants. These criteria are both objective - precisely quantifiable, and subjective - requiring descriptive assessment by experts. The purpose of this article was to make a multi-criteria assessment of variants of the modernization of the HBSS, considering various points of view of experts and the context of decisions made. Due to the existence of both the criteria described using linguistic variables and those dependent on complex random processes, both fuzzy inference methods and simulation methods based on microscale models were used. The developed method was implemented to assess the modernization variants for Katowice International Airport. The highest score resulting from the group decision-making was obtained by the modernization variant consisting in reducing the number of baggage control levels with the simultaneous increase in the number of people performing manual checks. If we consider a different decision-making process environment, the group's preferred variant changes. For example, for the scenario involving a significant increase in the size of the traffic being handled, the variant of doubling X-ray devices at the first level of control becomes the most advantageous. The change in the group preference, depending on the context of the decision-making situation, clearly indicates that this context must be taken into account in the decision-making process. The proposed method allows one not only to indicate the preferred variant in each scenario but also to numerically determine the strength of preferences for individual variants, which may facilitate making the right decision considering the chances for implementation of individual scenarios.

An approach for adaptive automatic threat recognition within 3D computed tomography images for baggage security screening.

The screening of baggage using X-ray scanners is now routine in aviation security with automatic threat detection approaches, based on 3D X-ray computed tomography (CT) images, known as Automatic Threat Recognition (ATR) within the aviation security industry. These current strategies use pre-defined threat material signatures in contrast to adaptability towards new and emerging threat signatures. To address this issue, the concept of adaptive automatic threat recognition (AATR) was proposed in previous work. In this paper, we present a solution to AATR based on such X-ray CT baggage scan imagery. This aims to address the issues of rapidly evolving threat signatures within the screening requirements. Ideally, the detection algorithms deployed within the security scanners should be readily adaptable to different situations with varying requirements of threat characteristics (e.g., threat material, physical properties of objects). We tackle this issue using a novel adaptive machine learning methodology with our solution consisting of a multi-scale 3D CT image segmentation algorithm, a multi-class support vector machine (SVM) classifier for object material recognition and a strategy to enable the adaptability of our approach. Experiments are conducted on both open and sequestered 3D CT baggage image datasets specifically collected for the AATR study. Our proposed approach performs well on both recognition and adaptation. Overall our approach can achieve the probability of detection around 90% with a probability of false alarm below 20%. Our AATR shows the capabilities of adapting to varying types of materials, even the unknown materials which are not available in the training data, adapting to varying required probability of detection and adapting to varying scales of the threat object.

Hold baggage security screening system in Kuwait International Airport using Arena software

Abstract This paper presents a simulation for Hold Baggage Security Screening (HBSS) system at Kuwait International Airport to develop a model to improve the current performance of the system. A well conducted investigation for HBSS system is performed to fully understand and analyze the throughput of the system and the factors affecting the baggage movement and queue duration. The HBSS model was adopted using Arena software which provides an “As is” model. First, the HBSS system flow chart was developed and further investigation related to the time and capacity of each of the HBSS levels was performed. Then, the required input data was collected and analyzed to choose the suitable decisions for each level. To ensure system verification, a warm up period of two hours was allowed, 30 replications were applied, and then the results were tested and compared to the real system. After running the “as is” model, the result analysis showed that the highest waiting time was in level 3 and the highest number of “system time-out” status baggage was in level 2. To tackle this situation, more SSO Operators were added to level 2, which reduced the total waiting time from 270 min to 78 min.

On the relevance of denoising and artefact reduction in 3D segmentation and classification within complex computed tomography imagery.

We evaluate the impact of denoising and Metal Artefact Reduction (MAR) on 3D object segmentation and classification in low-resolution, cluttered dual-energy Computed Tomography (CT). To this end, we present a novel 3D materials-based segmentation technique based on the Dual-Energy Index (DEI) to automatically generate subvolumes for classification. Subvolume classification is performed using an extension of Extremely Randomised Clustering (ERC) forest codebooks, constructed using dense feature-point sampling and multiscale Density Histogram (DH) descriptors. Within this experimental framework, we evaluate the impact on classification accuracy and computational expense of pre-processing by intensity thresholding, Non-Local Means (NLM) filtering, Linear Interpolation-based MAR (LIMar) and Distance-Driven MAR (DDMar) in the domain of 3D baggage security screening. We demonstrate that basic NLM filtering, although removing fewer artefacts, produces state-of-the-art classification results comparable to the more complex DDMar but at a significant reduction in computational cost - bringing into question the importance (in terms of automated CT analysis) of computationally expensive artefact reduction techniques. Overall, it was found that the use of MAR pre-processing approaches produced only a marginal improvement in classification performance (< 1%) at considerable additional computational cost (> 10×) when compared to NLM pre-processing.

