KAUST develops low-cost AI drone system to track camels and study migration patterns
- SAUDI ARABIA BREAKING NEWS
- Nov 13, 2025
- 2 min read
RIYADH, November 13, 2025 (Saudi Arabia Breaking News) – Researchers at King Abdullah University of Science and Technology (KAUST) have developed a low-cost, AI-powered drone system capable of identifying and tracking camels from the air, offering herders and scientists a new tool to monitor one of the Kingdom’s most important animals.
According to a KAUST press release, the system—created by Professor Basem Shihada and his research team—uses commercial, inexpensive drones and cameras to track camels in real time, eliminating the need for costly GPS collars or satellite-based systems.
The team mounted a single camera on a drone to film small camel herds in Saudi Arabia, using the footage to train a machine-learning model. The AI system was then able to recognize camels, follow their movement patterns, and provide new behavioral insights.
“We found their migration patterns were not random but showed identifiable patterns,” said KAUST scientist Chun Pong Lau, who participated in the project.
The findings showed that camels—particularly older animals—tend to migrate in coordinated grazing paths. They may travel significant distances during the day, but consistently return to their herder by sunset. The study also noted that camels were sensitive to the drone’s noise, prompting researchers to keep the aircraft at least 120 meters above ground.
Camels have historically played a central role in Arabian life, and today contribute more than SAR2 billion annually to Saudi Arabia’s economy through food products, textiles, tourism, and cultural events. Tracking remains a significant challenge, however, as camels can roam up to 50 kilometers per day in remote terrain, leading to lost livestock, overgrazing, and occasional road incidents.
As the next phase of the project, the KAUST team plans to expand data collection by filming larger and more diverse herds, enabling the AI model to improve its accuracy across varying sizes, colors, and environments.
