ALERT AATR Final Report: Lawrence Livermore National Laboratory
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
This report addresses the problem of automatically recognizing objects of interest (OOIs) in x-ray computed tomography (CT) images of baggage (plastic bins in our case). The discussion draws heavily from the material in [1]. The material composition and basic physical features of interest (FOIs, such as mass and thickness) of the OOIs are defined in an object requirement specification (ORS). The ORS may also provide a detection – false alarm probability goal for each material of interest (MOI). Automatic threat recognition (ATR) systems identify CT images of baggage that contain OOIs. ATRs must also identify locations of OOIs within baggage. The current ATR certification process used by DHS requires the ATR hardware and software to be certified on a specific ORS. When the ORS changes, the ATR hardware and software must be recertified. To pass re-certification, the hardware, algorithms and codes may need to be modified. Because ATR-based certification and re-certification are so time-consuming, the current process cannot quickly adapt to changing requirements. Unlike ATRs, adaptive automatic threat recognition (AATR) systems can quickly adapt to an ORS that changes or evolves over time [2]. The proposed AATR-based certification process would require the AATR hardware and software to be certified on a specific baseline ORS. Once certified, the same AATR hardware, algorithms and codes would be applied (by TSA or its delegates) to any ORS supplied in the future as input without going through lengthy recertification. This proposed process would enable the AATR to quickly adapt to changing requirements. This report describes the AATR developed at the Lawrence Livermore National Laboratory (LLNL) for x-ray CT images of baggage. The need and technical requirements for an AATR were developed in collaboration with DHS’s Explosives Division and Northeastern University’s Awareness and Localization of Explosives-Related Threats (ALERT) Center, a DHS Center of Excellence (http://www.northeastern.edu/alert/).
- Research Organization:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA); USDHS Science and Technology Directorate (S&T)
- Contributing Organization:
- Northeastern Univ., Boston, MA (United States). Awareness and Localization of Explosives-Related Threats (ALERT) Center
- DOE Contract Number:
- AC52-07NA27344
- OSTI ID:
- 1465307
- Report Number(s):
- LLNL-TR--754219; 939469
- Country of Publication:
- United States
- Language:
- English
Similar Records
Explosive Detection in Aviation Applications Using CT
Automated Threat Recognition For Aviation Security Applications
System and method for identifying objects of interest in images based on likelihood map decluttering
Conference
·
Mon Feb 14 23:00:00 EST 2011
·
OSTI ID:1021067
Automated Threat Recognition For Aviation Security Applications
Technical Report
·
Wed Mar 25 00:00:00 EDT 2020
·
OSTI ID:1643774
System and method for identifying objects of interest in images based on likelihood map decluttering
Patent
·
Tue Jun 06 00:00:00 EDT 2023
·
OSTI ID:1998455