The Department of Homeland Security (DHS) Science and Technology Directorate (S&T) awarded $199,536 Phase 1 funding to Analytical AI of Birmingham, Alabama. Analytical AI received its award under the Silicon Valley Innovation Program’s (SVIP’s) “Object Recognition and Adaptive Algorithms in Passenger Property Screening” solicitation, which focuses on using adaptive image interpretation and object recognition to enhance the Transportation Security Administration’s (TSA’s) detection and screening capabilities.
Analytical AI proposes to generate deep learning algorithms to develop an object identification engine that can rapidly and accurately detect common Stream of Commerce (SoC) items. The application of artificial intelligence techniques has the potential to significantly improve screening efficiency at security checkpoints by reducing the cognitive load on Transportation Security Officers (TSOs). Machine Learning algorithms that can rapidly and accurately label baggage and passenger items have the potential to revolutionize airport screening by increasing throughput, reducing false alarms, and improving detection.
“The airport screening process engages human experts in a repetitive, visually learned task with inherent inefficiencies,” said Karl Harris, S&T Object Recognition Program Manager. “With appropriate training, deep learning techniques can match or exceed human expert accuracy and augment the efficiency of the screening process.”
The proposed product will provide both stand-alone and cloud-based interaction across a network of screening devices, which will rapidly implement new algorithms across the network as they are organically updated with new screening data and priorities.
“Our goal is to help TSA use artificial intelligence techniques to differentiate stream-of-commerce items,” said SVIP Managing Director Melissa Oh. “Analytical AI has proposed to develop robust, network-ready screening tools that would meet current TSA requirements with the flexibility to adapt to future TSA mission priorities.”
SVIP is one of the programs and tools available for S&T to fund innovation and engage with private sector partners to advance homeland security solutions. Companies participating in SVIP are eligible for up to $800,000 of non-dilutive funding over four phases to develop and adapt commercial technologies for homeland security use cases.
For more information about S&T’s innovation programs and tools, visit https://www.dhs.gov/science-and-technology/business-opportunities.