🤖 AI Summary
To address the low efficiency and insufficient accuracy of disease detection in shrimp aquaculture—leading to substantial economic losses—this paper proposes a lightweight YOLOv8n-based model. The method introduces three key innovations: (1) an RLDD detection head, (2) a C2f-EMCM feature fusion module, and (3) an enhanced SegNext_Attention self-attention mechanism, collectively improving multi-scale lesion feature representation while reducing computational overhead. Experiments on a custom shrimp disease dataset and the URPC2020 benchmark demonstrate that the proposed model reduces parameter count by 32.3%, achieves an mAP@0.5 of 92.7% (+3.0% improvement), and attains a +4.1% mAP@0.5 gain on URPC2020—outperforming state-of-the-art lightweight YOLO variants. The approach delivers an efficient, robust solution for intelligent disease identification in aquaculture.
📝 Abstract
Shrimp diseases are one of the primary causes of economic losses in shrimp aquaculture. To prevent disease transmission and enhance intelligent detection efficiency in shrimp farming, this paper proposes a lightweight network architecture based on YOLOv8n. First, by designing the RLDD detection head and C2f-EMCM module, the model reduces computational complexity while maintaining detection accuracy, improving computational efficiency. Subsequently, an improved SegNext_Attention self-attention mechanism is introduced to further enhance the model's feature extraction capability, enabling more precise identification of disease characteristics. Extensive experiments, including ablation studies and comparative evaluations, are conducted on a self-constructed shrimp disease dataset, with generalization tests extended to the URPC2020 dataset. Results demonstrate that the proposed model achieves a 32.3% reduction in parameters compared to the original YOLOv8n, with a mAP@0.5 of 92.7% (3% improvement over YOLOv8n). Additionally, the model outperforms other lightweight YOLO-series models in mAP@0.5, parameter count, and model size. Generalization experiments on the URPC2020 dataset further validate the model's robustness, showing a 4.1% increase in mAP@0.5 compared to YOLOv8n. The proposed method achieves an optimal balance between accuracy and efficiency, providing reliable technical support for intelligent disease detection in shrimp aquaculture.