基于改进GhostNet V2的轻量化熊蜂图像分类模型  

A lightweight bumblebee image classification model based on improved GhostNet V2

作　　者：范为培 于晓明 沈凤龙 王亮 王星[4] FAN Weipei;YU Xiaoming;SHEN Fenglong;WANG Liang;WANG Xing(School of Information Engineering,Liaodong University,Dandong 118003,Liaoning,China;School of Computer Science and Technology,Shenyang University of Chemical Technology,Shenyang 110142,China;Key Laboratory of Chemical Process Industry Intelligent Technology of Liaoning Province,Shenyang University of Chemical Technology,Shenyang 110142,China;School of Agriculture,Liaodong University,Dandong 118003,Liaoning,China)

机构地区：[1]辽东学院信息工程学院,辽宁丹东118003 [2]沈阳化工大学计算机科学与技术学院,辽宁沈阳110142 [3]沈阳化工大学辽宁省化工过程工业智能化技术重点实验室,辽宁沈阳110142 [4]辽东学院农学院,辽宁丹东118003

出　　处：《浙江农业学报》2024年第12期2832-2845,共14页Acta Agriculturae Zhejiangensis

基　　金：2022年辽宁省应用基础研究计划项目(2022JH2/101300149)。

摘　　要：为准确、快速地实现熊蜂的自动分拣,提出了一种轻量化深度学习熊蜂图像分类模型。首先,采集了地熊蜂的蜂王、雄蜂和工蜂图像1 742张,并通过数据增强构建了包含13 117张熊蜂图像的数据集BumblebeeImage。然后,以GhostNet V2模型为基础,通过多尺度卷积获取输入图像更多感受野下的特征信息,增加两条捷径分支分别将低层与中层、高层的特征融合,将ReLU激活函数替换为SiLU,删减bottleneck层数和通道数,设计了一种轻量化熊蜂图像分类模型GMCFF。结果表明,利用GMCFF模型对BumblebeeImage数据集进行分类的准确率达到了98.40%,较原模型提高了1.53百分点,与ShuffleNetV2和MobileNetV2模型的分类准确率对比也更高,分别提高了1.53百分点和1.15百分点。该模型参数量只有0.73 M,浮点运算量较改进前下降了25.15 M,模型大小仅有3.01 MB,单张熊蜂图像的平均测试时间为17.08 ms,满足轻量化与实时性的要求。In order to realize automatic sorting of bumblebees accurately and quickly,a lightweight deep learning bumblebee image classification model is proposed.Firstly,1742 images of queen,drone and worker bees of ground bumblebee were collected,and a dataset containing 13117 bumblebee images was constructed by data augmentation.Then,based on the GhostNet V2 model,the feature information of the input image under more receptive fields was obtained by multi-scale convolution,two shortcut branches were added to fuse the features of the low-level and the middle-level,the high-level respectively,the ReLU activation function was replaced by SiLU,and the number of bottleneck layers and channels was cut,and a lightweight bumblebee image classification model GMCFF was designed.The results showed that the classification accuracy of the BumblebeeImage dataset using the GMCFF model reached 98.40%,which was 1.53 percentage points higher than the original model,and the classification accuracy compared with the ShuffleNetV2 and MobileNetV2 model was also higher,increasing by 1.53 and 1.15 percentage points respectively.The number of parameters of the model was only 0.73 M,the amount of floating point operations was decreased by 25.15 M compared with that before the improvement,the model size was only 3.01 MB,and the average test time of a single bumblebee image was 17.08 ms,which met the requirements of lightweight and real-time.

关 键 词：熊蜂分类 GhostNet V2 轻量化 多尺度卷积 特征融合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]