Today, the Department of Homeland Security (DHS) Science and Technology Directorate (S&T) and the Transportation Security Administration (TSA) announced the eight winners of the Passenger Screening Algorithm Challenge. The prize competition solicited new automated detection algorithms from individuals and entities that can improve the speed and accuracy of detecting small threat objects and other prohibited items during the airport passenger screening process. The competition, which was co-funded by S&T and TSA, awarded a total of $1.5 million to the top eight finishers.
“By reaching beyond the screening equipment industry, we have an opportunity to discover new, non-traditional performers that might otherwise be overlooked,” said William N. Bryan, DHS Senior Official Performing the Duties of Under Secretary for Science and Technology. “Working with algorithm developers to improve screening technologies directly serves S&T’s mission to deliver effective and innovative insight, methods and solutions for the critical needs of the Homeland Security Enterprise.”
Algorithms developed from this competition have the potential to improve the speed and accuracy of the Advanced Imaging Technology (AIT) scanners used to screen airline passengers for prohibited items. A comprehensive set of new automated detection algorithms has the potential to be integrated into the latest screening equipment.
Jeremy Walthers of Rockville, MD, will receive the 1st Place prize of $500,000 for the top scoring algorithm. Walthers’ first place lace approach used an array of deep learning models customized to process images from multiple views.
Sergei Fotin located in Nashua, NH, will receive the second place prize of $300,000 with an approach that fuses 2D and 3D sources of data to make object and location predictions.
David Odaibo and Thomas Anthony of Alabaster, AL, are the winners of the $200,000 third place prize, presenting a solution that uses specialized image level annotations to train their 2-stage identification models.
The following entrants rounded out the top eight teams and will each receive $100,000:
- Fourth Place: Zach Teed, Hudson, OH, for a solution that works to define threats using a location-based model
- Fifth Place: Oleg Trott, San Diego, CA, fused 2D and 3D data sources with automated image augmentation to improve model accuracy
- Sixth Place: Halla Yang, Wilmette, IL, and Phillip Adkins, Chicago, IL, designed an approach that automatically segmented the image before running models trained on specific cropped images
- Seventh Place: Suchir Balaji, Sunnyvale, CA, used synthetic data and cross-image analysis to produce more robust predictions
- Eighth Place: Michael Avendi, Irvine, CA, used separately trained models and random image augmentation for best results
Congress requires all person screening technology to have automated target recognition (ATR) capability. ATR enables passenger screening equipment to maintain privacy while maintaining security effectiveness. “The Passenger Screening Algorithm Challenge was an innovative way to challenge a broad community to solve a difficult problem,” said Dr. John Fortune, DHS S&T Apex Screening at Speed Program Manager. “Better ATR algorithms directly contribute to the passenger experience, reducing the need for pat-downs and accelerating the screening process. Through the prize competition, we’re getting better results than we ordinarily might see, by connecting with very smart people who have great ideas but might not typically be part of a Government proposal process.”
The prize competition was run through the Kaggle data science platform and conducted in two stages. The first stage gave six months for entrants, or solvers, to train and build automated threat detection algorithms using a dataset of 1,000 volunteer passenger images in a variety of formats. The second stage was to evaluate those models against a larger holdout set of images for validating algorithm performance. The top eight ranked Solvers at the end of the second stage were eligible to receive prize money.
These algorithms will complement existing systems funded under the DHS S&T Apex Screening at Speed Program, which is pursuing transformative R&D activities that support a future vision for increasing security effectiveness while dramatically reducing wait times and improving the passenger experience. The competition supports DHS S&T and TSA’s goals of increased security effectiveness and rapidly responding to evolving threats.
The next steps will be to conduct test and evaluation of the algorithms with additional image sets. “We hope to continue to engage the combined expertise of our winners to improve the winning solutions and ultimately see them used in airport security checkpoints,” said Fortune.
