| Citation: |
LUO Runmei, YIN Huili, LIU Weikang, et al. Identification of bergamot pests and diseases using YOLOv5-C algorithm[J]. Journal of South China Agricultural University, 2023, 44(1): 151-160. DOI: 10.7671/j.issn.1001-411X.202203012
|
In order to achieve rapid and accurate identification of pests and diseases in the early disease stage of bergamot in complex background, we proposes a YOLOv5-C-based method for the identification of bergamot pests and diseases.
The YOLOv5s network model was used as the base network. The multi-scale feature fusion module was proposed and introduced to improve the feature extraction and feature fusion capability of the network model, and to improve the recognition accuracies of different bergamot pests and diseases in a balanced manner. The attention mechanism module was used to upgrade the attention degree of the network model to the information of target features of pests and diseases, weaken the interference information of complex background, and raise the recognition accuracy of the network model. An improved C3-SC module was used to replace the C3 module in the PANet structure to decrease the number of parameters in the network model without lowering the network model recognition performance.
F1 score of 90.95% and mean average precision of 93.06% were achieved when identifying the bergamot pests and diseases under a complex background using the YOLOv5-C method. The size of network model was 14.1 Mb, and the average detection time was 0.01 s per image on the GPU. Comparing with the original YOLOv5s, the mean accuracy of YOLOv5-C increased by 2.45 percentage point, the standard deviation of the average precision for seven categories was reduced from 7.14 to 3.13, and the coefficient of variation decreased from 7.88% to 3.36%. Moreover, the mean average accuracy was 22.30, 20.65, 4.84 and 2.36 percentage point higher than those of RetinaNet, SSD, Efficientdet and YOLOv4, respectively.
The method can quickly and accurately identify bergamot pests and diseases under complex background, and provide a reference for intelligent management of bergamot cultivation industry.
| [1] |
曹瑞, 郝二伟, 杜正彩, 等. 广佛手化学成分、药理作用的研究进展及质量标志物的预测分析[J/OL]. [2022-02-11]. https://kns.cnki.net/kcms/detail/21.1546.r.20220210.1726.076.html.
|
| [2] |
张思荻, 杨海燕, 曾俊, 等. 佛手的研究进展[J]. 中华中医药杂志, 2018, 33(8): 3510-3514.
|
| [3] |
翟肇裕, 曹益飞, 徐焕良, 等. 农作物病虫害识别关键技术研究综述[J]. 农业机械学报, 2021, 52(7): 1-18. doi: 10.6041/j.issn.1000-1298.2021.07.001
|
| [4] |
LI L, ZHANG S, WANG B. Plant disease detection and classification by deep learning: A review[J]. IEEE Access, 2021, 9: 56683-56698. doi: 10.1109/ACCESS.2021.3069646
|
| [5] |
兰玉彬, 王天伟, 陈盛德, 等. 农业人工智能技术: 现代农业科技的翅膀[J]. 华南农业大学学报, 2020, 41(6): 1-13. doi: 10.7671/j.issn.1001-411X.202008045
|
| [6] |
YUAN Y, FANG S, CHEN L. Crop disease image classification based on transfer learning with DCNNs[C]// Pattern Recognition and Computer Vision. Cham: Springer, 2018: 457-468.
|
| [7] |
CHEN J, CHEN J, ZHANG D, et al. Using deep transfer learning for image-based plant disease identification[J]. Computers and Electronics in Agriculture, 2020, 173: 105393. doi: 10.1016/j.compag.2020.105393
|
| [8] |
LÜ M, ZHOU G, HE M, et al. Maize leaf disease identification based on feature enhancement and dms-robust alexnet[J]. IEEE Access, 2020, 8: 57952-57966. doi: 10.1109/ACCESS.2020.2982443
|
| [9] |
陆健强, 林佳翰, 黄仲强, 等. 基于Mixup算法和卷积神经网络的柑橘黄龙病果实识别研究[J]. 华南农业大学学报, 2021, 42(3): 94-101. doi: 10.7671/j.issn.1001-411X.202008041
|
| [10] |
HASSAN S M, MAJI A K. Plant disease identification using a novel convolutional neural network[J]. IEEE Access, 2022, 10: 5390-5401. doi: 10.1109/ACCESS.2022.3141371
|
| [11] |
ZOU Z, SHI Z, GUO Y, et al. Object detection in 20 years: A survey[EB/OL]. 2019, arXiv: 1905.05055. https://arxiv.org/abs/1905.05055.
