高级检索+

改进RegNet识别多种农作物病害受害程度

杜甜甜, 南新元, 黄家興, 张文龙, 马志侠

杜甜甜, 南新元, 黄家興, 张文龙, 马志侠. 改进RegNet识别多种农作物病害受害程度[J]. 农业工程学报, 2022, 38(15): 150-158. DOI: 10.11975/j.issn.1002-6819.2022.15.016
引用本文: 杜甜甜, 南新元, 黄家興, 张文龙, 马志侠. 改进RegNet识别多种农作物病害受害程度[J]. 农业工程学报, 2022, 38(15): 150-158. DOI: 10.11975/j.issn.1002-6819.2022.15.016
Du Tiantian, Nan Xinyuan, Huang Jiaxing, Zhang Wenlong, Ma Zhixia. Identifying the damage degree of various crop diseases using an improved RegNet[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(15): 150-158. DOI: 10.11975/j.issn.1002-6819.2022.15.016
Citation: Du Tiantian, Nan Xinyuan, Huang Jiaxing, Zhang Wenlong, Ma Zhixia. Identifying the damage degree of various crop diseases using an improved RegNet[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(15): 150-158. DOI: 10.11975/j.issn.1002-6819.2022.15.016

改进RegNet识别多种农作物病害受害程度

基金项目: 国家自然科学基金项目(52065064)

