Research on Corn Disease Detection Based on Improved YOLOv5 Algorithm

doi:10.3778/j.issn.1673-9418.2210066

Abstract

Abstract: In order to solve the problems of backward identification technology, low efficiency and insufficient accuracy of corn leaf disease, an improved YOLOv5 algorithm is proposed to identify corn disease. In order to maintain low computation of the model, and improve detection speed and algorithm performance, the feature extraction structure of traditional YOLOv5s network is improved, and CA (coordinate attention) attention mechanism is added to the backbone network, which improves the problem of target undetected, and helps the model locate and identify more accurately. In the neck, BiFPN (bidirectional feature pyramid network) is used to replace original PANet (path aggregation network), and the application of multi-scale semantic features is improved through two-way feature fusion to enhance the extraction for deep features of images. A small target monitoring layer is added to enhance the detection effect of small objects. Loss function is improved and Focal-EIOU Loss is introduced to improve the precision of BBox regression. Compared with traditional YOLOv5s, Recall is increased by 4.61 percentage points, AP is increased by 4.5 percentage points, mAP@0.5 is increased by 2.14 percentage points, and detection speed is increased by 4.5 FPS. Experimental results show that the improved YOLOv5 algorithm significantly improves the efficiency and performance of the algorithm with little complexity increase, and the effect is better than traditional YOLOv5s algorithm.

Key words: corn disease, YOLOv5, feature pyramid, attention mechanism, efficient intersection over union (EIOU), object detection

摘要： 为了解决玉米叶部病害识别技术落后、效率不高、精度不够的问题，提出一种改进的YOLOv5算法识别玉米病害。在保持模型的较低计算量的情况下，同时提升检测速度和算法性能，将传统的YOLOv5s网络的特征提取结构进行改进，在主干网络中添加CA注意力机制，改善目标漏检问题，帮助模型更加精准地定位和识别；在颈部使用BiFPN替代原有的PANet，通过双向的特征融合提升多尺度语义特征的利用，加强对图像深层特征的提取，添加小目标监测层，加强对小物体的检测效果；改进损失函数，引入Focal-EIOU Loss损失函数，提高BBox的回归精度。改进后的YOLOv5算法和传统的YOLOv5s相比，Recall提升了4.61个百分点，平均精度AP上升了4.5个百分点，mAP@0.5提高了2.14个百分点，检测速度上升了4.5 FPS。实验结果表明，改进后的YOLOv5算法在增加极少复杂度的情况下明显提升了算法的效率和性能，并且效果优于传统的YOLOv5s算法。

关键词: 玉米病害, YOLOv5, 特征金字塔, 注意力机制, EIOU, 目标检测

SU Junkai, DUAN Xianhua, YE Zhaobing. Research on Corn Disease Detection Based on Improved YOLOv5 Algorithm[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(4): 933-941.

苏俊楷, 段先华, 叶赵兵. 改进YOLOv5算法的玉米病害检测研究[J]. 计算机科学与探索, 2023, 17(4): 933-941.

References

[1] 马先红, 李峰, 宋荣琦. 玉米的品质特性及综合利用研究进展[J]. 粮食与油脂, 2019, 32(1): 1-3.
MA S H, LI F, SONG R Q. Research on quality characte-ristics and comprehensive utilization of maize[J]. Cereals & Oils, 2019, 32(1): 1-3.
[2] 杨小倩, 郅慧, 张辉, 等. 玉米不同部位化学成分、药理作用、利用现状研究进展[J]. 吉林中医药, 2019, 39(6): 837-840.
YANG X Q, ZHI H, ZHANG H, et al. Research progress on chemical constituents, pharmacological effects and utili-zation status of different parts of corn[J]. Jilin Journal of Traditional Chinese Medicine, 2019, 39(6): 837-840.
[3] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Image-Net classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[4] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, Jun 7-12, 2015. Washington: IEEE Computer Society, 2015: 1-9.
[5] HE K M, ZHANG X Y, REN S Q, et al. Deep residual lear-ning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30, 2016. Washington: IEEE Computer Society, 2016: 770-778.
[6] REDMON J, FARHADI A. YOLOv3: an incremental imp-rovement[J]. arXiv:1804.02767, 2018.
[7] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//LNCS 9905: Proceedings of the 14th European Conference on Computer Vision, Oct 11-14, 2016. Cham: Springer, 2016: 21-37.
[8] REN S Q, HE K M, GIRSHICK R B, et al. Faster R-CNN: towards real time object detection with region proposal net-works[J]. IEEE Transactions on Pattern Analysis and Mac-hine Intelligence, 2017, 39(6): 1137-1149.
[9] LIN T Y, DOLLáR P, GIRSHICK R B, et al. Feature pyra-mid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 936-944.
[10] LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 8759-8768.
[11] TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recogni-tion, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 10778-10787.
[12] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 7132-7141.
[13] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//LNCS 11211: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 3-19.
[14] HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]//Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recogni-tion, Jun 19-25, 2021. Washington: IEEE Computer Society, 2021: 13713-13722.
[15] ZHENG Z H, WANG P, REN D W, et al. Enhancing geome-tric factors in model learning and inference for object detec-tion and instance segmentation[J]. IEEE Transactions on Cybernetics, 2022, 52(8): 8574-8586.
[16] ZHANG Y F, REN W Q, ZHANG Z, et al. Focal and effi-cient IOU loss for accurate bounding box regression[J]. Neuro-computing, 2022, 506: 146-157.