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
范为培 1于晓明 2沈凤龙 2王亮 3王星4
作者信息
- 1. 辽东学院信息工程学院,辽宁丹东 118003;沈阳化工大学计算机科学与技术学院,辽宁沈阳 110142;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
- 2. 辽东学院信息工程学院,辽宁丹东 118003
- 3. 沈阳化工大学计算机科学与技术学院,辽宁沈阳 110142;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
- 折叠
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Bumble-beeImage.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.
Abstract
In order to realize automatic sorting of bumblebees accurately and quickly,a lightweight deep learning bumblebee image classification model is proposed.Firstly,1 742 images of queen,drone and worker bees of ground bumblebee were collected,and a dataset containing 13 117 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 de-signed.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Key words
bumblebee classification/GhostNet V2/lightweight/multi-scale convolution/feature fusion引用本文复制引用
出版年
2024
NETL
NSTL
万方数据