ALERT Awarded Two New Task Orders
Maturation and Validation of Dielectric Characterization Algorithms Task Order
ALERT has received a task order contract from the Department of Homeland Security (DHS) Science & Technology Directorate (S&T) to mature and operationalize the Advanced Imaging Technology material characterization (complex dielectric constant) algorithms being developed in ALERT Projects R3-A.2 and R3-B.1, led by ALERT Researchers, Dr. Carey Rappaport and Dr. Jose Martinez-Lorenzo of Northeastern University, respectively.
The task order, known as the “Maturation and Validation of Dielectric Characterization Algorithms,” will allow ALERT to use DHS owned images captured originally for the DHS S&T/TSA “Passenger Screening Algorithm Challenge.” The data for this prize competition was originally captured on the Apex Screening at Speed (SaS) High Definition – Advanced Imaging Technology (HD-AIT) laboratory prototype designed by Pacific Northwest National Lab. These images are available in several different file formats, including raw reflectivity formats. The data also includes ground truth information including relative body zone and materials for objects of interest. In the future, this data set may be augmented with additional images from future data collections. The end state for this development is an operationally functioning algorithm that is able to:
- Integrate with provided open file formats to add material characterization capabilities to existing Automatic Threat Recognition (ATR) algorithms;
- Demonstrate performance improvements (namely false alarm rate reduction while maintaining probability of detection) over current ATR algorithms;
- Run in near-real time, almost suitable for an operational environment; and
- Provide TSO-friendly output that will classify a foreign object into one of three categories (unlikely to be explosive, possible explosive threat, and undetermined).
Correlation of Luggage and Specific Passengers (CLASP) Algorithm Maturation and Deployment Task Order
ALERT has also received a DHS S&T task order contract, titled “Correlation of Luggage and Specific Passengers (CLASP) Algorithm Maturation and Deployment,” to mature algorithms developed under the ALERT CLASP Program so that the passenger-baggage tracking capability is sufficiently robust to support operational pilots and to support risk-based screening in an airport environment. DHS S&T has a variety of projects supporting the development of next-generation aviation security capabilities as a part of its Apex Screening at Speed (SaS) Program. Under the Apex SaS Program, passenger and carry-on screening requirements have necessitated adoption of a risk-based screening approach to the aviation checkpoint. In support of these risk-based screening requirements, the Apex SaS Program seeks to develop video analytics algorithms capable of associating passengers and their carry-on items as they travel through the airport checkpoint. Combined with existing TSA technologies, these algorithms will enable risk-based screening to occur on a per passenger and per item basis, improving screening efficiency and increasing overall passenger throughput. As a secondary benefit, effective video analytics will be able to identify thefts or items left behind at the checkpoint.
DHS S&T is seeking the following from the ALERT CLASP Algorithms project to further meet the needs of the Apex SaS Program:
- Algorithms capable of associating passengers and their carry-on items as they traverse the airport checkpoint that are robust to variations in lighting, passenger density, glare, camera angles, etc;
- Requirements and best practices for algorithm deployment in an operational environment (recommended hardware, configurations, etc.); and
- Algorithms capable of leveraging passenger/bag association information to identify actions at the checkpoint (such as interaction with scanning equipment, item theft, or items left behind).