Identifying the damage degree of various crop diseases using an improved RegNet

  • 摘要: 针对传统农作物病害识别方法效率低、受害程度识别不准确的问题,提出了一个基于深度迁移学习和改进RegNet的多种农作物病害受害程度识别模型。该模型首先在RegNet输入端进行在线数据增强,用以提高训练样本的多样性;其次在模型的特征提取层引入了有效通道注意力机制,用以提高模型的特征提取能力;然后在模型的分类层引入多尺度特征融合策略,用以提高模型对细粒度特征的分类能力;最后使用深度迁移学习来优化模型的整体性能,加快模型的收敛速度,提高模型的泛化能力。试验结果表明,改进后的网络模型在农作物病害受害程度数据集上准确率达到了94.5%,相较于RegNet原模型准确率提高了10.4个百分点。改进后的模型具有更好的特征提取能力,对细粒度特征有更强的分类能力,该模型为农作物病害类型及其受害程度的识别提供了一种有效方法。
    Abstract: Crop yield has been one of the most prominent issues in the world in recent years. However, crop diseases have posed a great threat to crop yield. It is a high demand to timely and accurately detect crop disease types and the degree of damage. The manual recognition can rely only on skilled technicians. But, the visual fatigue of humans can easily lead to reduce the accuracy rate. The current machine learning cannot consider the correlation between the attributes in the data set, resulting in low recognition accuracy. In this study, a network model was proposed to identify the damage degree of multiple crop diseases using deep transfer learning and improved RegNet. The model contained four aspects as follows. Firstly, an online data enhancement was carried out at the input side of this model. Nine strategies were selected for the data enhancement, such as the HSV color variation, grayscale transformation, and Gaussian noise. The diversity of data samples increased while reducing the time and space for the data set collection expansion. As such, the over-fitting of the network was alleviated during this time. Secondly, the Efficient Channel Attention (ECA) mechanism was introduced into the feature extraction layer of the model for the cross-channel interaction. The model was then improved to extract more subtle features, particularly for the crop disease features. As such, a higher accuracy of recognition was achieved for the crop disease damage, which increased by 1.5 percentage points, compared with the original model at the same model size. In addition, a multi-scale feature fusion was introduced into the classification layer of the model. A spatial pyramid pooling was adopted to highly improve the accuracy of the model. The degree of crop disease damage was classified at different scales, especially for the fine-grained features. Correspondingly, the accuracy of crop disease damage recognition increased by 2.4 percentage points. Finally, deep transfer learning was used to optimize the overall performance of the model. The convergence speed was accelerated to improve the generalization ability of the model. The recognition accuracy was improved by 2.7 percentage points, compared with the strategy without deep transfer learning. The experimental results show that the improved RegNet network model achieved 94.5 percentage points accuracy on the dataset of crop disease damage level, which was 10.4 percent higher than the original one. The recognition accuracy of the improved model was improved by 2.1, 6.0, 3.7, and 1.6 percentage points, respectively, compared with the commonly-used classification network models, such as ResNet50, VGG16, InceptionV3, and ConvNeXt. Consequently, higher accuracy of recognition and smaller model size were achieved in the improved classification model, compared with the rest. The better performance of feature extraction and stronger classification ability were also obtained for the fine-grained features during this time. The finding can also provide a promising way to identify the crop disease types and the degree of damage.
  • [1] Zhou C, Zhou S, Xing J, et al. Tomato leaf disease identification by restructured deep residual dense network[J]. IEEE Access, 2021, 9: 28822-28831.
    [2] 王彦翔,张艳,杨成娅,等. 基于深度学习的农作物病害图像识别技术进展[J]. 浙江农业学报,2019,31(4):669-676.Wang Yanxiang, Zhang Yan, Yang Chengya, et al. Advances in new nondestructive detection and identification techniques of crop diseases based on deep learning[J]. Acta Agriculturae Zhejiangensis, 2019, 31(4): 669-676. (in Chinese with English abstract)
    [3] LeCun Y, Kavukcuoglu K, Farabet C. Convolutional networks and applications in vision[C]//Proceedings of 2010 IEEE International Symposium on Circuits and Systems. Paris France: IEEE, 2010: 253-256.
    [4] Jia S, Jia P, Hu S. Automatic detection of tomato diseases and pests based on leaf images[C]//2017 Chinese Automation Congress (CAC). Jinan China: IEEE, 2017: 2537-2510.
    [5] 孙俊,朱伟栋,罗元秋,等. 基于改进MobileNet-V2的田间农作物叶片病害识别[J]. 农业工程学报,2021,37(22):161-169.Sun Jun, Zhu Weidong, Luo Yuanqiu, et al. Recognizing the diseases of crop leaves in fields using improved Mobilenet-V2[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(22): 161-169. (in Chinese with English abstract)
