Surveillance has always been known as an effective deterrent of crime, and this has become ever more prevalent in an age with more and more cameras, whether it is in your pocket or in the air.
Police and other governmental agencies have begun employing drones to be their eyes, searching the horizon for criminals, and crime that takes place on the streets. They can be found in war zones, monitoring hostiles or in the air spying on foreign drug cartels.
Cambridge researchers have taken this notion one step further and figured out a method to classify live footage from the drone and notify authorities of suspicious and violent behaviour.
This product was undertaken by several researchers and is entitled as the 'eye in the sky: real-time drone surveillance system (DDS) for violent individuals identifications', using ScatterNet Hybrid Deep Learning Network. Firstly, the drone uses pyramid network to identify the humans and focus on them.
It uses ScatterNet – a hybrid deep network – to help the drones analyse the footage let the authorities know what the situation is. Inside the eye of the drone, the human form is broken down into fourteen points from head to toe. These points are connected by lines that signify the arms, legs and body, the drone can tell, based on quick measurement of the angles, if the subject is potentially dangerous.
To analyse these videos proves difficult, due to illumination changes, shadows, poor resolution and blurring, but the recent test has proved quite resilient. With "the rate of criminal activities by individuals and threats by terrorist groups has been on the rise in recent years," it is important to find new ways to stay safe and deter crime; yet rightly so there are some concerns about this technology’s potential legal and humanitarian setbacks should it be used for the wrong reasons.