<p>The TV show “Person of Interest” depicts a national system by which America’s citizens are behaviorally monitored for abnormalities by which potential victims of crime and perpetrators are detected and thereby addressed by the hero. Most people think this isn’t possible recalling the movie “Minority Report” which based on a similar premise.</p>
People just have no idea—studying the cognitive sciences, especially the intersection of artificial intelligence and neuroscience, leaves me fascinated by all the technology that is currently in play in our society unbeknownst to most.
Case in point, check out this patent: AISight was shown off in Vegas at the ISC International Security Technology conference just a few weeks ago…
In 2005, a team of experienced software developers and scientists with backgrounds in computer vision, artificial intelligence, machine learning, and theoretical physics began working at BRS Labs to create a technology that would allow computers to autonomously learn to recognize unusual behaviors observed by security cameras and warn security teams about those behaviors.
The results of this work – the patented AISight® Behavioral Recognition System – accepts video streams from standard cameras, detects and tracks subjects, characterizes their appearances and properties, classifies them, learns the patterns of behavior they exhibit, remembers those patterns, recognizes behaviors that deviate from those patterns, and alerts the user about those events in real time.
“These advancements would not have been possible ten or fifteen years ago because science didn’t adequately understand how the human brain models and manipulates data, and there wasn’t enough computer power to get the job done,” said Dr. Wesley K. Cobb, Chief Science Officer at BRS Labs. “Now, computers are exponentially faster and we have been successful in developing a method and system for analyzing and learning behavior based on acquired streams of video frames. This was an extremely difficult technical problem to solve, and to our knowledge, no other company has been able to approximate or duplicate what we have done.”
U.S. Patent Number 8,131,012, issued to BRS Labs in March 2012, covers the invention of using artificial intelligence learning modules to recognize behavior patterns in a video stream to identify objects and events that are unusual. BRS Labs has also trademarked the term “Behavioral Recognition™” to describe this invention and revolutionary method of analyzing and learning behavior based on streaming video data.
In addition to the behavioral recognition system patent, other BRS Labs intellectual property filings cover technical breakthroughs in background models, detection, tracking, object characterization, classification, scene characterization, target matching, techniques for unsupervised learning of spatial and temporal behavior, long term associative memories, anomaly detection using long-term memories, sudden illumination change, scene preset identification, trajectory learning, trajectory anomaly detection, spatial and temporal anomaly detection, clustering techniques in self organizing maps, classification anomalies, semantic representation of scene content, and a cognitive model for behavior recognition.
“Our now patented behavioral recognition system technology is deployed in very prominent security surveillance installations to protect the safety of millions of citizens and employees across multiple vertical markets,” added BRS Labs President John Frazzini.