摘要
针对DeepLabV3+语义分割模型计算复杂度高、内存消耗大、难以在计算力有限的移动平台上部署等问题,提出一种改进的轻量化DeepLabV3+深度学习语义分割算法,用于实现无人机荞麦苗期图像的分割与识别。该算法采用RepVGG(Re-parameterization visual geometry group)与MobileViT(Mobile vision transformer)模块融合的方式建立主干网络实现特征提取;同时,在RepVGG网络结构中引入SENet(Squeeze-and-excitation networks)注意力机制,通过利用通道间的相关性,捕获更多的全局语义信息,保证荞麦分割的性能。实验结果表明,与FCN(Fully convolutional networks)、PSPNet(Pyramid scene parsing network)、DenseASPP(Dense atrous spatial pyramid pooling)、DeepLabV3、DeepLabV3+模型相比,本文提出的改进算法在较大程度上降低了模型参数规模,更适合在移动端部署,自建荞麦苗期分割数据集上的语义分割平均像素准确率(Mean pixel accuracy,mPA)和平均交并比(Mean intersection over union,mIoU)分别为97.02%和91.45%,总体参数量、浮点运算次数(Floating-point operations,FLOPs)和推理速度分别为9.01×10^(6)、8.215×10^(10)、37.83 f/s,综合表现最优。在全尺寸图像分割中,训练模型对不同飞行高度的荞麦苗期分割的mPA和mIoU均能满足要求,也具有较好的分割能力和推理速度,该算法可为后期荞麦补种、施肥养护和长势监测等提供重要技术支持,进而促进小杂粮产业智能化发展。
In view of the problems of high computational complexity,large memory consumption,and difficulty in deployment on mobile platforms with limited computing power in DeepLabV3+segmentation model,an improved lightweight DeepLabV3+algorithm was proposed to realize the segmentation and recognition of buckwheat by UAV at seedling stage.The algorithm adopted the fusion of re-parameterization visual geometry group(RepVGG)and mobile vision transformer(MobileViT)modules to establish the backbone network for feature extraction.At the same time,the squeeze-and-excitation networks(SENet)attention mechanism was introduced into the RepVGG network structure to capture more global semantic information by using the correlation between channels,and ensure the performance of buckwheat segmentation.Experimental results showed that compared with fully convolutional networks(FCN),pyramid scene parsing network(PSPNet),dense atrous spatial pyramid pooling(DenseASPP),DeepLabV3,and DeepLabV3+models,the improved algorithm proposed greatly reduced the model parameters,making it more suitable for deployment on mobile terminals.The mean pixel accuracy(mPA)and mean intersection over union(mIoU)on the self-built buckwheat segmentation dataset were 97.02%and 91.45%,the overall parameters,floating-point operations(FLOPs)and inference speed were 9.01×10^(6),8.215×10^(10) and 37.83 f/s,respectively,with the best performance.In the full-size image segmentation,the mPA and mIoU for buckwheat segmentation can meet the requirements at different flight heights,which had good segmentation ability and inference speed.The algorithm can provide technical support for the later buckwheat seed replacement,fertilization maintenance,and growth monitoring,and promote the intelligent development of small and coarse grain industry.
作者
武锦龙
吴虹麒
李浩
雷兴鹏
宋海燕
WU Jinlong;WU Hongqi;LI Hao;LEI Xingpeng;SONG Haiyan(College of Agricultural Engineering,Shanxi Agricultural University,Taigu 030801,China;College of Information Science and Engineering,Shanxi Agricultural University,Taigu 030801,China;Dryland Farm Machinery Key Technology and Equipment Key Laboratory of Shanxi Province,Taigu 030801,China)
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2024年第5期186-195,共10页
Transactions of the Chinese Society for Agricultural Machinery
基金
国家重点研发计划项目(2021YFD1600602-09)
山西省基础研究计划项目(202203021212414、202303021222067)。
