U.S. looks to replace human surveillance with computers

Their Army-funded research, Oltramari and Lebiere claim, can go further than merely recognizing whether any illicit activities are currently taking place. It will, they say, be capable of “eventually predicting” what’s going to happen next.
This approach relies heavily on advances by machine vision researchers, who have made remarkable strides in last few decades in recognizing stationary and moving objects and their properties. It’s the same vein of work that led to Google’s self-driving cars, face recognition software used on Facebook and Picasa, and consumer electronics like Microsoft’s Kinect.