Does YOLO26 Truly Offer Advantages Over Its Predecessors for Edge Deployment? A Benchmark Study in Aquaculture

2026-07-10

AI Summary

This study addresses the lack of systematic evaluation of YOLO-series models for deployment in edge-based aquaculture scenarios. For the first time, it presents a comprehensive benchmark of nano- to medium-sized variants of YOLOv5u, YOLOv8, YOLO11, and the novel NMS-free YOLO26 on real-world fish mortality detection tasks using the Ultralytics framework, evaluating training efficiency, detection accuracy (mAP50), and inference speed across both an NVIDIA A100 GPU and a Raspberry Pi 5 CPU. Results show that all models achieve comparable accuracy on the full dataset (mAP50 variation within 1.04%), with YOLOv8 demonstrating superior data efficiency. YOLO26n achieves the fastest inference on the Raspberry Pi (7.51 FPS), while YOLOv5mu proves most suitable for medium-scale CPU deployments, offering practical guidance for model selection in edge-based aquaculture applications.

Abstract

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.

Problem

• YOLO26
• edge deployment
• aquaculture
• object detection
• model benchmarking

Innovation

• YOLO26
• edge deployment
• aquaculture
• NMS-free
• benchmark study