Heat-vision Based Drone Surveillance Augmented By Deep Learning For Critical Industrial Monitoring

This study examines the application of drone-assisted infrared (IR) imaging with vision grayscale imaging and deep learning for enhanced abnormal detection in nuclear power plants. A scaled model was used to replicate the modern pressurized water reactor, and a drone equipped with dual vision and IR cameras captured detailed operational imagery. Deep learning algorithms were deployed to interpret the images and identify component abnormalities not easily detectable by traditional monitoring. Results indicated that the YOLO v8m model was particularly effective, showcasing high accuracy in both detecting and adapting to system anomalies. This approach has the potential to revolutionize real-time monitoring in safety-critical settings by providing a comprehensive, automated solution to abnormal detection.