MFENet:面向植物伪装的多频边缘检测网络  

MFENet:Multi-Frequency Edge Detection Network for Plant Camouflage

作　　者：祁杰 张生[1] 韩韧[1] Jie Qi;Sheng Zhang;Ren Han(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海

出　　处：《建模与仿真》2025年第3期589-597,共9页Modeling and Simulation

摘　　要：本文针对植物伪装检测任务中低信噪比、动态干扰与细粒度识别问题,提出一种多频边缘动态检测网络MFENet,以提升复杂生态场景下的隐蔽植物检测精度与鲁棒性。在MFENet中,采用多尺度频率分离模块处理低信噪比问题,通过多尺度分组卷积分离低频全局特征与高频细节特征。同时,构建了通道感知边缘注意力模块,结合Sobel边缘先验与通道–空间注意力优化细粒度特征。为进一步提升检测精度,提出了边缘强度驱动的动态迭代反馈机制,自适应调整计算复杂度。在PlantCamo数据集上,与通用的伪装检测模型相比,MFENet在各指标上提升明显。消融实验验证了各模块的有效性。MFENet显著提升了植物伪装检测的精度与效率,为生态保护与农业监测提供可靠技术支撑。This paper addresses the problems of low signal-to-noise ratio,dynamic interference,and finegrained recognition in the task of plant camouflage detection.We propose a multi-frequency edge dynamic detection network(MFENet)to enhance the accuracy and robustness of concealed plant detection in complex ecological scenes.MFENet employs a multi-scale frequency separation module to address the low signal-to-noise ratio issue by utilizing multi-scale grouped convolutions to sepa-rate low-frequency global features from high-frequency detail features.Additionally,we construct a Channel-Aware Edge Attention module that combines Sobel edge priors with channel-space atten-tion to optimize fine-grained features.To further enhance detection accuracy,we introduce an edge intensity-driven dynamic iterative feedback mechanism to adaptively adjust computational com-plexity.On the PlantCamo dataset,MFENet shows significant improvements in all evaluation met-rics compared to conventional camouflage detection models.Ablation studies validate the effective-ness of each module.MFENet significantly enhances the accuracy and efficiency of plant camouflage detection,providing reliable technical support for ecological protection and agricultural monitor-ing.

关 键 词：植物伪装检测 目标检测 注意力机制 动态迭代 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]