U.S. gov’t sponsors new predictive surveillance technology

Researchers at Carnegie Mellon University have developed new surveillance technology that watches human activity and predicts what will happen next.

According to a Forbes article, the United States Army Research Laboratory sponsored Carnegie Mellon researchers to develop an artificial intelligence system that can watch and predict what a person will “likely” do in the future using specially programmed software designed to analyze various real-time video surveillance feeds.

The system can automatically identify and notify officials if it recognizes that an action is suspicious, detecting what is describes as “anomalous behaviors”. The system can also be deployed to detect suspicious events. Utilizing security cameras at an airport or bus station, the autonomous system can flag luggage that has been abandoned for more than a few minutes.

Ultimately, such software could have multiple applications for military, police, national and even home security. The technology can be used a preemptive alert system, actually sounding off an alarm before a break-in, theft, heist or terrorist event.

Carnegie Mellon is one of 15 research teams and commercial integrators that is participating in a five-year program, started in 2010, to develop smart video software. The program is sponsored by the Information Innovation Office at the Defense Advanced Research Projects Agency (DARPA).

In many ways, the new predictive surveillance technology is reminiscent of Trapwire, the surveillance system purchased by U.S. law enforcement and intelligence agencies, that digitally collates surveillance video and instantaneously delivers intelligence information to a central database for evaluation and preemptive action.

Article Topics

artificial intelligence  |  behavioral biometrics  |  biometrics research  |  education  |  law enforcement  |  military  |  security  |  software  |  surveillance  |  TrapWire  |  video