Behavior profiling is an interesting area with a lot of potential, but there are a lot of problems.
This article describes a system that automatically monitors surveillance cameras and attempts to infer the patterns of behavior seen in the footage. The striking thing is the accuracy claim:
“The system works quite accurately,” says Park. Tests were carried out on six different pairs of people performing a total of 54 different staged interactions including hugging, punching, kicking and shaking hands. On average, the system was 80% accurate at identifying these activities correctly.
Imagine all the false alarms as hundreds or thousands of interactions are monitored throughout the day. What will be done when, 20% of the time, an alarm is made about some behavior being observed? Is this any better than human monitoring or social controls that are already in place?