Law enforcement agencies around the world are using technology to prevent crime or improve their response time. Most of them are deployed drones to monitor large groups of people or a large area of interest with limited manpower. Anyway very useful, this technology is limited to one aspect: the ability to decide what is normal and what is not. They can only relay the footage to their handlers who decide what action to take. So, a group of Czech scientists decided to give these machines the ability to detect suspicious behavior. They claim to have developed a surveillance system that analyzes drone footage similar to the human brain.
Developed as a joint research program between the University of Brno Technology and the Police of the Czech Republic, this new system uses neural networks to decode data. In addition to monitoring and crowd control, it can also be used for traffic management, scientists said.
David Bažout, a recent graduate from the University’s Faculty of Information Technology, explains how the system has developed the work of him and his colleagues. He said Radio Prague International That Drones The footage is divided into small “cells”. The system then analyzes and establishes a general picture of what is going on. It then develops a model of standard behavior in a given environment and then compares the discrepancies, if any, to report to the supervisor.
The great advantage of this system is that it learns and implements the program in a real time, eliminating the possibility of significant time loss in the development of a police response.
During the test, the scientists urged football players to observe the system on the pitch. Some of them were then suddenly told to lie down on the floor. According to the report, the system immediately alerted the observer to the discrepancy.
But there can be so much distortion in a crowd because everyone is expected to behave differently. So Bažout and his team have given the system supervisor the option to set the sensitivity level.
Czech police are now reportedly launching their own tests to see the efficiency of the system, with the hope that it will allow its officers to get to a scene much faster.