Threat Objects Detection in X-ray Images Using an Active Vision Approach

Riffo, Vladimir; Flores, S; Mery, Domingo

doi:10.1007/s10921-017-0419-3

Cited by 22 publications

(15 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applications for object threat-detection include efficient and effective automated detection systems [65], use of modern computer vision techniques for automated object recognition [66], and image reconstruction/enhancement techniques [53], [55], [57], [59][60][61], [67]. Airport cargo security at peak times often have to scan over 1500 individual pieces of luggage per hour, which provides only a limited time frame to check for threats per unit of cargo.…”

Section: Imaging Techniques For Threat Objectsmentioning

confidence: 99%

“…These systems greatly rely on operator experience and expertise to effectively reduce the risk of (or deter) crime and terrorist activity. As a result, human operators for security screening systems may suffer from a) demanding and stressful process (limited window of time for inspection during peak hours at airports) b) arduous and tedious task (sustained focus and attention to discern threatening articles) c) a level of difficulty (operators undergo object threat detection programs and receive minimal technological /negligence/neglect)[61].…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Simulation Algorithm Capable Of Modelling Spatial Impact Points From The Neutralization Of An Improvised Explosive Device

Chan¹,

Ferworn²

2022

Preprint

View full text Add to dashboard Cite

An improvised explosive device (IED) is a bomb constructed from unknown materials, often concealed, such as inside an innocuous container, and deployed in unconventional ways resulting in a potentially deadly weapon. Public safety personnel such as Explosive Disposal Units (EDUs), are trained in the safe handling of explosives and the threats posed by IEDs. One method of neutralizing a suspect IED is to use water fired from a high-powered dispersion weapon commonly known as a disrupter cannon. Our research proposes an algorithm for developing an IED neutralization simulation that can emulate real-world physical effects of the successful neutralization of an IED without danger to the public or first responders. This algorithm includes 6 methodologies with the goal of providing EDU with additional information on the potential physical dispersion of the components of an IED and any major points of impact (splatter) and possible actionable intelligence on the pose and direction of a disrupter cannon for a successful neutralization of an IED. We have developed a prototype simulation based on this algorithm and evaluated the simulation with an appropriate real-world disrupter and compared the real-world splatter to our simulation’s splatter. We argue systems developed with our algorithm may provide relevant information directly from the simulation and can be accurately used to analyze particle dispersion for the purposes of augmenting EDU IED neutralization processes.

show abstract

Section: Imaging Techniques For Threat Objectsmentioning

confidence: 99%

mentioning

confidence: 99%

A Simulation Algorithm Capable Of Modelling Spatial Impact Points From The Neutralization Of An Improvised Explosive Device

Chan¹,

Ferworn²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…On the other hand, in the analysis of single dual-energy images, Baştan et al [4] presented a bag of visual words (BoVW) model with several hand-crafted feature representations. Additionally, there are some methods based on a single energy multi-view, using active vision [25], [26]. Support vector machine (SVM) classifiers and visual dictionaries are proposed in dual-energy multi-views Xray [5], [27].…”

Section: B X-ray Computer Vision Algorithmsmentioning

confidence: 99%

Learning-Based Image Synthesis for Hazardous Object Detection in X-Ray Security Applications

Kim

Cho

Baek³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

X-ray baggage inspection has been widely used for maintaining airport and transportation security. Towards automated inspection, recent deep learning-based methods have attempted to detect hazardous objects directly from X-ray images. Since it is challenging to collect a large number of training images from real-world environments, most previous learning-based methods rely on image synthesis for training data generation. However, these methods randomly combine foreground and background images, restricting the effectiveness of synthetic images for object detection. To solve this problem, in this paper, we propose a learning-based X-ray image synthesis method for object detection. Specifically, for each foreground object to be synthesized, we first estimate positions difficult to detect by the object detector. These positions and their corresponding confidence values are then used to construct a difficulty map, which is used for sampling the target foreground position for image synthesis. The performance analysis using various state-of-the-art object detectors shows that the proposed synthesis method can produce more useful training data compared with the conventional random synthesis method.INDEX TERMS Deep learning, neural network, object detection, X-ray, inspection.

show abstract

“…Photographs are regularly used as evidence in the courtroom and other forums where deliberation and the building of consensus may be required. But when found in contemporary automated systems using artificial intelligence, the forum and the audience are replaced with computers whose goals range from deboning fish fillets (Mery et al, 2011) to discovering "threat objects" in luggage (Riffo et al, 2017). When seen as a passive receiver of reality-as a "pencil of nature"-the camera, when coupled with a computer, takes on additional value as a device for reporting a series of objective facts to be acted upon.…”

Section: Managing Time: Nonhuman Animal Labor In Photographic Imagesmentioning

confidence: 99%

Material Ecologies in the Géniaux Brothers’ Picture Archive of Brittany, ca. 1900

Coughlin¹

2021

Ubiquity

View full text Add to dashboard Cite

show abstract

Threat Objects Detection in X-ray Images Using an Active Vision Approach

Cited by 22 publications

References 29 publications

A Simulation Algorithm Capable Of Modelling Spatial Impact Points From The Neutralization Of An Improvised Explosive Device

A Simulation Algorithm Capable Of Modelling Spatial Impact Points From The Neutralization Of An Improvised Explosive Device

Learning-Based Image Synthesis for Hazardous Object Detection in X-Ray Security Applications

Material Ecologies in the Géniaux Brothers’ Picture Archive of Brittany, ca. 1900

Contact Info

Product

Resources

About