AI 中文总结
本研究针对水产养殖中鱼类死亡率检测，在纳米、小型和中型模型规模上，对YOLO26与三个Ultralytics前身进行基准测试，评估检测准确性、训练效率和推理性能，发现架构新颖性不足以选模型，应综合考虑多因素。
AI 中文摘要
最近推出的YOLO26架构采用无NMS的端到端推理，并针对基于资源受限CPU的设备进行了优化，非常适合基于边缘的水产养殖应用。然而，其性能、运行效率和部署适用性在特定水产养殖场景中尚未得到系统验证。本研究针对鱼类死亡率检测这一鱼类种群健康和福利的关键指标，在纳米、小型和中型模型规模上，对YOLO26与三个Ultralytics前身（YOLOv5u、YOLOv8和YOLO11）进行了全面基准测试。评估了12个模型变体在检测准确性、七种数据集大小下的训练效率以及在高性能NVIDIA A100 GPU和仅含CPU的Raspberry Pi 5边缘平台上的推理性能。所有模型在完整数据集上实现了可比的性能，mAP50仅相差1.04个百分点，表明当有足够训练数据时，架构生成对最终检测准确性影响不大。然而，在数据效率和部署性能方面出现了明显的权衡。YOLOv8仅用400张训练图像就达到了90%的mAP50，而YOLO26纳米和小型变体需要1000张图像才能达到可比的准确性。相反，YOLO26n在Raspberry Pi 5上实现了最高的推理速度（7.51 FPS），而YOLOv5mu在基于CPU的硬件上优于所有当代中型架构。这些结果表明，仅架构新颖性不足以进行模型选择，在为水产养殖中的实际边缘AI部署选择目标检测模型时，应综合考虑训练数据可用性、目标硬件和推理要求。
英文摘要
The recently introduced YOLO26 architecture incorporates NMS-free end-to-end inference and is optimized for deployment on resource-constrained CPU-based devices, making it well-suited for edge-based aquaculture applications. However, its performance, operational efficiency, and deployment suitability have not been systematically validated in aquaculture-specific scenarios. This study presents a comprehensive benchmark of YOLO26 against three Ultralytics predecessors (YOLOv5u, YOLOv8, and YOLO11) across nano, small, and medium model scales for fish mortality detection, a critical indicator of fish population health and welfare. Twelve model variants were evaluated for detection accuracy, training efficiency across seven dataset sizes, and inference performance on high-performance NVIDIA A100 GPUs and a CPU-only Raspberry Pi 5 edge platform. All models achieved comparable performance on the full dataset, with mAP50 differing by only 1.04 percentage points, indicating that architectural generation has little influence on final detection accuracy when sufficient training data are available. However, clear trade-offs emerged in data efficiency and deployment performance. YOLOv8 achieved 90% mAP50 with only 400 training images, whereas the YOLO26 nano and small variants required 1,000 images to reach comparable accuracy. Conversely, YOLO26n achieved the highest inference speed on the Raspberry Pi 5 (7.51 FPS), while YOLOv5mu outperformed all contemporary medium-scale architectures on CPU-based hardware. These results show that architectural novelty alone is insufficient for model selection and that training data availability, target hardware, and inference requirements should be considered jointly when selecting object detection models for practical edge AI deployment in aquaculture.
CommentsPublished in MDPI AI. Final version available at https://doi.org/10.3390/ai7090354
Journal refAI 2026, 7, 354
