MEM-YOLO11:一种多特征选择机制的无人机小目标检测模型

摘要：

针对遥感图像目标具有多尺度、多旋转角度、背景复杂等特点，提出了一种多特征选择机制融合改进模型MEM-YOLO11.首先，在backbone中设计了一种特征提取模块,结合了多尺度特征提取和边缘信息增强，提高了对特征信息的整合效果。其次，设计了一种高效的卷积网络模块，由原始图像生成更高分辨率的图像，增强了颈部网络中全局到局部的特征学习能力,并且，重新设计了一个多头部特征提取模块，减少标准卷积中广泛存在的空间和信道冗余。减少了参数量和计算量.最后，优化MEM-YOLO11模型的超参数.缓解分类和定位不相关问题.在Vis-Drone2019数据集上精度、召回率、_mAP50分别提升7.6%、5.6%、6.5%; Wider Person数据集上精度、召回率、_mAP50分别提升6.8%、4.2%、5.6%.

To address the chllenges of muli-scale objects, varied orientations, and complex backgrounds in remote sensing images, we propose MEM-YOLO11, an enhanced model integrating a multi-feature selection mechanism. First, a feature extraction module is designed within the backbone network, combining mulli-scale feature extraction and edge information enhancement to improve feature integration, Second, an efficient convolutional network module is developed to generate higher-resolution images from raw inputs, strengthening the global-to- local feature learning capability in the neck network. Additionally. a reconstructed mulli-head feature extraction module reduces spatial and channel redundancy inherent in standard conyolu-tions, significantly decreasing parameters and computational costs. Finally, hyperparameters of MEM-YOLO11 are optimized to alleviate the discrepancy between classification and localization tasks. Evaluations demonstrate significant improvements:on the VisDrone2019 dataset, precision, recall, and _mAP50 increase by 7.6%,5.6%,and 6.5%. respectively; on the Wider Per-son dataset, gains of 6.8%,4.2%,and 5.6% are achieved for the same metrics.

作者：

徐世周，杨红，张梦洁，张钰昊

Xu Shizhou, Yang Hong, Zhang Mengjie, ZhangYuhao

机构地区：

河南师范大学光电工程学院

引用本文：

徐世周，杨红，张梦洁等。MEM-YOLO11:一种多特征选择机制的无人机小目标检测模型[J].河南师范大学学报(自然科学版).2026,54(4):91-97.(Xu Shizhou, Yang Hong,Zhang Mengjie,et al. MEM-YOLO11:A UAV small object detection model with multi-feature selection mechanism[J].Journal of Henan Normal University(Natural Science Edition),2026 ,54(4):91-97.DOI:10.16366/j.cnki.1000-2367.2025.05.12.0002.)

基金：

国家自然科学基金；河南省科技攻关项目

关键词：

小目标检测;多尺度特征提取;边缘增强;超参数

small object detection; Multi-scale feature extraction; edge enhancement; hyperparameter

分类号：

‍

TP391.4

MEM-YOLO11:一种多特征选择机制的无人机小目标检测模型.pdf