An evaluation of deep learning based object detection strategies for threat object detection in baggage security imagery

Rising crimes are likely to promote the need for effective security systems for baggage screening at airports. Therefore, technologies enabling public safety are of paramount importance. Out of all the technologies available, X-ray based baggage-screening plays a major role in threat detection. Originally the screening is done manually where a person scrutinizes the X-ray images on a screen to identify potential threat objects. Within this context, with limited dataset availability, we employ an imaging model for a generation of new X-ray images. In this article, an effort is made to perform threat object detection by using deep neural networks based framework. The framework is built upon Convolutional Neural Network (CNN) based techniques such as You Only Look Once (YOLO) and Faster Region based CNN (FRCNN) to perform threat object detection. Apart from this, to improve the model performance with limited original training data the transfer-learning paradigm is also tested out. The performance is studied on 4 classes of threat objects: 1) Gun; 2) Shuriken; 3) Razor-blade; 4) Knife. As compared to traditional Machine Learning (ML) techniques, FRCNN uses region proposal in its first stage to produce better results. On using Faster RCNN with RESNET which was pre-trained on ImageNet dataset, 98.4% accuracy is achieved for 4-class threat recognition requiring 0.16 sec per image. Comparative performance of these threat detection techniques for cluttered X-ray baggage imagery is also presented. We firmly believe that it is possible to fully automate this screening process by using these computer vision techniques

Data Augmentation for X-Ray Prohibited Item Images Using Generative Adversarial Networks

Recognizing prohibited items automatically is of great significance for intelligent X-ray baggage security screening. Convolutional neural networks (CNNs), with the support of big training data, have been verified as the powerful models capable of reliably detecting the expected objects in images. Therefore, building a specific CNN model working reliably on prohibited item detection also requires large amounts of labeled item image data. Unfortunately, the current X-ray baggage image database is not big enough in count and diversity for CNN model training. In this paper, we propose a novel method for X-ray prohibited item data augmentation using generative adversarial networks (GANs). The prohibited items are first extracted from X-ray baggage images using a K-nearest neighbor matting scheme. Then, the poses of the obtained item images are estimated using a space rectangular coordinate system and categorized into four or eight classes for constructing a training database. For generating the realistic samples reliably, different GAN models are evaluated using Frechet Inception Distance scores, and some important tips of handling GAN training in X-ray prohibited item image generation are reported. Finally, to verify whether the generated images belong to its corresponding class or not, a cross-validation scheme based on a CNN model is implemented. The experimental results show that most of the generated images can be classified correctly by the CNN model. This implies that the generated prohibited item images can be used as the extended samples to augment an X-ray image database.

Using Deep Convolutional Neural Network Architectures for Object Classification and Detection Within X-Ray Baggage Security Imagery

We consider the use of deep convolutional neural networks (CNNs) with transfer learning for the image classification and detection problems posed within the context of X-ray baggage security imagery. The use of the CNN approach requires large amounts of data to facilitate a complex end-to-end feature extraction and classification process. Within the context of X-ray security screening, limited availability of object of interest data examples can thus pose a problem. To overcome this issue, we employ a transfer learning paradigm such that a pre-trained CNN, primarily trained for generalized image classification tasks where sufficient training data exists, can be optimized explicitly as a later secondary process towards this application domain. To provide a consistent feature-space comparison between this approach and traditional feature space representations, we also train support vector machine (SVM) classifier on CNN features. We empirically show that fine-tuned CNN features yield superior performance to conventional hand-crafted features on object classification tasks within this context. Overall we achieve 0.994 accuracy based on AlexNet features trained with SVM classifier. In addition to classification, we also explore the applicability of multiple CNN driven detection paradigms, such as sliding window-based CNN (SW-CNN), Faster region-based CNNs (F-RCNNs), region-based fully convolutional networks (R-FCN), and YOLOv2. We train numerous networks tackling both single and multiple detections over SW-CNN/ F-RCNN/R-FCN/YOLOv2 variants. YOLOv2, Faster-RCNN, and R-FCN provide superior results to the more traditional SW-CNN approaches. With the use of YOLOv2, using input images of size $544\times 544$ , we achieve 0.885 mean average precision (mAP) for a six-class object detection problem. The same approach with an input of size $416\times 416$ yields 0.974 mAP for the two-class firearm detection problem and requires approximately 100 ms per image. Overall we illustrate the comparative performance of these techniques and show that object localization strategies cope well with cluttered X-ray security imagery, where classification techniques fail.

A method of hold baggage security screening system throughput analysis with an application for a medium-sized airport

The hold baggage security screening (HBSS) is one of the essential steps in a pre-flight operation process. With the continuous increase in the overall air traffic volume, the development of security screening (and control) technologies, and the changes in applicable regulations of law, the structure and equipment of HBSS systems require frequent upgrades. In order to make good, effective decisions about the upgrades, airport management requires tools for quantitative determination of their results. The aim of this work is to analyse the HBSS system throughput. The analysis can serve as an aid in airport management in on-the-go solving of operating issues and making decisions about HBSS upgrades. A mathematical model was established for the analysis in the form of a coloured timed Petri net, and implemented in a computer-aided solution. It was a microscale simulation model, in which every piece of hold baggage is localised in time and with a resolution of a single belt conveyor. The computer-simulated experiments completed with the model helped (i) determine the actual throughput of the HBSS system operated at the Katowice International Airport, (ii) determine the effects of disturbances on the HBSS system operation, (iii) evaluate the impact of the time windows available to SSO (security screening operators), the SSO's work organisation and the efficiency of automatic security screening on the HBSS system throughput, and (iv) determine the throughput for specific alternative variants of the HBSS organisation, including doubled automatic security screening. These results allow a conclusion, that a four-level HBSS system, which includes automatic security screening, two SSO screening levels based on X-ray imaging, and manual control is an HBSS solution adequate for a regional medium-sized airport. It was also found that, given the growth of airport facility complexity and area, an increase of HBSS throughput is viable rather not by improving the capacity of specific HBSS components, but by deploying them in parallel processing lines. The highest throughput growth potential lies in parallel deployment of automatic security screening lines.