摘要
针对冬季休眠期矮化苹果树果园修剪中人工修剪及半自动化修剪作业效率低的问题,在U-Net网络模型基础上,通过VGG16与U-Net结合构建改进的U-Net网络模型,采用VGG16作为上采样特征提取网络,运用注意力机制SEnet增强图像特征提取能力,提升分割精度,进而与下采样提取的图像特征进行融合,实现端到端图像分割效果。结果表明,测试集上SE2网络模型(改进U-Net网络模型)的MIo U、MPA均大于原始U-Net网络模型;在SE2网络模型中,当r=8时测试集的MIo U、测试集的MPA、训练集的F_(score)、测试集的F_(score)均最大,分别为89.59%、94.17%、0.942806、0.944506;在试验台上对SE2网络模型(r=8)进行性能验证,表明SE2网络模型(r=8)分割性能较好。
In response to the low efficiency of manual and semi-automatic pruning operations in dwarfing apple trees during the winter dormancy period,based on the U-Net network model,an improved U-Net network model was constructed by combining VGG16 with U-Net.Using VGG16 as the upsampling feature extraction network,the attention mechanism SEnet was used to enhance the image fea-ture extraction ability,improve segmentation accuracy,and then fuse with the downsampling extracted image features to achieve the end-to-end image segmentation effect.The results showed that the MIoU and MPA of the SE2 network model(improved U-Net net-work model)on the test set were greater than those of the original U-Net network model;in the SE2 network model,when r=8,the MIoU of the test set,MPA of the test set,F_(score) of the training set,and F_(score) of the test set were all the highest,with values of 89.59%,94.17%,0.942806,and 0.944506,respectively;the performance of the SE2 network model(r=8)was validated on the test bench,and it was found that the segmentation performance of the SE2 network model(r=8)was good.
作者
宋振帅
宋龙
周艳
何磊
朱贺
王治民
韩大龙
SONG Zhen-shuai;SONG Long;ZHOU Yan;HE Lei;ZHU He;WANG Zhi-min;HAN Da-ong(College of Mechanical and Electrical Engineering,Shihezi University,Shihezi 832003,Xinjiang,China;Institute of Machinery and Equipment,Xinjiang Academy of Agricultural and Reclamation Science,Shihezi 832000,Xinjiang,China)
出处
《湖北农业科学》
2024年第5期194-200,206,共8页
Hubei Agricultural Sciences
基金
新疆生产建设兵团重大科技项目(2021AA00503)
国家重点研发计划项目(2017YFD07014)
新疆生产建设兵团农业领域重点科技攻关项目(2018AB016)。
关键词
改进U-Net
网络模型
冬季休眠期
矮化苹果树
修剪枝条
分割方法
improved U-Net
network model
winter dormancy period
dwarfing apple trees
pruned branches
segmentation method
