PrintPrint

Awards

Topic Information Award/Contract Number Proposal Information Company Performance
Period
Award/Contract
Value
Abstract

H-SB012.2-002
Automated Threat Recognition (ATR) Algorithms using Standardized Image File Formats

HSHQDC-16-C-00089 DHS SBIR-2012.2-H-SB012.2-002-0001-CRPP
(DHS SBIR-2012.2 CRPP)
Automatic Threat Recognition Algorithm for Volumetric CT Data

TeleSecurity Sciences
7391 Prairie Falcon Rd
Suite 150-B
Las Vegas, NV 89128-0186

09/01/2016
to
05/31/2017
$199,769.75

Through the support of SBIR Phase I and Phase II funding, we have developed a DICOS compliant ATR algorithm and its efficacy has been demonstrated for three different CT vendors. Important milestones achieved are: (1) implementation of the DICOS standard including network protocol, (2) improvement of the proposed ATR algorithm in terms of explosive detection performance and computational efficiency, (3) development of plug-in ATR software with the DICOS standard, and (4) optimal parameter tuning using the receiver operating characteristics analysis. The goal of the CRPP effort will be the commercialization of the ATR algorithm in the security and medical markets The CRPP phase will focus on preparing the ATR through additional testing and evaluation for successful commercialization of TSS ATR. The preparation consists of further tuning and evaluation of the ATR algorithm against appropriate threat data. The TSS developed ATR algorithm has already passed the TSL Qualifications Test in the US, and the algorithm must pass the European Civil Aviation Conference (ECAC) Certification for deployment in Europe. TSS will evaluate and test the ATR algorithm with liquid and explosive data in preparation of the ECAC Certification. The medical market will be addressed by evaluating the existing ATR for the detection of tumor cells using medical Computed Tomography (CT) scans of cancer patients. TSS has been conducting ongoing research into certain medical applications of CT technology. Evaluation of the TSS developed ATR for the detection of tumor cells may lead to new commercial opportunities in the medical arena.

H-SB012.2-002
Automated Threat Recognition (ATR) Algorithms using Standardized Image File Formats

HSHQDC-12-C-00076 DHS SBIR-2012.2-H-SB012.2-002-0001-I
(DHS SBIR-2012.2 Phase I)
Automatic Threat Recognition Algorithm for Volumetric CT Data

TeleSecurity Sciences
7391 Prairie Falcon Rd
Suite 150-B
Las Vegas, NV 89128-0186

09/15/2012
to
07/14/2013
$149,911.19

This Phase I proposal describes the development of an Automatic Threat Recognition (ATR) algorithm for volumetric CT data. Our ATR algorithm consists of four stages: (1) preprocessing of CT data, (2) object segmentation of preprocessed CT data, (3) post-processing of segmentation results, and (4) explosive detection from the segmented objects. The ATR algorithm will be made computationally efficient by GPGPU programming in order to meet desired throughput of the screening process. The performance of the ATR algorithm will be thoroughly analyzed via extensive experiments with CT dataset of typical checked bags with ground truth. Since a preliminary segmentation algorithm is already built, Phase I begins from TRL 3 and concludes with experiments and comprehensive quantitative performance analysis (TRL 4). A DICOS-compliant ATR algorithm and standard CT test datasets for reliable quantification of explosive detection performance is expected at the end of Phase II.

H-SB012.2-002
Automated Threat Recognition (ATR) Algorithms using Standardized Image File Formats

HSHQDC-13-C-00055 DHS SBIR-2012.2-H-SB012.2-002-0001-II
(DHS SBIR-2012.2 Phase II)
Automatic Threat Recognition Algorithm for Volumetric CT Data

TeleSecurity Sciences
7391 Prairie Falcon Rd
Suite 150-B
Las Vegas, NV 89128-0186

09/03/2013
to
04/02/2016
$748,840.76

For Phase II work, we propose to complete the development of the DICOS compliant ATR algorithm whose feasibility has been demonstrated by results of Phase I work. Important project milestones for the first base year of Phase II are as follows: (1) implementation of the DICOS standard including network protocol, (2) improvement of the proposed ATR algorithm in terms of explosive detection performance and computational efficiency, (3) development of plug-in ATR software with the DICOS standard, and (4) optimal parameter tuning using the receiver operating characteristics analysis. The goal of the second option year of Phase II is to be ready for the certification test by continuing improving the ATR algorithm and optimizing parameters via extensive experiments with training datasets. With the successful completion of Phase II work, we expect that our ATR algorithm will outperform existing ATR algorithms of EDS vendors in terms of PD and PFA while meeting the certification requirement of throughput. If our ATR algorithm is certified by TSL and used for EDS, it will contribute to enhance aviation security significantly. Since our ATR algorithm will be able to lower PFA while maintaining PD of the current state-of-the-art EDS, it will be also able to reduce the cost related to manual inspection of alarmed bags.

H-SB012.2-003
Objective, Quantitative Image Quality Measurements and Metrics for Screener Imaging Technologies

HSHQDC-12-C-00080 DHS SBIR-2012.2-H-SB012.2-003-0002-I
(DHS SBIR-2012.2 Phase I)
Image Quality Assessment Toolkit for X-ray Imaging Systems

TeleSecurity Sciences
7391 Prairie Falcon Rd
Suite 150-B
Las Vegas, NV 89128-0186

09/15/2012
to
03/14/2013
$99,961.96

This Phase I proposal describes (1) an automated image quality assessment (IQA) software to objectively quantify image quality of airport security X-ray imaging systems for both checked and carry-on baggage and (2) a design for a novel test phantom specialized for security CT scanners. For fixed images, automated algorithms will measure the Modulation Transfer Function (MTF) and Contrast-to-Noise Ratio (CNR) of scan images; for moving images, automated algorithms will measure the uniformity of the horizontal speed of the object on the screen. These powerful automated IQA algorithms will objectively quantify image quality, without human intervention. For IQA of line scanners for carry-on baggage, we will use the existing ASTM phantom test object; for IQA of CT scanners for checked baggage, we will use a new test phantom, the TSS CT Phantom (TCP), which will be designed and built during this project. Given the widespread use of the MTF and CNR in IQA of medical X-ray imaging systems and that TCP is adapted from a prevalent medical CT phantom, Phase I efforts begin from TRL 2. Phase I mostly involves developing software and hardware-(1) the preliminary design and building of TCP prototype and (2) developing automated IQA algorithms-and concludes with performing experimental tests of the algorithms on available data (TRL 4). An on-site comparative analysis between human screener IQA and automated (algorithmic) IQA of real baggage data is expected at the end of Phase II.