    [6] 鲍文霞,吴刚,胡根生,等. 基于改进卷积神经网络的苹果叶部病害识别[J]. 安徽大学学报(自然科学版),2021,45(1):53-59.Bao Wenxia, Wu Gang, Hu Gensheng, et al. Apple leaf disease recognition based on improved convolutional neural network[J]. Journal of Anhui University (Natural Science), 2021, 45(1): 53-59. (in Chinese with English abstract)
    [7] 黄雪峰. 基于深度卷积神经网络的玉米叶部病害识别算法及系统实现[D]. 合肥:安徽大学,2021.Huang Xuefeng. Maize Leaf Disease Recognition Algorithm and System Implementation Based on Deep Convolutional Neural Network[D]. Hefei: Anhui University, 2021. (in Chinese with English abstract)
    [8] 张善文,许新华,齐国红,等. 基于可形变VGG-16模型的田间作物害虫检测方法[J]. 农业工程学报,2021,37(18):188-194.Zhang Shanwen, Xu Xinhua, Qi Guohong, et al. Detecting the pest disease of field crops using deformable VGG-16 model[J]. Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2021, 37(18): 188-194. (in Chinese with English abstract)
    [9] Elhoucine E, Recep E, Lahcen E. Beans leaf diseases classification using MobileNet Models[J]. IEEE Access, 2022, 10: 9471-9482.
    [10] 牛学德,高丙朋,南新元,等. 基于改进DenseNet卷积神经网络的番茄叶片病害检测[J]. 江苏农业学报,2022,38(1):129-134.Niu Xuede, Gao Bingpeng, Nan Xinyuan, et al. Detection of tomato leaf disease based on improved DenseNet convolutional neural network[J]. Jiangsu Journal of Agricultural Sciences, 2022, 38(1): 129-134. (in Chinese with English abstract)
    [11] 何东健,王鹏,牛童,等. 基于改进残差网络的田间葡萄霜霉病病害程度分级模型[J]. 农业机械学报,2022,53(1):235-243.He Dongjian, Wang Peng, Niu Tong, et al. Classification model of grape downy mildew disease degree in field based on improved residual network[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(1): 235-243. (in Chinese with English abstract)
    [12] 温长吉,王启锐,陈洪锐,等. 面向大规模多类别的病虫害识别模型[J]. 农业工程学报,2022,38(8):169-177.Wen Changji, Wang Qirui, Chen Hongrui, et al. Model for the recognition of large-scale multi-class diseases and pests[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(8): 169-177. (in Chinese with English abstract)
    [13] Vinyals O, Blundell C, Lillicrap T, et al. Matching networks for one shot learning[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. Barcelona, Spain: 2016: 3637-3645.
    [14] Larson S, Zheng A, Mahendran A, et al. Iterative feature mining for constraint-based data collection to increase data diversity and model robustness[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing(EMNLP).Punta Cana, Dominican Republic: 2020: 8097-8106.
    [15] 叶中华,赵明霞,贾璐. 复杂背景农作物病害图像识别研究[J]. 农业机械学报,2021,52(S1):118-124,147.Ye Zhonghua, Zhao Mingxia, Jia Lu. Image recognition of crop diseases in complex background[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(S1): 118-124, 147. (in Chinese with English abstract)
    [16] 甘雨,郭庆文,王春桃,等. 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, et al. 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)
    [17] Ilija R, Kosaraju R P, Girshick R, et al. Designing network design spaces[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA: 2020: 10428-10436.
    [18] Wang Q, Wu B, Zhu P, et al, ECA-Net: efficient channel attention for deep convolutional neural networks[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle, WA, USA: 2020: 11531-11539.
    [19] Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: 2017: 2117-2125.
    [20] Mei Y, Fan Y, Zhou Y. Image super-resolution with non-local sparse attention[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA: 2021: 3517-3526.
    [21] Pan S J, Yang Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2009, 22(10): 1345-1359.
    [22] 李茂莹,杨柳,胡清华. 同构迁移学习理论和算法研究进展[J]. 南京信息工程大学学报(自然科学版),2019,11(3):269-277.Li Maoying, Yang Liu, Hu Qinghua. A survey on theories and algorithms about homogeneous transfer learning[J]. Journal of Nanjing University of Information Science and Technology (Natural Science Edition), 2019, 11(3): 269-277. (in Chinese with English abstract)
    [23] 陈立福,武鸿,崔先亮,等. 基于迁移学习的卷积神经网络SAR图像目标识别[J]. 中国空间科学技术,2018,38(6):45-51.Chen Lifu, Wu Hong, Cui Xianliang, et al. Convolution neural network SAR image target recognition based on transfer learning[J]. Chinese Space Science and Technology, 2018, 38(6): 45-51. (in Chinese with English abstract)
    [24] 苏仕芳,乔焰,饶元. 基于迁移学习的葡萄叶片病害识别及移动端应用[J]. 农业工程学报,2021,37(10):127-134.Su Shifang, Qiao Yan, Rao Yuan. Recognition of grape leaf diseases and mobile application based on transfer learning[J] Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(10): 127-134. (in Chinese with English abstract)
    [25] Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: 2018: 7132-7141.
    [26] Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA: 2021: 13713-13722.
    [27] Liu Z, Mao H, Wu C Y, et al. A convnet for the 2020s[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans, LA, USA: 2022: 11976-11986.
    [28] Meng L, Li H, Chen B C, et al. AdaViT: adaptive vision transformers for efficient image recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans, LA, USA: 2022: 12309-12318.
  • 期刊类型引用(19)

