电子测量与仪器学报

郭文豪,郝斌,张飞.改进YOLOv11的轻量化水下生物目标检测算法[J].电子测量与仪器学报,2026,40(6):101-115

改进YOLOv11的轻量化水下生物目标检测算法

Improved YOLOv11 lightweight underwater biologicalobject detection algorithm

DOI：

中文关键词: 水下生物目标检测；YOLOv11；轻量化 PConv；注意力机制

英文关键词:underwater biological target detection YOLOv11 lightweight PConv attention mechanism

基金项目:内蒙古自然基金重点项目（2025ZD011）资助

作者	单位
郭文豪	内蒙古科技大学数智产业学院包头014010
郝斌	内蒙古科技大学数智产业学院包头014010
张飞	内蒙古科技大学数智产业学院包头014010

Author	Institution
Guo Wenhao	School of Digital and Intelligent Industry, Inner Mongolia University of Science and Technology, Baotou 014010, China
Hao Bin	School of Digital and Intelligent Industry, Inner Mongolia University of Science and Technology, Baotou 014010, China
Zhang Fei	School of Digital and Intelligent Industry, Inner Mongolia University of Science and Technology, Baotou 014010, China

摘要点击次数: 45

全文下载次数: 22

中文摘要:

水下生物目标检测技术对于海洋生态保护、渔业资源开发等众多领域的发展具有重要意义。为了提高水下生物检测精度和速度以及解决现有水下生物检测模型参数量较大的问题,提出了一种改进YOLOv11的轻量化水下生物检测算法YOLOv11-PiA。首先,通过引入部分卷积(partial convolution,PConv)对C3k2模块进行改进,设计出C3k2_PConv模块,有效降低了模型的参数量和计算复杂度,并提高了检测精度和速度。其次,结合C2PSA模块和倒置残差块注意力机制(inverted residual block attention mechanism,iRMB),提出了C2PSA_iRMB模块,该模块通过强化不同深度的特征信息以增强特征表达能力,进而提升了检测精度。最后,采用轻量化下采样模块(lightweight downsampling module,ADown)替换基线模型中的传统卷积下采样模块,模型的参数量得到进一步降低,检测效率进一步提升。实验数据表明,在水下生物数据集RUOD和DUO上,YOLOv11-PiA模型的mAP@0.5达到了85.6%和82.6%,帧率(frames per second,FPS)达到了97和116 fps。与YOLOv11n原模型相比,YOLOv11-PiA模型的mAP@0.5分别提高了2.8%和2.3%,FPS分别提高了9和13 fps,且参数量、浮点运算量和模型大小分别降低了29.8%、22.2%和29.1%。其综合性能优于RTDETR、YOLOv12等主流的目标检测模型,可实现对水下生物的快速准确检测。

英文摘要:

Underwater biological target detection technology is of great significance to the development of numerous fields, such as marine ecological protection and fishery resource exploitation. To improve the accuracy and speed of underwater biological detection and address the high parameter count in existing models, a lightweight algorithm, YOLOv11-PiA, based on improved YOLOv11, is proposed. Firstly, the C3k2 module is improved by introducing partial convolution (PConv), resulting in the C3k2_PConv module, which effectively reduces the model’s parameter count and computational complexity while enhancing detection accuracy and speed. Secondly, the C2PSA_iRMB module, which combines the C2PSA module with the inverted residual block attention mechanism (iRMB), is proposed. This module strengthens feature information at multiple depths to enhance feature representation, thereby improving detection accuracy. Finally, the traditional convolutional downsampling module in the baseline model is replaced with the lightweight downsampling module (ADown), further reducing the model’s parameter count and improving detection efficiency. Experimental results on the RUOD and DUO underwater biological datasets show that the proposed YOLOv11-PiA model achieves mAP@0.5 values of 85.6% and 82.6%, with frames per second (FPS) reaching 97 and 116 fps, respectively. Compared with the original YOLOv11n model, YOLOv11-PiA increases mAP@0.5 by 2.8% and 2.3%, and improves FPS by 9 and 13 fps, respectively. Meanwhile, the parameter count, floating-point operations per second (FLOPs), and model size are reduced by 29.8%, 22.2%, and 29.1%, respectively. The comprehensive performance of YOLOv11-PiA outperforms mainstream target detection models such as RTDETR and YOLOv12, enabling fast and accurate detection of underwater organisms.

查看全文查看/发表评论下载PDF阅读器