Carnegie Mellon unveils system that locates a shooter in minutes

Active shooters can be located within minutes by new software that analyzes smartphone video from the scene and can even identify the type of gun

  • VERA is designed to locate a shooter within minutes of them firing the first shot
  • Using information from smartphones in the area of the terrible event
  • Looks at delay between shots and audio to determine the type of gun 
  • It also looks at the speed of the bullet to pinpoint the exact location 

It took nearly 10 minutes to locate the shooter’s position during the mass shooting in Las Vegas two years, but new technology could have put an end to the ‘pro-longed massacres’ after three bullets were fired.

Researchers at Carnegie Mellon University have developed a system that can accurately locate a shooter within minutes using video recordings from at least three smartphones.

Using machine learning, the system looks at the time delay between shots, audio to determine the type of gun and estimates the bullet speed to calculate the shooter’s distance from each of the smartphones –allowing it to pinpoint the gunman’s location.

The team demonstrated this technology using just three video recordings from the 2017 Las Vegas shooting, which left 58 dead and hundreds of injured. 

The system, called Video Event Reconstruction and Analysis (VERA) gathered information from just three smartphones belonging to individuals who were in the area of the shooting.

Using machine learning, the system looks at the time delay between shots, audio to determine the type of gun and estimates the bullet speed to calculate the shooter’s distance from each of the smartphones –allowing it to pinpoint the gunman’s location

It was able to correctly determine that the suspect, Stephen Paddock, setup in the north wing of the Mandalay Bay hotel in just a few minutes from the first shot – and the analysis only needed three gunshots to come to this conclusion.

VERA harnesses the power of machine learning to synchronize video feeds from different smartphones during a shooting and calculates the position of each camera based on what is in the clips.

However, it is the audio from these videos that play a major role in locating the source of the gunshots.

The system collects the time delay between the crack caused by a supersonic bullet’s shock wave and the muzzle blast, which travels at the speed of sound. 

It was able to correctly determine that the suspect, Stephen Paddock, setup in the north wing of the Mandalay Bay hotel in just a few minutes from the first shot – and the analysis only needed three gunshots to come to this conclusion

The system, called Video Event Reconstruction and Analysis (VERA) gathered information from just three smartphones belonging to individuals who were in the area of the shooting

It also uses audio to identify the type of gun used, which determines bullet speed. 

Alexander Hauptmann, research professor in CMU’s Language Technologies Institute, said VERA was not designed to replace the commercial microphone arrays for locating shooters that public safety officials already use, but could be a backup option for when these are not available.

A main reason for developing VERA was to provide human rights workers and journalists in war stricken areas with a tool that will help them stay out of cross fire, Hauptmann said.

Fellow researcher Jay D. Aronson, a professor of history at CMU and director of the Center for Human Rights Science, explained that this type of technology is currently available to military and intelligence agencies, but believes ‘it’s crucial for the human rights community to have the same types of tools.

The team demonstrated this technology using just three video recordings from the 2017 Las Vegas shooting, which left 58 dead and hundreds of injured. The system located the shooter in the north wing of the Mandalay Bay hotel (pictured) in just a few minutes from the first shot

‘It provides a necessary check on state power.’

Hauptmann said he has used this technology to help investigators analyze events such as the 2014 Maidan massacre in Ukraine, which left at least 50 antigovernment protesters dead.

‘When we began, we didn’t think you could detect the crack with a smartphone because it’s really short,’ he said.

‘But it turns out today’s cell phone microphones are pretty good.’

 

Source: Read Full Article