摘要
为应对水面波动、光照变化以及漂浮物部分遮挡等复杂场景中水面小目标漂流物检测面临的准确性和鲁棒性问题,提出了MEC-YOLOv11n算法。MEC-YOLOv11n算法包括Backbone、Neck和Head共3个部分。为了增大目标感受野的识别区域,本研究设计了MSWTC结构,并在Neck部分改进了C3k2结构,这一优化显著提高了水面小目标漂流物的提取能力,从而增强了模型在复杂背景下对细节的捕捉能力;其次,提出了一种EUCB上采样方法,替代了v11中的传统上采样模块,该方法在上采样过程中增强了图像边缘的清晰度,使得高分辨率特征图中的目标轮廓更加精确,尤其在处理复杂背景和小目标检测任务时,显著提升了模型对细节的捕捉能力;最后,在Head前设计了一种专门用于识别边缘特征的注意力模块CCA,进一步优化了模型在边缘信息提取方面的表现。实验结果表明,经过优化后的模型,其精确率P相较之前提高了3.3%,召回率R提高了2.4%,mAP50提升了2.5%,mAP50-95提高了1.5%。
To address the accuracy and robustness issues of small floating object detection on water surfaces under complex scenarios such as wave disturbances,changes in lighting,and partial occlusion by floating debris,the MEC-YOLOv11n algorithm is proposed.The MEC-YOLOv11n algorithm consists of three parts:Backbone,Neck and Head.To increase the recognition area of the target receptive field,we designed the MSWTC structure and improved the C3k2 structure in the Neck part,which significantly enhances the extraction ability of small floating objects on water surfaces,thus strengthens the model′s ability to capture details in complex backgrounds;next,we proposed a EUCB up-sampling method,replacing the traditional up-sampling module in v11,which enhances the clarity of image edges during up-sampling,making the object contours more accurate in high-resolution feature maps,especially when dealing with complex backgrounds and small target detection tasks,which significantly improves the model′s ability to capture details;finally,we designed an attention module CCA specifically for recognizing edge features before the Head,further optimizing the model′s performance in edge information extraction.Experimental results show that after optimization,the precision P of the model has increased by 3.3%,the recall R has increased by 2.4%,the mAP50 has increased by 2.5%,and the mAP50-95 has increased by 1.5%.
作者
安梦军
吴朝明
邓承志
An Mengjun;Wu Zhaoming;Deng Chengzhi(School of Information Engineering,Nanchang Institute of Technology,Nanchang 330000,China;Smart Water Conservancy Jiangxi Provincial Key Laboratory,Nanchang 330000,China)
出处
《电子测量技术》
北大核心
2025年第14期185-197,共13页
Electronic Measurement Technology
基金
江西省科技厅重大科技研发专项“揭榜挂帅”制项目(20213AAG01012-06)资助。
作者简介
安梦军,硕士研究生,主要研究方向为人工智能、计算机视觉等。E-mail:anmengjun1025@163.com;通信作者:吴朝明,博士,副教授,硕士生导师,主要研究方向为人工智能、机器视觉、视觉伺服等。E-mail:zmwunit@foxmail.com;邓承志,博士,教授,硕士生导师,主要研究方向为图像处理与机器视觉、模式识别与机器学习、多媒体计算技术、高光谱遥感影像处理等。E-mail:dengcz@nit.edu.cn。
