Akademik Veri Yönetim Sistemi
Journal of Robotics, Networking and Artificial Life, cilt.11, sa.3, ss.226-235, 2026 (ESCI, Scopus)
Aquaculture continues to expand as a response to rising seafood demand, but feeding remains a critical challenge due to its high costs and environmental impact. This study introduces an underwater imaging system that integrates video enhancement, YOLOv8-based fish detection, and velocity estimation to provide a data-driven solution for optimizing feeding strategies. Unlike conventional farmer intuition, the proposed approach offers objective monitoring of fish behavior under real aquaculture conditions. The system enhances underwater video quality by correcting color distortion, reducing noise, and sharpening contours, which improved fish detection accuracy from 69.3% to 73.2%. YOLOv8 achieved an overall detection accuracy of 85%, while velocity tracking successfully distinguished between normal and hunger-driven behaviors. These results confirm that fish velocity is a reliable indicator of feeding demand. By linking motion dynamics with feeding decisions, the system can reduce feed waste, lower costs, and improve fish health while minimizing environmental impacts. This work demonstrates the potential of integrating artificial intelligence and imaging technologies to establish standardized, sustainable, and more profitable aquaculture feeding practices. Future studies will focus on larger datasets, adaptive enhancement techniques, and real-time feeding control.