Synthetic Data Generation for Property and Passenger Screening

Building and testing reliable machine vision Artificial Intelligence (AI) systems requires access to large amounts of high-quality, labeled data. For homeland security applications, there are several barriers to getting this data: 1) threats are constantly evolving; 2) tailored sensor data (particularly threat data) is expensive to acquire; 3) manual annotation is time consuming; and 4) security datasets are massive and difficult to share. To address these challenges, under a series of Other Transaction Agreements, Cignal created the Cignal Engine prototype which is a suite of simulation and multi-spectral data lifecycle tools to support machine vision AI Development and Operations (DevOps).
The Contractor shall develop and demonstrate software tools that support synthetic data generation suitable for public algorithm development (non-sensitive) and Government development, testing, and evaluation (sensitive). It is anticipated that the contractor shall collaborate with potential end users at S&T, TSA, and elsewhere to validate tools and generated images for suitability for machine learning development, training, testing, and evaluation over the course of the contract.
The objective will be accomplished by specifically accomplishing the following tasks: • Task 1: Program Management • Task 2: Computed Tomography Synthetic Data Generation • Task 3: Millimeter Wave Synthetic Data Generation • Task 4: User Interface and System Integration Development