首页 > 分享 > 基于改进YOLOv5s的储粮害虫检测方法研究

基于改进YOLOv5s的储粮害虫检测方法研究

花匠小妙招
2024-11-09 06:11

摘要: 针对当前因检测背景复杂、粮虫个体较小等因素造成的储粮害虫检测准确率较低、漏检、误检的现状,提出一种改进YOLOv5s的检测方法。使用MobileNetv3作为YOLOv5s模型的主干特征提取网络,并将其SE 注意力机制修改为ECA模块,减少计算量和参数量;同时,调整PANet网络为加权双向特征金字塔BiFPN 结构,增强特征融合能力;颈部网络部分引入Swin Transformer,解决全局提取特征不足的问题,提升识别精度;采用EIOU损失函数,提高模型的收敛速度。结果表明:改进后的模型mAP达到 97.8%,FPS达到133.3,与主流目标检测模型比较,表现出较强的鲁棒性和泛化能力;改进的YOLOv5s检测模型能克服复杂环境的影响,显著提高储粮害虫在密集分布及遮挡条件下的检测效果。研究结果为移动设备上实现储粮害虫实时检测提供技术参考。

Abstract: Addressing the current challenges of low detection accuracy and missed detections due to complex backgrounds and small sizes of these pests, an enhanced YOLOv5s method for detecting stored grain pests is proposed. Firstly, MobileNetv3 is employed as the backbone feature extraction network for the YOLOv5s model, with its SE attention mechanism being modified into an ECA module to reduce computation and parameter count. Simultaneously, the PANet network is adjusted to incorporate a weighted bidirectional feature pyramid BiFPN structure to enhance feature fusion capabilities. Secondly, Swin Transformer is introduced into the neck network to address insufficient global feature extraction issues and improve recognition accuracy. Finally, the EIOU loss function is utilized to expedite model convergence speed. The results demonstrate that this improved model achieves a mAP (mean average precision) score of 97.8% and operates at a FPS (frames per second) rate of 133.3, showcasing remarkable robustness and generalization abilities when compared with mainstream target detection models. This study's improved YOLOv5 model for detecting stored grain pests effectively overcomes environmental complexities while significantly enhancing pest detection under conditions involving dense distributions and occlusions-thereby providing valuable technical insights towards achieving real-time pest detection on mobile devices.

[1] 高华, 祝玉华, 甄彤. 仓储害虫检测技术的研究现状及展望 [J]. 粮油食品科技, 2016, 24(2): 93-96. [2] 陈卫东,王莹,范冰冰,等. 基于深度学习的储粮害虫检测研究进展[J]. 中国粮油学报,2023,38(11):18-27. [3] 许德刚, 王露, 李凡. 深度学习的典型目标检测算法研究综述 [J]. 计算机工程与应用, 2021, 57(8): 10-25. [4]

REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6): 1137-1149.

[5]

LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector [M]//LEIBE B, MATAS J, SEBE N, et al. Lecture notes in computer science. Cham: Springer International Publishing, 2016: 21-37.

[6]

REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection //2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. IEEE, 2016: 779-788.

[7]

REDMON J, FARHADI A. YOLO9000: better, faster, stronger //2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA. IEEE, 2017: 6517-6525.

[8]

REDMON J, FARHADI A. YOLOv3: an incremental improvement. 2018: arXiv: 1804.02767. http://arxiv.org/abs/1804.02767.

[9]

BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection.. http://arxiv.org/abs/2004.10934v1.

[10] 吕宗旺, 金会芳, 孙福艳, 等. 一种基于SSD算法的特征融合的粮虫识别方法和识别系统:CN112288022A.2021-01-29. [11]

LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection //2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA. IEEE, 2017: 936-944.

[12]

LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation //2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA. IEEE, 2018: 8759-8768.

[13]

HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3 //2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, Korea (South). IEEE, 2019: 1314-1324.

[14]

HOWARD A G, ZHU M L, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications.. https://arxiv.org/abs/1704.04861v1.

[15]

SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks //2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA. IEEE, 2018: 4510-4520.

[16]

HU J, SHEN L, SUN G. Squeeze-and-excitation networks //2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA. IEEE, 2018: 7132-7141.

[17]

TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection //2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA. IEEE, 2020: 10778-10787.

[18]

LIU Z, LIN Y T, CAO Y, et al. Swin Transformer: hierarchical vision transformer using shifted windows //2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, QC, Canada. IEEE, 2021: 9992-10002.

[19] 周亚罗, 武献超, 刘文广, 等. 基于STCS-YOLO的带钢表面缺陷检测算法[J]. 中国冶金,2023,33(12):128-138. [20]

ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression [J]. Proceedings of the AAAI conference on artificial intelligence, 2020, 34(7): 12993-13000.

[21]

ZHANG Y F, REN W Q, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression [J]. Neurocomputing, 2022, 506: 146-157.

[22] 吕建华, 杨晓柯, 陈益锋,等. 赤拟谷盗、锯谷盗及锈赤扁谷盗幼虫对不同气味源的行为选择研究[J]. 河南工业大学学报(自然科学版), 2023, 44 (3): 98-103,119.