DARPA is spending millions of dollars to identify trash cans, which may have raised a few eyebrows, except these and other common urban objects could in the course of today's combat missions prove to be tactically significant.
BAE Systems received a $7.1 million contract to work on Phase II of the Urban Reasoning and Geospatial Exploitation Technology (URGENT) program, which is designed to improve the quality and timeliness of geospatial intelligence U.S. troops receive when facing enemy threats in urban environments.
This phase of the program's goal will be to "develop a 3D reasoning engine to query over object shapes, locations, and classifications for rapid urban mission planning, mission rehearsal, and situation analysis," according to DARPA.
DARPA's contention is that since target recognition in urban environments is so far removed from what soldiers have historically focused on, i.e. military objects such as tanks and armored personnel carriers, that the need to preemptively identify urban objects has become an important requirement.
That's going to be news to veterans of Chechnya, Hue, and Sarajevo.
Still, the reasoning is that tanks and cannons have unique signatures and were usually positioned in relatively isolated areas away from civilians and that's not so with today's asymmetric threats, where troops are forced to engage enemy combatants in cities with large civilian populations.
"Even the most common urban objects can have tactical significance: trash cans can contain improvised explosive devices, doors can conceal snipers, jersey barriers can block troop ingress, roof tops can become landing zones, and so on," hence the need for an all-knowing system.
BAE contribution will be to fuse Light Detection, and Ranging and Geographic Information Systems' data to automatically detect and classify an urban object's attributes, function and geospatial features, company officials said.
The BAE team has already developed "a system that combines a suite of complementary feature extraction and matching algorithms with higher-level inference and contextual reasoning to detect, segment, and classify urban entities of interest in a fully automated fashion."
Next up could be the market to identify domestic urban threats-like errant shopping carts and guys with squeegees.