Awards Registry

DeepSpektra - Enhanced Explosives and Illicit Drugs Detection by Targeted Interrogation of Surfaces
Profile last edited on: 3/15/2021

Program
SBIR
Agency
DHS
Total Award Amount
$1,155,315
Award Phase
2
Principal Investigator
Tim Brewer
Activity Indicator

Company Information

Synthetik Applied Technologies LLC (AKA:Ichor~Synthetik)

701 Brazos Street
Austin, TX 78701
   (605) 593-5500
   N/A
   www.synthetik-technologies.com
Multiple Locations:   
Congressional District:   21
County:   Travis

Phase I

Phase I year
2020
Phase I Amount
$155,909
Synthetik propose to leverage a new generation of high-resolution, low-cost (e.g. less than $1,000, 25-100x less than currently available systems) hyperspectral cameras in conjunction with state-of-the-art machine learning to rapidly image, process and predict locations where residues of interest are present to deliver a targeted, relevant and more dense samples to the trace detector.During Phase I, Synthetik plan to adapt their Spektra high-resolution, low-cost hyperspectral camera system (developed as part of a NAA-funded industrial and food safety techNlogy development project) for application to this DHS requirement.Training of state-of-the-art machine learning models suitable forhyperspectral data will allow discrimination between background material and areas of interest containing residues and this will provide targeting information to the screener. This concept will be demonstrated to DHS at the close of Phase I.Hyperspectral imaging provides a modality that is well-suited to this task. The techNlogy is a natural, multi-dimensional spatial extension of standard spectroscopy techniques, whereby each pixel of the captured image represents a complete spectral signature at a given spectral resolution (e.g. wavelength). In this way, a hyperspectral image can be viewed as a data cube which contains both spatial information and spectral (e.g. wavelength, intensity) information for each captured image.Critically, when paired with modern deep learning-based semantic segmentation models, the captured image can be used to identify and classify materials, including traces of explosive or illicit drugs, and then show the operator where these materials are on the article of interest

Phase II

Phase II year
2021 (last award dollars: 2021)
Phase II Amount
$999,406
The Synthetik team is uniquely placed to conduct this Phase II SBIR effort where we plan to extend and optimize our DeepSpektra high-resolution hyperspectral and deep learning-based non-contact detection technology to provide enhanced, targeted sampling for explosive and illegal drugs trace detection that was successfully demonstrated in Phase I.Synthetik's DeepSpektra technology directly addresses a significant pain point for TSA, namely optimal sample collection for effective trace detection at passenger security checkpoints. The technology will greatly enhance non-contact explosives and illicit drugs detection technologies by directing these modalities toward surfaces that have residues of interest for further interrogation.DeepSpektra technology is not intended to replace current in-service trace detectors, but rather to augment their capabilities such that they can be more effective in the field.More effective and accurate trace detection and classification is dependent on the collection of more feature rich data.This will be achieved during Phase II by: 1) determining the wavelengths that provide optimal data for detection, 2) improving machine learning (ML) model architecture, pre-processing, and training, and 3) enhancing hardware design, including increased illumination.During Phase II, we will also seek to quickly realize the immediate commercial potential in this technology by rapidly fabricating and distributing the DeepSpektra system to both federal and commercial markets in the US and globally.