Scholarlink

<p>This study presents a deployment-oriented fish-counting pipeline for multivariate aquaculture environments, where illumination, turbidity, depth, and fish density jointly affect detection reliability. Using a dataset of 6,500 labeled 1080p images collected across Vietnamese aquaculture sites, we benchmark two unmodified Ultralytics detectors (YOLO11 and YOLOv8), quantify the contribution of scenario-informed preprocessing and augmentation, and export the selected model to ONNX for execution on heterogeneous hardware (GPU, CPU, and embedded edge devices). On the test set, YOLO11 achieves <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\:mA{P}_{50-95}=\:0.993\)</EquationSource> </InlineEquation> and YOLOv8 achieves 0.995; under the operational constraint of <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\:mA{P}_{50-95}\ge\:\:0.99\)</EquationSource> </InlineEquation>, YOLO11 is selected due to consistently lower latency. ONNX export accelerates YOLO11 inference by ~ 25% while preserving accuracy within <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\:\varDelta\:mA{P}_{50-95}\le\:\:0.001\)</EquationSource> </InlineEquation>, and a Wilcoxon signed-rank test confirms that the latency advantage is statistically significant (<i>p</i> &lt; 0.05). Field deployment in three fish ponds further demonstrates reliable counting and proof-of-concept alerting via short-horizon aggregation of frame-wise counts. Importantly, the contribution of this work is system-level: an environment-stratified evaluation protocol, a data-centric robustness analysis, and an ONNX-based “train once, deploy across devices” monitoring pipeline—rather than a new detection architecture.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Proposed dynamic fish counting method in a multivariate environment based on YOLO model and ONNX format

  • 期刊论文

  • 发表日期：

    2026年3月9日

查看全文
  • Nguyen Minh Son,
  • Huynh Cao Tuan,
  • Phan Thi Huong,
  • Nguyen Khac Hoang,
  • Niusha Shafiabady,
  • Thanh Q. Nguyen

摘要

This study presents a deployment-oriented fish-counting pipeline for multivariate aquaculture environments, where illumination, turbidity, depth, and fish density jointly affect detection reliability. Using a dataset of 6,500 labeled 1080p images collected across Vietnamese aquaculture sites, we benchmark two unmodified Ultralytics detectors (YOLO11 and YOLOv8), quantify the contribution of scenario-informed preprocessing and augmentation, and export the selected model to ONNX for execution on heterogeneous hardware (GPU, CPU, and embedded edge devices). On the test set, YOLO11 achieves \(\:mA{P}_{50-95}=\:0.993\) and YOLOv8 achieves 0.995; under the operational constraint of \(\:mA{P}_{50-95}\ge\:\:0.99\) , YOLO11 is selected due to consistently lower latency. ONNX export accelerates YOLO11 inference by ~ 25% while preserving accuracy within \(\:\varDelta\:mA{P}_{50-95}\le\:\:0.001\) , and a Wilcoxon signed-rank test confirms that the latency advantage is statistically significant (p < 0.05). Field deployment in three fish ponds further demonstrates reliable counting and proof-of-concept alerting via short-horizon aggregation of frame-wise counts. Importantly, the contribution of this work is system-level: an environment-stratified evaluation protocol, a data-centric robustness analysis, and an ONNX-based “train once, deploy across devices” monitoring pipeline—rather than a new detection architecture.