Automated Threat Recognition (ATR) Initiative
The final report for this initiative will be available after the initiative concludes at: final-reports.
This initiative will address improving CT-based object detection equipment by improving object recognition using and developing advanced automatic target recognition algorithms.
In the field, EDS scanners mostly perform automated threat recognition (ATR) on images to identify threat objects. It follows that improved automated threat recognition (ATR) will improve threat object detection. The goal of this proposal is to involve third parties in the development of object detection system (ODS) technologies that could eventually be deployed by system integrators such as the incumbent vendors. The distinction between ODS and EDS development is the requirement that real explosives or sensitive simulants not be used in the effort proposed at ALERT.
This research builds on previously obtained data from multi-energy CT instruments, research and technology development in iterative and filtered back projection reconstruction, and image segmentation. It is directed at improved target object recognition, using improved artifact reduction, improved image quality, improved segmentation and improved object detection algorithms. All of this work follows recommendations made by the participants at the ADSA workshops.
The research is designed with the following outcomes for DHS.
- The program will improve target object recognition. The improved X-ray CT performance as a result of improved target recognition may decrease minimum threat weight, increase threat population coverage, increased probability of detection and decreased probability of false alarm.
- The program will increase involvement of third parties via the availability of common CT datasets, and tools, which will increase the work in target object recognition, and the number of students who can join the workforce of the vendors and DHS
- The program will foster closer collaboration between academics, national laboratory personnel and incumbent security industry vendors.
Technical interchange will be facilitated near the end of the project so that the researchers can present their results to the security industry vendors, DHS and other third-parties.
Innovation Fast Track
EXCLUSIVE TO CENTER MEMBERS: Log in to explore your Innovation Fast Track, an online portal that gives you one-stop access to center researchers, funding opportunities, exclusive events and more.Learn More
Students, get connected with Industry Partners, find out about research and volunteer opportunities within ALERT, or get advice on how to best showcase your work at Student Central.Learn More
ALERT is led by Northeastern University (NEU) and includes three key academic strategic partners: Boston University, Purdue University, and University of Rhode Island (URI).Learn More