首页 > 分享 > 面向大规模多类别的病虫害识别模型

面向大规模多类别的病虫害识别模型

花匠小妙招
2024-09-15 16:58

摘要: 早期病虫害精准识别是预警和防控的关键，但是病虫害种类繁多数量巨大，外部形态存在类间相似度较高而类内差异性较大等性状特征，导致病虫害识别仍然是一项极具挑战的工作。为实现病虫害识别分类任务中差异化特征的提取和表示，该研究提出一种大规模多类别精细病虫害识别网络模型（a large-scale multi-category fine-grained pest and disease network，PD-Net）。首先通过在基准网络模型中引入卷积块注意力模型，通过混合跨特征通道域和特征空间域实现模型在通道和空间两个维度上对关键特征提取和表示，用以增强网络对差异化特征的提取和表示能力。其次引入跨层非局部模块，提升模型在多个特征提取层之间对于多尺度特征的融合。在61类病害数据集和102类虫害数据集上的试验结果表明，对比AlexNet、VGG16、GoogleNet、Inception-v3、DenseNet121和ResNet50模型，该研究提出的面向大规模多类别病虫害识别模型，Top1识别准确率在病害和虫害集上分别达到88.617%和74.668%，精确率分别达到了0.875和0.745，召回率分别达到0.874和0.738，F1值达到0.874和0.732，试验结果对比其他模型均有一定幅度的提升，验证了PD-Net模型在大规模多类别病虫害识别上的有效性。

Abstract: Abstract: Diseases and pests have posed a huge loss to agricultural production in recent years. Food losses that resulted from pests and diseases can be greater than 10% in the world, and even up to 30% in local areas, according to the latest statistics from the World Food and Agriculture Organization (FAO). It is a high demand to early identify the pests and diseases for the early warning, prevention, and control. However, an accurate identification of large-scale pests and diseases still remains a great challenge, due to the wide variety of pests and diseases and trait characteristics, such as high inter-class similarity and high intra-class variability of external morphology. This study aims to effectively extract and characterize the subtle features between categories for the large-scale multi-category pest classification and recognition task. A typical fine-grained classification was first established using the convolutional block attention mechanism, which was a visual attention mechanism module with better performance in the benchmark network. The key features were extracted to represent in both channel and spatial dimensions via blending across the feature channel and spatial domain. The feature dimension information with a high contribution rate to the pest classification task was extracted in the channel domain, while, the location dimension information with a high contribution rate was extracted in the spatial domain, where the benchmark network was achieved a fine-grained differential enhancement and representation. Secondly, the multi-scale feature extraction and representation were also particularly important for the fine-grained classification tasks. Since there were the different sizes and shapes of individuals to be recognized in fine-grained classification tasks, the sensory field scales were fixed for the same layer of convolutional kernels, indicating the influencing feature extraction when the sensory fields did not match the individuals. Therefore, a cross-layer nonlocal module was introduced into the benchmark model, in order to select a deeper layer and multiple shallow layers between multiple feature extraction layers of the benchmark network model. As such, the spatial response relationships were established to learn more multi-scale features for the improved feature extraction and representation capability of the benchmark model. Thirdly, a probability of default (PD)-Net model was also built in a large-scale multi-category fine-grained pest and disease network. A total of 800 images were collected, including the cherry powdery mildew general and severe, grape black rot general and severe, tomato spotted wilt general and severe, as well as citrus yellow dragon disease general and severe. Finally, a pest identification APP was developed using the PD-Net model. A pest and disease identification APP was developed on 61 categories of disease datasets and 102 categories of pests. After that, the 88.617% and 98.922% accuracies were achieved for the Top1 and Top2 recognition on the disease dataset, respectively, the 74.668% and 83.298% accuracy for the Top1 and Top2 recognition on the pest dataset. Respectively, compared with the AlexNet, VGG16, GoogleNet, Inception-v3, and DenseNet121 deep learning models. More importantly, the Top1 and Top2 recognition accuracies were improved by 1.748 percentage points to 4.331 percentage points, and 1.469 percentage points to 6.076 percentage points on the disease dataset, respectively. By contrast, the Top1 and Top2 recognition accuracies were improved by 1.906 percentage points to 8.122 percentage points, and 1.869 percentage points to 6.644 percentage points on the pest dataset, respectively. Meanwhile, the loss value, accuracy, precision, recall rate, and F1 were all improved, compared with the others. The experimental data was selected to verify the effectiveness of the PD-Net model. Consequently, a fine-grained recognition model can be widely expected for large-scale multi-category pests and diseases.

