Posts: 12,304 +120
The system, dubbed Video Event Reconstruction and Analysis (VERA), uses machine learning techniques to sync video feeds and calculate their approximate location based on their vantage point. Even more crucial to the process is the audio.
By analyzing the delay between the crack created by a supersonic bullet’s shock wave and the blast from a gun’s muzzle, the system can provide an approximation of the origin of a gunshot. Furthermore, audio cues can provide insight on the type of gun used which is helpful in determining bullet speed.
Just imagine how much easier it would be to confirm or discredit conspiracy theories if we had dozens of smartphone videos to analyze as President John F. Kennedy’s motorcade passed through Dallas, Texas, on November 22, 1963.
The researchers who developed VERA presented it at the Association for Computing Machinery's International Conference on Multimedia last month and even released it as open-source code. The hope is that “the journalism human rights communities can build on it in ways we don't have the imagination for or time to do,” said Jay D. Aronson, a professor of history at Carnegie Mellon University and director of the Center for Human Rights Science.
Masthead credit: Police line by Prath