    1. 马巍巍,陈悦,王咏梅. 基于深度网络集成的复杂背景甘蔗叶片病害识别. 智慧农业(中英文). 2025(01): 136-145 . 百度学术
    2. 胡晓波,许桃胜,王成军,朱洪波,甘雷. 基于实例白化与特征恢复的草莓病害识别领域泛化方法. 智慧农业(中英文). 2025(01): 124-135 . 百度学术
    3. 向玉云,陈思远,高爽,李书琴. 基于自适应BayesShrink和频-空特征融合的作物病害识别方法. 农业工程学报. 2025(06): 204-215 . 本站查看
    4. 章广传,李彤,高泉,叶荣,何云. 融合迁移学习和知识蒸馏的轻量级马铃薯叶片病害识别模型的构建方法. 江苏农业科学. 2024(04): 197-206 . 百度学术
    5. 李云红,张蕾涛,李丽敏,苏雪平,谢蓉蓉,史含驰. 基于CycleGAN-IA方法和M-ConvNext网络的苹果叶片病害图像识别. 农业机械学报. 2024(04): 204-212 . 百度学术
    6. 冯永强,刘成忠,韩俊英,邢雪,杨红强. 基于EAMnet的小麦开花期品种识别研究. 软件导刊. 2024(05): 1-8 . 百度学术
    7. 戚晓利,王兆俊,毛俊懿,王志文,崔德海,赵方祥. 基于RegNet-CSAM与ZOA-KELM模型的滚动轴承故障诊断. 振动与冲击. 2024(11): 165-175 . 百度学术
    8. 郑权,乔江伟,李婕,秦涛,涂静敏,李礼,蒋琦. 融合多尺度特征和注意力机制的油菜倒伏分类. 农业工程学报. 2024(11): 186-194 . 本站查看
    9. 张澳雪,崔艳荣,李素若,陈华锋,胡玉荣,胡蓉华. 基于改进RegNet网络的玉米叶片病害识别研究. 江苏农业科学. 2024(11): 216-224 . 百度学术
    10. 王浩宇,崔艳荣. 基于改进ShuffleNet v2模型的苹果叶片病害识别方法. 江苏农业科学. 2024(13): 214-222 . 百度学术
    11. 李莹. 基于深度学习的农作物病害识别研究综述. 科技与创新. 2024(17): 93-96 . 百度学术
    12. 赵盎然,兰鹏,任洪泽,吴勇,孙丰刚. 基于联邦学习的玉米叶片病害识别方法. 山东农业大学学报(自然科学版). 2024(05): 740-749 . 百度学术
    13. 张建龙,邢文文,叶绍波,张超,郑德聪. 基于双输出回归卷积神经网络的燕麦株高估测研究. 中国农业科学. 2024(20): 3974-3985 . 百度学术
    14. 周罕觅,陈佳庚,代智光,马林爽,秦龙,李纪琛,苏裕民,向友珍. 基于知识蒸馏和轻量级卷积神经网络的植物病害识别方法. 南京农业大学学报. 2024(06): 1189-1201 . 百度学术
    15. 章广传,李彤,何云,高泉,叶荣,钱晔,马自飞. 基于迁移模型集成的马铃薯叶片病害识别方法. 江苏农业科学. 2023(15): 216-224 . 百度学术
    16. 姜丽华,赵瑞雪,董春岩,常晓燕,马娟娟,谢能付,方松. 基于深度学习的水产病害可视化知识图谱构建与验证. 农业工程学报. 2023(15): 259-267 . 本站查看
    17. 胡晓波,许桃胜,黄伟,王儒敬. 交互式双分支特征融合的草莓病害程度快速诊断方法. 农业机械学报. 2023(11): 225-235 . 百度学术
    18. 左昊轩,黄祺成,杨佳昊,孙泉,李思恩,李莉. 基于改进YOLO v5s的作物黄化曲叶病检测方法. 农业机械学报. 2023(S1): 230-238 . 百度学术
    19. 陈禹,吴雪梅,张珍,闫建伟,张富贵,喻丽华. 基于改进YOLOv5s的自然环境下茶叶病害识别方法. 农业工程学报. 2023(24): 185-194 . 本站查看

    其他类型引用(20)

计量
  • 文章访问数:  295
  • HTML全文浏览量:  0
  • PDF下载量:  360
  • 被引次数: 39
出版历程
  • 收稿日期:  2022-05-06
  • 修回日期:  2022-06-19
  • 发布日期:  2022-08-14

目录

    /

    返回文章
    返回