Nichols Martin
The Pentagon’s Defense Innovation Unit has launched a challenge machine learning professionals to create algorithms to automate the process of assessing post-disaster structural damages. DIU said Monday the xView2 Challenge seeks computer vision tools that can help accelerate satellite- or aerial-based analyses of damage to buildings.
“DIU’s goal in hosting this Challenge is to enlist the global community of machine learning experts to tackle a critically hard problem: detecting key objects in overhead imagery in context and assessing damage in a disaster situation,” said Mike Kaul, artificial intelligence portfolio director at DIU.
DoD will apply winning works to operational and academic efforts such as obstructed road rerouting and resource allocation. The organization will divide $150K in prizes among teams from three categories: open source, non-exclusive government purpose rights and evaluation only.
Participants may submit entries from this month through November. DIU will also give winners the chance to present entries at the NeurIPS workshop event in December. XView2 is the unit’s second prize competition aimed at advancing computer vision technology for potential disaster relief and humanitarian assistance applications.
The first iteration of the challenge sought algorithms that were designed to recognize relevant objects for first responders on the ground.