[1] Eskola M, Kos G, Elliott C T, etal. Worldwide contamination of food-crops with mycotoxins: Validity of the widely cited 'FAO estimate'of 25%[J]. Critical reviews in Food Science and Nutrition, 2020, 60(16): 2773-2789. [2] Cheng X, Zhang Y, Chen Y, et al. Pest identification via deep residual learning in complex background[J]. Computers and Electronics in Agriculture, 2017, 141: 351-356. [3] Rahman C R, Arko P S, Ali M E, et al. Identification and recognition of rice diseases and pests using convolutional neural networks[J]. Biosystems Engineering, 2020, 194: 112-120. [4] 贾少鹏，高红菊，杭潇. 基于深度学习的农作物病虫害图像识别技术研究进展[J]. 农业机械学报，2019，50(S1)：313-317.Jia Shaopeng, Gao Hongju, Hang Xiao. Research progress on image recognition technology of crop pests and diseases based on deep learning[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(S1): 313-317. (in Chinese with English abstract) [5] 李波，刘占宇，黄敬峰，等. 基于PCA和PNN的水稻病虫害高光谱识别[J]. 农业工程学报，2009，25(9)：143-147.Li Bo, Liu Zhanyu, Huang Jingfeng, et al. Hyperspectral identification of rice diseases and pests based on principal component analysis and probabilistic neural network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2009, 25(9): 143-147. (in Chinese with English abstract) [6] 温芝元，曹乐平. 椪柑果实病虫害的傅里叶频谱重分形图像识别[J]. 农业工程学报，2013，29(23)：159-165.Wen Zhiyuan, Cao Leping. Citrus fruits diseases and insect pest recognition based on multifractal analysis of Fourier transform spectra[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2013, 29(23): 159-165. (in Chinese with English abstract) [7] Ropelewska E, Zapotoczny P. Classification of Fusarium- infected and healthy wheat kernels based on features from hyperspectral images and flatbed scanner images: A comparative analysis[J]. European Food Research and Technology, 2018, 244(8): 1453-1462. [8] Mishra M, Singh P K, Brahmachari A, et al. A Robust Pest identification system using Morphological analysis in neural networks[J]. Periodicals of Engineering and Natural Sciences (PEN), 2019, 7(1): 483-495. [9] Bienkowski D, Aitkenhead M J, Lees A K, et al. Detection and differentiation between potato (Solanum tuberosum) diseases using calibration models trained with non-imaging spectrometry data[J]. Computers and Electronics in Agriculture, 2019, 167: 105056. [10] Zhang D, Chen G, Zhang H, et al. Integration of spectroscopy and image for identifying fusarium damage in wheat kernels using hyperspectral imaging[J]. Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy, 2020, 236: 118344. [11] Lins E A, Rodriguez J P M, Scoloski S I, et al. A method for counting and classifying aphids using computer vision[J]. Computers and Electronics in Agriculture, 2020, 169: 105200. [12] Khan S, Nadir S, Lihua G, et al. Identification and characterization of an insect toxin protein, Bb70p, from the entomopathogenic fungus, Beauveria bassiana, using Galleria mellonella as a model system[J]. Journal of invertebrate pathology, 2016, 133: 87-94. [13] Wen C, Guyer D E, Li W. Local feature-based identification and classification for orchard insects[J]. Biosystems Engineering, 2009, 104(3): 299-307. [14] 温长吉，娄月，张笑然，等. 基于改进稠密胶囊网络模型的植物识别方法[J]. 农业工程学报，2020，36(8)：143-155.Wen Changji, Lou Yue, Zhang Xiaoran, et al. Plant recognition method based on a improved dense CapsNet[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2020, 36(8): 143-155. (in Chinese with English abstract) [15] 张荣，李伟平，莫同. 深度学习研究综述[J]. 信息与控制，2018，47(4)：385-397Zhang Rong, Li Weiping, Mo Tong. A review of deep learning research[J]. Information and Control, 2018, 47(4): 385-397. (in Chinese with English abstract) [16] Srdjan S, Marko A, Andras A, et al. Deep neural networks based recognition of plant diseases by leaf image classification[J]. Computational Intelligence and Neuroence, USA 2016, 2016: 1-11. [17] Amanda R, Kelsee B, Peter M C, et al. Deep learning for image-based cassava disease detection[J/OL]. Frontiers in Plant Science, 2017: 1852. https://doi.org/10.3389/fpls.2017.01852 [18] Xie C, Wang R, Jie Z, et al. Multi-level learning features for automatic