融合递归特征金字塔的病原微生物检测  

Detection of Pathogenic Microorganisms by Fusion of Recursive Feature Pyramid

作　　者：黄志添 谢怡宁 赵晶[1] 何勇军[3] HUANG Zhitian;XIE Yining;ZHAO Jing;HE Yongjun(School of Computer Science and Technology,Harbin University of Science and Technology,Harbin 150080,China;College of Mecheanical and Electrical Engineering,Northeast Forestry University,Harbin 150006,China;Harbin Institute of Technology,School of Computer Science and Technology,Harbin 150006,China)

机构地区：[1]哈尔滨理工大学计算机科学与技术学院,哈尔滨150080 [2]东北林业大学机电工程学院,哈尔滨150006 [3]哈尔滨工业大学计算机科学与技术学院,哈尔滨150006

出　　处：《哈尔滨理工大学学报》2023年第5期91-102,共12页Journal of Harbin University of Science and Technology

基　　金：国家自然科学基金面上项目(61673142);黑龙江省自然科学基金杰出青年项目(JJ2019JQ0013)。

摘　　要：针对病原微生物的检测研究较少且目标尺寸相差较大、背景复杂问题,提出了一种融合递归特征金字塔的病原微生物多尺度检测方法。考虑到有些病原微生物的特征与正常细胞有一定的相似性,在YOLOv5特征提取阶段引入混合注意力模块CBAM,可以增强病原微生物的显著度,降低了病原微生物的误诊率。由于尺寸较小的病原微生物在下采样过程会丢失重要特征,在特征融合阶段使用递归特征金字塔RFP和增加小目标的检测层,可以对小目标的特征进行二次提取,丰富语义信息,提高了小目标的检出率,并在二次特征提取模块中使用深度可分离卷积DSConv替换普通卷积Conv,降低了模型的参数量,提升了性能。实验表明,本文算法在病原微生物数据集上的mAP达到了74.9%,相比基线网络YOLOv5提升了4.9%,小目标滴虫的mAP也提高了6.2%。同时在PascalVOC2007、PascalVOC2012和CDetector公开数据集上比基线网络YOLOv5分别提升了1.9%、3.1%和8%。Aiming at the problems of less research on the detection of pathogenic microorganisms,large differences in target size and complex background,a multi-scale detection method of pathogenic microorganisms fused with recursive feature pyramid was proposed.Considering that the characteristics of some pathogenic microorganisms are similar to normal cells,introducing the mixed attention module CBAM in the feature extraction stage of YOLOv5 can enhance the significance of pathogenic microorganisms and reduce the misdiagnosis rate of pathogenic microorganisms.Since the pathogenic microorganisms with small size will lose important features in the downsampling process,the recursive feature pyramid RFP is used in the feature fusion stage and the detection layer of the small target is added.The detection rate of the target is improved,and the depthwise separable convolution DSConv is used in the secondary feature extraction module to replace the ordinary convolution Conv,which reduces the number of parameters of the model and improves the performance.Experiments show that the mAP of the algorithm in this paper on the pathogenic microorganism dataset has reached 74.9%,which is 4.9%higher than the baseline network YOLOv5,and the mAP of the small target Trichomonas has also increased by 6.2%.At the same time,the public datasets of PascalVOC2007,PascalVOC2012 and CDetector are improved by 1.9%,3.1%and 8%respectively compared with the baseline network YOLOv5.

关 键 词：病原微生物 目标检测 递归特征金字塔 小目标 多尺度检测 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]