Zhang Ting, Zhu Jikui, Zhang Fengkui, Zhao Shijie, Liu Wei, He Ruohong, Dong Hongqiang, Hong Qingqing, Tan Changwei, Li Ping
College of Mechanical and Electrical Engineering/Modern Agricultural Engineering Key Laboratory at Universities of Education Department of Xinjiang Uygur Autonomous Region/Key Laboratory of Tarim Oasis Agriculture (Tarim University) Ministry of Education, Tarim University, Alar, China.
Jiangsu Co-Innovation Center for Modern Production Technology of Grain Crops/Joint International Research Laboratory of Agriculture and Agri-Product Safety of the Ministry of Education of China/Jiangsu Province Engineering Research Center of Knowledge Management and Intelligent Service, College of Information Engineer, Yangzhou University, Yangzhou, China.
Front Plant Sci. 2024 Aug 27;15:1445418. doi: 10.3389/fpls.2024.1445418. eCollection 2024.
Cotton pests have a major impact on cotton quality and yield during cotton production and cultivation. With the rapid development of agricultural intelligence, the accurate classification of cotton pests is a key factor in realizing the precise application of medicines by utilize unmanned aerial vehicles (UAVs), large application devices and other equipment.
In this study, a cotton insect pest classification model based on improved Swin Transformer is proposed. The model introduces the residual module, skip connection, into Swin Transformer to improve the problem that pest features are easily confused in complex backgrounds leading to poor classification accuracy, and to enhance the recognition of cotton pests. In this study, 2705 leaf images of cotton insect pests (including three insect pests, cotton aphids, cotton mirids and cotton leaf mites) were collected in the field, and after image preprocessing and data augmentation operations, model training was performed.
The test results proved that the accuracy of the improved model compared to the original model increased from 94.6% to 97.4%, and the prediction time for a single image was 0.00434s. The improved Swin Transformer model was compared with seven kinds of classification models (VGG11, VGG11-bn, Resnet18, MobilenetV2, VIT, Swin Transformer small, and Swin Transformer base), and the model accuracy was increased respectively by 0.5%, 4.7%, 2.2%, 2.5%, 6.3%, 7.9%, 8.0%.
Therefore, this study demonstrates that the improved Swin Transformer model significantly improves the accuracy and efficiency of cotton pest detection compared with other classification models, and can be deployed on edge devices such as utilize unmanned aerial vehicles (UAVs), thus providing an important technological support and theoretical basis for cotton pest control and precision drug application.
棉花害虫在棉花生产和种植过程中对棉花品质和产量有重大影响。随着农业智能化的快速发展，棉花害虫的准确分类是利用无人机、大型施药设备等实现精准施药的关键因素。
本研究提出了一种基于改进的Swin Transformer的棉花害虫分类模型。该模型将残差模块、跳跃连接引入Swin Transformer，以改善害虫特征在复杂背景下易混淆导致分类准确率低的问题，增强对棉花害虫的识别能力。本研究在田间采集了2705张棉花害虫叶片图像（包括棉蚜、棉盲蝽和棉叶螨三种害虫），经过图像预处理和数据增强操作后进行模型训练。
测试结果证明，改进后的模型准确率相比原模型从94.6%提高到了97.4%，单张图像预测时间为0.00434秒。将改进后的Swin Transformer模型与七种分类模型（VGG11、VGG11-bn、Resnet18、MobilenetV2、VIT、Swin Transformer small和Swin Transformer base）进行比较，模型准确率分别提高了0.5%、4.7%、2.2%、2.5%、6.3%、7.9%、8.0%。
因此，本研究表明，改进后的Swin Transformer模型与其他分类模型相比，显著提高了棉花害虫检测的准确率和效率，并且可以部署在无人机等边缘设备上，从而为棉花害虫防治和精准施药提供重要的技术支持和理论依据。
