The Department of Homeland Security’s Science and Technology Directorate and the Transportation Security Administration announced the winners of their passenger screening algorithm challenge that solicited new automated detection algorithms to improve speed and accuracy of detecting “small threat objects” during airport passenger screening processes.

DHS handed out a total of $1.5 million in prize money, including $500,000 to first prize winner Jeremy Walthers of Rockville, Md., whose “approach used an array of deep learning models customized to process images from multiple views.”

The second prize of $300,000 was awarded for “an approach that fuses 2D and 3D sources of data to make object and location predictions,” and the third prize of $200,000 was awarded for a solution “that uses specialized image level annotations to train their 2-stage identification models,” DHS said.  Five other entrants received prizes of $100,000 each.

Read More About
More Topics
John Curran
John Curran
John Curran is MeriTalk's Managing Editor covering the intersection of government and technology.