|
| [12] |
REN S, HE K, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. Advances in Neural Information Processing Systems, 2015, 28: 91-99.
|
| [13] |
LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]//European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
|
| [14] |
REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas: IEEE, 2016: 779-788.
|
| [15] |
REDMON J, FARHADI A. YOLO9000: Better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 7263-7271
|
| [16] |
REDMON J, FARHADI A. Yolov3: An incremental improvement[EB/OL]. 2018, arXiv: 1804.02767. http://arxiv.org/abs/1804.02767.
|
| [17] |
BOCHKOVSKIY A, WANG C, LIAO H M. Yolov4: Optimal speed and accuracy of object detection[EB/OL]. 2020, arXiv: 2004.10934. https://arxiv.org/abs/2004.10934.
|
| [18] |
ZHOU G, ZHANG W, CHEN A, et al. Rapid detection of rice disease based on FCM-KM and faster R-CNN fusion[J]. IEEE access, 2019, 7: 143190-143206. doi: 10.1109/ACCESS.2019.2943454
|
| [19] |
SUN J, YANG Y, HE X, et al. Northern maize leaf blight detection under complex field environment based on deep learning[J]. IEEE Access, 2020, 8: 33679-33688. doi: 10.1109/ACCESS.2020.2973658
|
| [20] |
LÜ Z, JIN H, ZHEN T, et al. Small object recognition algorithm of grain pests based on SSD feature fusion[J]. IEEE Access, 2021, 9: 43202-43213. doi: 10.1109/ACCESS.2021.3066510
|
| [21] |
MAMDOUH N, KHATTAB A. YOLO-based deep learning framework for olive fruit fly detection and counting[J]. IEEE Access, 2021, 9: 84252-84262. doi: 10.1109/ACCESS.2021.3088075
|
| [22] |
张博, 张苗辉, 陈运忠. 基于空间金字塔池化和深度卷积神经网络的作物害虫识别[J]. 农业工程学报, 2019, 35(19): 209-215. doi: 10.11975/j.issn.1002-6819.2019.19.025
|
| [23] |
胡嘉沛, 李震, 黄河清, 等. 采用改进YOLOv4-Tiny模型的柑橘木虱识别[J]. 农业工程学报, 2021, 37(17): 197-203. doi: 10.11975/j.issn.1002-6819.2021.17.022
|
| [24] |
IANDOLA F N, HAN S, MOSKEWICZ M W, et al. SqueezeNet: AlexNet-level accuracy with 50× fewer parameters and <0.5 MB model size[EB/OL]. 2016, arXiv: 1602.07360. https://arxiv.org/abs/1602.07360.
|
| [25] |
SZEGEDY C, LIU W, JIA Y, et al. Going deeper with Convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Boston: IEEE, 2015: 1-9.
|
| [26] |
LIN T, 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: IEEE, 2017: 2117-2125.
|
| [27] |
LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 8759-8768.
|
| [28] |
WANG C, LIAO H M, WU Y, et al. CSPNet: A new backbone that can enhance learning capability of CNN[C/OL]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society, 2020: 390-391.
|
| [29] |
HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916. doi: 10.1109/TPAMI.2015.2389824
|
| [30] |
WOO S, PARK J, LEE J, et al. CBAM: Convolutional block attention module[C]//Proceedings of the European conference on computer vision (ECCV). Cham: Springer, 2018: 3-19.
|
| 1. |
汪永红，罗铭欣，卢锦锋，陈莹，叶青，胡益波. 巴戟天种植管理技术. 种子科技. 2025(03): 132-134 .
| |
| 2. |
张才忠，白小明，闫玉邦，朱雅楠，李娟霞，冉福，何琳琳，吴廷达，朱奇萌. 有机肥对高寒退化草甸群落特征及其品质的影响. 草地学报. 2024(10): 3272-3279 .
|
Supported by: Beijing Renhe Information Technology Co., Ltd. 
DownLoad: