首页|改进注意力机制嵌入PR-Net模型的水稻病害识别仿真

改进注意力机制嵌入PR-Net模型的水稻病害识别仿真

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
针对现有的CNN模型在水稻叶部病害的识别中准确率较低的问题,提出了一种结合并行结构和残差结构的混合卷积神经网络模型 PRC-Net(parallel residual with coordinate attention network).引入并行结构,提高卷积的感受野;结合残差结构,使特征信息完整的连续传递;在骨干模型PR-Net中嵌入改进的空间注意力机制,增强对不同尺度病斑特征信息的凝聚程度;为进一步提升病害识别的准确率,并减少模型的训练时间和推理时间,通过改变加权方式对模型结构进行优化.仿真结果表明:与InceptionResNetV2等分类模型相比,PRC-Net具有更少的训练参数、更短的训练时间和更高的识别精度,性能优于其他作物病害识别模型.
Simulation of Rice Disease Recognition Based on Improved Attention Mechanism Embedded in PR-Net Model
Aiming at the low accuracy of existing CNN models in identifying rice leaf diseases,a hybrid convolutional neural network model PRC-Net(parallel residual with coordinate attention network)combining parallel structure and residual structure is proposed.A parallel structure is introduced to improve the receptive field of convolution,and the residual structure is combined to achieve the complete and continuous transmission of feature information.An improved spatial attention mechanism is embedded into the backbone model PR-Net to enhance the degree of aggregation of lesion feature information at different scales.In order to further improve the accuracy of disease identification and reduce the training and reasoning time of the model,the model structure is optimized by changing the weighting method.Simulation results show that,compared to the classification models such as InceptionResNetV2,PRC-Net has fewer training parameters,shorter training time,and higher recognition accuracy,which is superior to the other crop disease identification models.

rice leaf diseasePRC-Netconvolution neural networkattention mechanismimage recognition

路阳、刘鹏飞、许思源、刘启旺、顾福谦、王鹏

展开 >

黑龙江八一农垦大学信息与电气工程学院,黑龙江大庆 163319

东北石油大学黑龙江省网络化与智能控制重点实验室,黑龙江大庆 163318

东北石油大学人工智能能源研究院,黑龙江大庆 163318

东北石油大学三亚海洋油气研究院,海南三亚 572024

展开 >

水稻叶部病害 PRC-Net(parallel residual with coordinate attention network) 卷积神经网络 注意力机制 图像识别

国家自然科学基金国家自然科学基金国家自然科学基金黑龙江省自然科学基金联合引导项目黑龙江省博士后科研启动基金海南省科技专项

U21A20196187305861933007LH2020F042LBH-Q17134ZDYF2022SHFZ105

2024

10.16182/j.issn1004731x.joss.23-0322

系统仿真学报
北京仿真中心 中国系统仿真学会

系统仿真学报

CSTPCD北大核心
影响因子：0.551
ISSN：1004-731X
年,卷(期)：2024.36(6)
  • 23