Chicken Coop Monitoring System using You Only Look Once (YOLO) Algorithm

As chicken meat production increases in Padang City, farmers face serious threats from
predators and intruders that cause significant losses. Current solutions, such as PIR motion
detectors, have the disadvantage of not being able to recognize the objects they detect. This
study designs a chicken coop monitoring system capable of identifying objects using the You
Only Look Once (YOLO) algorithm. The system uses a Raspberry Pi 4 Model B as the
processing center, connected to two Arducam OV5647 cameras mounted on MG996R servo
motors. The system is also integrated with a Telegram application for real-time notifications.
Based on testing, the system is capable of detecting and classifying objects with an average
accuracy of 83.26% and an average notification response time of 10.8 seconds. Thus, the system
is effective in addressing security issues in chicken farms