Applying Artificial Intelligence (AI) to improve fire response activities
Ray Hsienho Chang, Yan‐Tsung Peng, Seongchul Choi, Changjie Cai
Abstract
This research discusses how to use a real-time Artificial Intelligence (AI) object detection model to improve on-site incident command and personal accountability in fire response. We utilized images of firegrounds obtained from an online resource and a local fire department to train the AI object detector, YOLOv4. Consequently, the real-time AI object detector can reach more than ninety percent accuracy when counting the number of fire trucks and firefighters on the ground utilizing images from local fire departments. Our initial results indicate AI provides an innovative method to maintain fireground personnel accountability at the scenes of fires. By connecting cameras to additional emergency management equipment (e.g., cameras in fire trucks and ambulances or drones), this research highlights how this technology can be broadly applied to various scenarios of disaster response, thus improving on-site incident fire command and enhancing personnel accountability on the fireground.