We are creating some awesome events for you. Kindly bear with us.

AI Helps Spot Fires Through Video Data in Sonoma County, California

Twenty-five tower-mounted cameras are transmitting images from Sonoma County, California to a company that specialises in visual Artificial Intelligence (AI) algorithm development and deployment. The AI solution applies an algorithm to compare those images against the more than 10 million it has been trained on to detect smoke plumes.

This is a big change from the previous approach, which involved emergency dispatchers keeping an eye on the video feeds as they came in, a nearly impossible task given their other responsibilities. Now, the video from the 25 connected cameras is sent via the cloud to a location where a human in the loop can verify that the algorithm has detected smoke.

The company put a box immediately around the smoke. It quickly determines that it is smoke, not fog, not steam, and then quickly, within seconds, sends the information to a dispatch centre that that latitude and longitude is a fire and needs to be addressed.

Sonoma’s fire and emergency medical technician dispatch centre is the county’s primary recipient of these alerts. An alarm sounds in the facility, triggering dispatchers to manually look at the affected area with at least two cameras so they can triangulate the location and dispatch crews.

Although dispatchers are the only ones who can act on the alerts, the messages go to about 32 email addresses and phone numbers for individuals at fire departments, the county’s Department of Emergency Management and the California Department of Forestry and Fire Protection.

The county announced that the Federal Emergency Management Agency’s Hazard Mitigation Grant Program had awarded it $2.7 million for early detection improvements, including augmenting an existing system with AI monitoring. That existing system was put in place by a consortium of public and private entities after the 2017 Tubbs Fire, which was one of the state’s most destructive.

Sonoma put its cameras on existing infrastructure such as radio towers built for emergency and regular communication. Many are located on high ground, which is crucial for spotting smoke; they have power and backup power and contain communications infrastructure needed to transmit the data.

Sonoma went live with the AI system in March, but it was put on hold as March and April are burn seasons for the county, which is home to many wineries. As vintners and other agricultural businesses burned excess vegetation ahead of Sonoma’s summer fire season, the cameras sent alerts about those planned and permitted burns.

The county resumed the AI detection when burns were no longer authorised. That month, dispatchers sent 14 responses to fires that the AI detected. Sonoma also began comparing how long it took the AI to detect a fire vs. a 911 call about it to come in.

A shortcoming of the camera and AI system is that it is only good for line-of-sight detection. If a fire starts in a valley, the smoke has to get above the ridgeline before the camera can see it. Very often, the local person can respond and call 911 before the smoke gets above it. But the county is more concerned with fires that are started in rural areas where somebody may not have eyes on the fire. Sonoma has 24 months to decide whether it will continue and expand the program. Wallis said he plans to evaluate its performance this and next fire season before making any long-term decisions.

As reported by OpenGov Asia, U.S. researchers have been utilising AI for mitigating disasters by developing an AI that can alert firefighters of imminent danger. As reported by OpenGov Asia, considering building fires can turn from bad to deadly in an instant, time is essential for firefighting. However, the warning signs of danger are frequently difficult for firefighters to detect amid the mayhem.

The fire service does not have many technologies that predict flashover at the scene. Firefighters often only rely on observation which can be deceiving. Seeking to remove this major blind spot, researchers at the National Institute of Standards and Technology (NIST) have developed P-Flash, or the Prediction Model for Flashover.

Send this to a friend