for a long time, surveillance has been known as an effective deterrent of crime. this notion has become ever more prevalent in an age with more and more cameras, weather they’re in our pockets, or in the air. police and other governmental agencies have begun employing drones to be their eyes, searching the horizon for crime. 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 behavior. 

real-time drone surveillance

image courtesy amarjot singh

 
 
the project was undertaken by several researchers and is entitled ‘eye in the sky: real-time drone surveillance system (DSS) for violent individuals identification’ using scatternet hybrid deep learning network. firstly, the drone uses pyramid networks to identify the humans and focus on them. it uses scatternet — a hybrid deep network — to help the drones analyze the footage let the authorities know what the situation is. in the eye of the drone, the human form id 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.  
 
analyzing these videos proves difficult due to illumination changes, shadows, poor resolution, and blurring, but the recent tests have 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.