Dejun Feng

Papers

Total Citations

H-Index

About

Dejun Feng is a researcher at the forefront of applying advanced computer vision and deep learning to aquaculture and environmental monitoring. His primary research areas include object detection, transformer-based architectures, and automated visual inspection systems for aquatic environments. Feng’s most notable contribution is the development of DF-DETR (Dead Fish-Detection Transformer), a pioneering model introduced in 2024 that leverages the Detection Transformer (DETR) framework to automatically identify dead fish in recirculating aquaculture systems. This work addresses a critical need in sustainable aquaculture—enabling real-time, non-invasive health monitoring to reduce waste and improve animal welfare. With 10 citations already, this paper has quickly gained attention for its practical application of state-of-the-art AI to a pressing industry challenge. Feng’s research bridges the gap between cutting-edge machine learning and real-world ecological management, offering scalable solutions for precision aquaculture. His work exemplifies how transformer-based detection can be adapted beyond generic object recognition to solve domain-specific problems, making him a rising voice in the intersection of artificial intelligence and aquatic science.