classification of field crop pests[J]. Computers and E lectronics in Agriculture, 2018, 152: 233-241. [19] Aravind K, Raja P. Disease classification in eggplant using pre-trained VGG16 and MSVM[J]. Scientific Reports, 2020, 10(1): 1-11. [20] Wang G, Sun Y, Wang J. Automatic image-based plant disease severity estimation using deep learning[J]. Computational Intelligence and Neuroscience, 2017, 2017:2917536. [21] Alfarisy A A, Chen Q, Guo M. Deep learning based classification for paddy pests & diseases recognition[C]//Proceedings of 2018 International Conference on Mathematics and Artificial Intelligence. SiChuan ChengDu 2018: 21-25. [22] Rangarajan A K, Purushothaman R. Disease Classification in Eggplant Using Pre-trained VGG16 and MSVM[J]. Scientific Reports, 2020, 10(1): 2322. [23] Zhang S, Zhang S, Zhang C, et al. Cucumber leaf disease identification with global pooling dilated convolutional neural network[J]. Computers and Electronics in Agriculture, 2019, 162: 422-430. [24] 陈善雄，伍胜，于显平. 基于卷积神经网络结合图像处理技术的荞麦病害识别[J]. 农业工程学报，2021，37(3)：155-163.Chen Shanxiong, Wu Sheng, Yu Xianping. Buckwheat disease recognition using convolution neural network combined with image processing[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(3): 155-163. (in Chinese with English abstract) [25] 宋余庆，谢熹，刘哲. 基于多层EESP深度学习模型的农作物病虫害识别方法[J]. 农业机械学报，2020，51(8)：196-202.Song Yuqing, Xie Xi, Liu Zhe. Crop pests and diseases recognition method based on multi-level EESP model[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(8): 196-202. (in Chinese with English abstract) [26] Wang J, Li Y, Feng H, et al. Common pests image recognition based on deep convolutional neural network[J]. Computers and Electronics in Agriculture, 2020, 179: 105834. [27] 李书琴，陈聪，朱彤. 基于轻量级残差网络的植物叶片病害识别[J]. 农业机械学报，2022，53(3)：243-250.Li Shuqin, Chen Cong, Zhu Tong. Plant leaf disease identification based on lightweight residual network[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(3): 243-250 (in Chinese with English abstract) [28] 甘雨，郭庆文，王春桃. 基于改进EfficientNet模型的作物害虫识别[J]. 农业工程学报，2022，38(1)：203-211.Gan Yu, Guo Qingwen, Wang Chuntao. Recognizing crop pests using an improved EfficientNet model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(1): 203-211. (in Chinese with English abstract) [29] Zhao X, Li K, Li Y, et al. Identification method of vegetable diseases based on transfer learning and attention mechanism[J]. Computers and Electronics in Agriculture, 2022, 193: 106703. [30] Qi J, Liu X, Liu K, et al. An improved YOLOv5 model based on visual attention mechanism: Application to recognition of tomato virus disease[J]. Computers and Electronics in Agriculture, 2022, 194: 106780. [31] 唐詹，柏召，刁磊，等. 基于注意力池化和堆叠式结构的病虫害文献识别模型[J]. 农业机械学报，2021，52(S1)：178-184.Tang Zhan, Bai Zhao, Diao Lei, et al. Diseases and pests articles identification model based on attention pooling and stacked structure[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(S1): 178-184. (in Chinese with English abstract) [32] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017, 30: 5998-6008. [33] Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV). Zürich: Springer 2018: 3-19. [34] Ye Z, Hu F, Liu Y, et al. Associating multi-scale receptive fields for fine-grained recognition[C]//2020 IEEE International Conference on Image Processing (ICIP). Abu dhabi National Exhibition Center. IEEE, 2020: 1851-1855. [35] Wu X, Zhan C, Lai Y K, et al. Ip102: A large-scale benchmark dataset for insect pest recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA 2019: 8787-8796. [36] Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259. [37] Mnih V, Heess N, Graves A. Recurrent models of visual attention[C]. Advances in Neural Information Processing Systems, Montreal, Canada 2014, 2204-2212. [38] Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Conference Location: New York, NY, USA 2018: 7132-7141. [39] Wang X, Girshick R, Gupta A, et al. Non-local neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Conference Location: New York, NY, USA 2018: 7794-7803.