"A truly 'smart' camera would be able to describe with words everything it sees and reason about what it cannot see," said DARPA.
The Mind's Eye software "will compare the video motion to actions it's already been trained to recognize (such as walk, jump, and stand) and identify patterns of actions such as pick up and carry. The software examines these patterns to infer what the person in the video is doing. It also makes predictions about what is likely to happen next and can guess at activities that might be obscured or occur off-camera."
Carnegie Mellon University's National Robotics Engineering Center explained the image below as: "The Mind's Eye program will automate video analysis - recognizing current behavior, interpolating actions that occur off-camera, and predicting future behavior." The next step is to make the 'Cognitive Engine' even smarter.
According to the report "Using Ontologies in a Cognitive-Grounded System: Automatic Action Recognition in Video Surveillance", the researchers "plan to extend the system functionalities in order to support a wider range of action verbs and run tests on a large video dataset."
DARPA explained, "In the first 18 months of the program, Mind's Eye demonstrated fundamentally new capabilities in visual intelligence, including the ability of automated systems to recognize actions they had never seen, describe observed events using simple text messages, and flag anomalous behaviors."
Let's hope the researchers get it right because when added to social media surveillance helping the government read your mind and future TSA plans to track all 'daily travels to work, grocery store and social events', the future surveillance society world could have a very Orwellian no-privacy flavor.
