Coconino County deploys AI-powered drones for search and rescue
The Coconino County Sheriff's Office is using autonomous drones and custom-trained AI models to speed up search and rescue operations across northern Arizona. The department processes drone footage through pixel-detection software that identifies abnormalities in natural environments-work that would take humans far longer to complete manually.
Deputy Paul Clifton, Assistant Search and Rescue Coordinator, said the technology handles the volume problem. "As opposed to looking at thousands of photographs with the human eye that fatigues in 10 minutes, we're leveraging automation tools," Clifton said.
How the software works
Once a drone covers a search area, the department analyzes footage using LOC8, software that examines drone imagery pixel by pixel. The system can filter for specific colors based on what a missing person was wearing at the time they went missing, and it accounts for how light reflects off different surfaces.
The result is practical. "Maybe it reduces the number of photos you have to look at from a thousand down to twenty," Clifton said. "You can say, I don't care about blue or yellow or anything. I'm looking for red because we believe that's what the person was last seen wearing."
When the software flags a potential match, it provides searchers with precise GPS coordinates.
Hardware and obstacle avoidance
Coconino County has operated drones since 2018. The department now uses Skydio drones equipped with six onboard cameras that provide AI-powered obstacle avoidance. The system creates a three-dimensional field of vision to prevent crashes, even in areas with weak GPS signals like canyons.
Training models for local conditions
The Sheriff's Office is working with a company in Scotland to develop AI models tailored to northern Arizona's specific environment. The system can reanalyze video from past flights and retrain the model to better identify targets in future searches.
"Northern Arizona versus Southern Arizona, the context, the environments are very different," Clifton said. "And the ability to train models that work in your environment is super important."
The department is still testing the custom training feature. Clifton said their work could benefit other public safety departments operating in similar geographic areas.
Operations professionals implementing AI systems should consider how AI Agents & Automation can reduce manual review time in data-heavy workflows. For those managing these implementations, the AI Learning Path for Operations Managers covers practical deployment strategies.
Your membership also unlocks:
