结合注意力机制与双向特征融合的叶片病害检测方法
Leaf disease detection method combining attention mechanism and bidirectional feature fusion
马晓慧 1王骥 1覃嘉俊2
作者信息
- 1. 广东海洋大学电子与信息工程学院,广东湛江,524088;广东省智慧海洋传感器及其装备工程技术研究中心,广东湛江,524088
- 2. 广东省智慧海洋传感器及其装备工程技术研究中心,广东湛江,524088;广东海洋大学数学与计算机学院,广东湛江,524088
- 折叠
摘要
传统的Mask R-CNN网络检测目标时会出现特征丢失和特征混淆的情况,且对于密集的小目标容易出现漏检、错检等问题.针对这一问题,提出一种结合注意力机制和双向特征融合的叶片病害检测方法.首先,构建数据集时给叶片图片加入高斯噪声斯和椒盐噪声两种人工噪声,模仿自然界的复杂噪声,提升数据的多样性;其次,结合PAFPN结构与CBAM注意力机制,生成的CBAM-PAFPN结构,替代Mask R-CNN网络FPN结构,优化Mask R-CNN网络的特征提取方式;最后,将原网络NMS筛选候选框的方式替换为Soft-NMS.结果表明:对于无噪声的数据集,mAP值提升0.46%,Recall值提升2.24%;平均错检率为1.34%,降低3.28%,约为原网络的1/4,平均漏检率为0.12%,降低2.19%,约为原网络的1/20.改进后的网络在检测和定位精度上都有所提升,为有效检测不同大小、不同密集度的叶片病害提供技术支持.
Abstract
When the traditional Mask R-CNN network detects the target,feature loss and feature confusion will occur,and for the dense small target,it is easy to miss detection,false detection and other problems.In order to solve this problem,this paper proposes a leaf disease detection method combining attention mechanism and bidirectional feature fusion.Firstly,two kinds of artificial noises such as Gaussian noise and salt and pepper noise,were added to the leaf picture during the construction of the data set to imitate the complex noises in nature and improve the diversity of data.Secondly,combining the PAFPN structure with the CBAM attention mechanism,the CBAM-PAFPN structure is generated to replace the FPN structure of Mask R-CNN network and optimize the feature extraction mode of Mask R-CNN network.Finally,replace the original NMS filtering candidate box with Soft-NMS.The experimental results show that for the noiseless data set,mAP value increases by 0.46%and Recall value increases by 2.24%.The average error detection rate is 1.34%,a decrease of 3.28%,about 1/4 of the original network,the average missing detection rate is 0.12%,a decrease of 2.19%,about 1/20 of the original network.The improved network has increased the accuracy of detection and positioning,which provides technical support for the effective detection of leaf diseases of different sizes and densities.
关键词
叶片病害/CBAM/双向特征融合/Mask/R-CNN/NMSKey words
leaf disease/CBAM/bidirectional feature fusion/Mask R-CNN/NMS引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据