An app claims that it has the technology to detect more than 90 percent of gunfire incidents and can help make cities safer.
Used in 90 cities, including Cincinnati and Columbus, ShotSpotter uses a combination of sensors, algorithms and artificial intelligence to find gunfire in real time.
ShotSpotter breaks down its technology into three sections: detection and location, classification and notification, with all three areas working together to find, locate and notify police of gunfire.
Here’s how the app says it works:
Detection and Location:
- Software filters out background noise, such as traffic and wind, and listens for sounds with gunfire characteristics. These are called pulses.
- If the sensor detects pulse, it extracts those features, such as sharpness, strength, duration and decay time.
- If at least three sensors detect a pulse believed to be a gunshot, the sensor sends data to cloud servers where technology determines a precise location based off the time difference of arrival and angle of arrival.
- Algorithms consider the distance from the sound source, pattern matching and other methods to classify the sound.
- The machine classifier compares the sound to a large database of known gunfire and other community sounds to determine if it is gunfire.
- Once classified as likely gunfire, the incident is sent to experts in ShotSpotter's Incident Review Center for additional analyzing. It is then published to police or dismissed.
- Notifications are triggered once an incident is confirmed as gunfire.
- Gunfire alerts are pushed to ShotSpotter's mobile, desktop and browser apps.
- From initial gunfire to alert, the entire process takes less than 60 seconds.
News Center 7's I-Team took a closer look at ShotSpotter and spoke to area law enforcement agencies about the possibility of bringing it to the Miami Valley. For more details, tune in Tuesday, May 21, at 5:30 p.m.