融合双线性网络和注意力机制的油橄榄品种识别  

Identification of olive cultivars using bilinear networks and attention mechanisms

作　　者：朱学岩 陈锋军[1,2,3] 郑一力 李志强[1,4] 张新伟 ZHU Xueyan;CHEN Fengjun;ZHENG Yili;LI Zhiqiang;ZHANG Xinwei(School of Technology,Beijing Forestry University,Beijing 100083,China;National Key Laboratory-Forest Resource Efficient Production,Beijing 100083,China;Beijing Laboratory of Urban and Rural Ecological Environment,Beijing 100083,China;Key Laboratory of State Forestry Administration for Forestry Equipment and Automation,Beijing,100083,China;Research Center for Intelligent Forestry,Beijing 100083,China)

机构地区：[1]北京林业大学工学院,北京100083 [2]林木资源高效生产全国重点实验室,北京100083 [3]城乡生态环境北京实验室,北京100083 [4]林业装备与自动化国家林业局重点实验室,北京100083 [5]智慧林业研究中心,北京100083

出　　处：《农业工程学报》2023年第10期183-192,共10页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家重点研发计划(2019YFD1002401);中央高校基本科研业务费专项资金(2021ZY74);北京市共建项目联合资助。

摘　　要：为解决自然条件下的油橄榄品种识别问题,该研究以油橄榄品种佛奥、莱星、皮削利和鄂植8号为研究对象,融合双线性网络与注意力机制,提出双线性注意力EfficientNet模型。针对不同品种油橄榄表型差异很小的特点,搭建双线性网络以充分提取油橄榄图像中的特征信息。在此基础上,选用兼顾了速度和精度的EfficientNet-B0网络为特征提取网络。针对自然条件下油橄榄品种识别易受复杂背景干扰的问题,将CBAM(convolutional block attention module,CBAM)注意力与双线性网络结合,使模型在提取油橄榄图像特征时,能够聚焦到对油橄榄品种识别起关键作用的特征上。经测试,所提模型对4个油橄榄品种识别的总体准确率达到90.28%,推理时间为9.15 ms。Grad-CAM(gradient-weighted class activation mapping,Grad-CAM)热力图可视化结果也表明,所提模型在识别油橄榄品种时重点关注了果实以及部分叶子区域。消融试验结果表明,在EfficientNet模型中引入CBAM注意力和搭建双线性网络后,总体准确率分别提高了5.00和10.97个百分点。并且,对比试验结果表明,与双线性ResNet34、EfficientNet-SE注意力、双线性ResNet18、双线性VGG16和双线性GoogLeNet等模型相比,所提模型的总体识别准确率分别高12.78、11.53、11.11、10.70和5.00个百分点。该研究为解决自然条件下的油橄榄品种识别提供了依据,同时也可为其他作物的品种识别提供参考。The extensive range of olive cultivars available in the market exhibit minor differences in their phenotypic traits.Nonetheless,their quality attributes,particularly the oil content and fatty acid composition,significantly differ among distinct cultivars,resulting in the emergence of use iinferior products as superior products in the market.The accurate and quick identification of olive cultivars holds significant importance in enhancing the production and quality of olives.As such,delving into the study of olive cultivar identification is crucial for the advancement of the olive industry.This study presents a novel approach to address the challenge of identifying olive cultivars in natural conditions.Specifically,a bilinear attentional EfficientNet model is proposed,which incorporates the bilinear network design concept and attention mechanism.The model is trained and evaluated using four commonly planted olive cultivars(i.e.,Frantoio,Leccino,Picholine,and Ezhi 8)in Longnan,Gansu.The experimental results demonstrate the effectiveness of the proposed model in accurately and quickly identifying different olive cultivars.A bilinear network has been suggested to comprehensively extract feature information from olive images,for the limited phenotypic differences across different olive cultivars.In light of this,the selection of a feature extraction network has been made with consideration for both speed and accuracy,leading to the selection of the EfficientNet-B0 network.To tackle the challenge of identifying olive cultivars under natural conditions which are prone to intricate background interferences,a novel approach combining convolutional block attention module(CBAM)with bilinear network has been proposed.This approach facilitates the model in selectively focusing on the salient features responsible for cultivar identification during the feature extraction process of olive images.Upon conducting experiments,the bilinear attention EfficientNet model presented in this study has exhibited an overall accuracy of 90.2

关 键 词：图像处理 模型 品种识别 油橄榄 EfficientNet-B0 CBAM注意力 Grad-CAM 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] S24[自动化与计算机技术—计算机科学与技术]