Abstract
The rise in sea temperatures due to global warming has accelerated the migration of marine species, leading to the frequent discovery of toxic marine organisms in domestic waters. The blue-ringed octopus in particular is very dangerous because it contains a deadly poison called tetrodotoxin. Therefore, early detection of these toxic species and minimizing the risk to human life is crucial. This study evaluates the effectiveness of using the latest object detection technology, the YOLO model, to detect toxic marine species, aiming to provide valuable information for the development of a smart fisheries system. The analysis results showed that YOLOv8 achieved the highest precision at 0.989, followed by YOLOv7 at 0.775 and YOLOv5m at 0.318. In terms of recall, YOLOv8 scored 0.969, YOLOv5l scored 0.845, and YOLOv7 scored 0.783. For mAP50 and mAP50-95 metrics, YOLOv8 also performed the best with scores of 0.978 and 0.834, respectively. Overall, YOLOv8 demonstrated the highest performance, indicating its strong suitability for real-time detection of toxic marine organisms. On the other hand, the YOLOv5 series showed lower performance, revealing limitations in detection under complex conditions. These findings suggest that the use of the latest YOLO model is essential for establishing an early warning system for toxic marine species.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call