程存良 1王禹 2宋青峰 3简晨晨 4张严鑫 1魏中伟5
作者信息
- 1. 上海第二工业大学计算机与信息工程学院,上海 201209||上海黍峰生物科技有限公司,上海 200032
- 2. 上海黍峰生物科技有限公司,上海 200032
- 3. 中国科学院分子植物科学卓越创新中心,上海 200032
- 4. 上海第二工业大学计算机与信息工程学院,上海 201209
- 5. 湖南杂交水稻研究中心,湖南 长沙 410125
- 折叠
摘要
Abstract
Rice diseases have a critical influence on yield,accurately identifying disease types and taking timely control measures are essential for minimizing economic losses.With rise of smart agriculture,precise identification and monitoring of plant diseases based on image technology has become critical.To achieve higher accuracy and reduce computational load in rice disease identification,an im-proved ResNeXt50 model,named ECA-ResNeXt,was proposed.Initially,ResNeXt network depth was reduced to 35 layers,a num-ber of channels in initial layers was adjusted,convolutional channels were reduced,and standard convolutions were replaced with depth-wise convolutions,effectively reducing a number of floating-point operations,parameter count,and storage requirements.Secondly,integration with efficient channel attention(ECA)module played a key role in improving model's feature representation capabilities.Experimental results showed that ECA-ResNeXt achieved an accuracy of 99.83%in rice disease identification,with a float-ing-point operations volume of only 0.054 GFLOPs,model parameters of 0.054×106,and model size of 0.593 MB,demonstrating sig-nificant computational and storage efficiency.Compared to other classic convolutional neural networks,such as ResNet18,ResNet101,ResNeXt50,EfficientNet-b4,MobileNetV2,and MobileNetV3-Small,ECA-ResNeXt outperformed them in several evaluation met-rics,including accuracy,precision,recall,and F1 score,particularly exceeding 99%in both precision and recall.In terms of trans-fer learning,ECA-ResNeXt's performance in rice disease identification was further improved by pre-training on Plant Village dataset.Finally,an efficient rice pest and disease detection system was developed.Experimental validation confirmed that ECA-Res-NeXt was highly efficient and resource-saving in rice disease identification,and showed great potential for practical applications.关键词
水稻病害/深度学习/ResNeXt/图像识别/深度卷积/智慧农业Key words
rice disease/deep learning/ResNeXt/image recognition/depthwise convolution/smart agriculture分类
农业科技
