基于改进轻量化YOLOv5s的卷烟厂烟草粉螟视觉检测方法
Visual detection method of tobacco moth in cigarette factory based on improved lightweight YOLOv5s
-
摘要: 针对卷烟厂仓储车间在检测烟草粉螟时普遍存在的检测速度慢及检测精度低的问题，研发了一种基于改进轻量化YOLOv5s的卷烟厂烟草粉螟视觉检测方法。该方法利用特征图之间的相关性和冗余性设计EESP-Ghost模块，并以该模块为基础设计融合高效空间金字塔的双重注意力Ghost-bneck模块，将其引入到YOLOv5s模型中以实现深度神经网络模型的轻量化，同时提高检测精度。利用烟草粉螟数据集对该方法进行验证实验，结果表明，该方法在参数量仅为原始YOLOv5s参数量49.88%的情况下，检测平均精度（mAP）提升了4.37%。该方法在真实检测场景下对粘附到粘虫板上的烟草粉螟进行检测时，检测置信度、正确检测数均较高，可实现对卷烟厂烟草粉螟的高精度实时检测，为烟草粉螟的有效防治提供保障。
-
关键词:
- 改进轻量化YOLOv5s /
- 烟草粉螟 /
- EESP-Ghost模块 /
- 双重注意力 /
- 融合高效空间金字塔
Abstract: To address the problems of slow detection speed and low accuracy commonly found in cigarette factory warehouse workshops when detecting tobacco moth, a visual detection method for tobacco moth in cigarette factories based on improved lightweight YOLOv5s was developed. The method utilizes the correlation and redundancy between feature maps to design the EESP-Ghost module, and uses this module as the basis for designing a double-attention Ghost-bneck block incorporating an efficient spatial pyramid, which is introduced into the YOLOv5s model to achieve lightweighting of the deep neural network model while improving the detection accuracy. The method is used for validation experiments on the tobacco moth dataset. The results showed that the method improved the average accuracy by 4.37% with only 49.88% of the original YOLOv5s parameter count. When the tobacco moth adhering to the sticky board was detected in a real detection scenario, the method has high detection confidence and correct detection number, which could realize the high-precision real-time detection of the tobacco moth in the cigarette factory, and provide a guarantee for the effective control of the tobacco moth. -
-
[1]
曾涛, 宗钊辉, 陈桢禄, 等.烟草害虫绿色防控技术研究进展[J].安徽农业科学, 2022, 50(1):15-17
, 36. -
[2]
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.
-
[3]
徐聪, 王旭启, 刘裕.一种改进可形变FCN的农作物害虫检测方法[J].江苏农业科学, 2022, 50(9):211-219.
-
[4]
刘凯旋, 黄操军, 李亚鹏, 等.一种基于级联R-CNN的水稻害虫检测算法[J].黑龙江八一农垦大学学报, 2021, 33(5):106-111
, 134. -
[5]
肖德琴, 黄一桂, 张远琴, 等.基于改进Faster R-CNN的田间黄板害虫检测算法[J].农业机械学报, 2021, 52(6):242-251.
-
[6]
REN S Q, HE K M, GIRSHICK R, et al.Faster r-cnn:Towards real-time object detection with region proposal networks[J].Advances in Neural Information Processing Systems, 2015, 39(6):1137-1149.
-
[7]
陈向东, 邓江洪.基于显著性检测的害虫图像自动分割算法研究[J].中国粮油学报, 2021, 36(1):181-186.
-
[8]
苗海委, 周慧玲.基于深度学习的粘虫板储粮害虫图像检测算法的研究[J].中国粮油学报, 2019, 34(12):93-99.
-
[9]
林俊宇.基于机器视觉的烟虫检测方法研究[D].武汉:华中科技大学, 2020.
-
[10]
洪金华, 忻惠琴, 陆海华, 等.基于YOLOv3模型的卷烟厂烟虫识别方法[J].烟草科技, 2020, 53(9):77-84.
-
[11]
REDMON J, FARHADI A.YOLOv3:An incremental improvement[J/OL].arXiv:1804.02767, 2018[2023-03-10].https://arxiv.org/abs/1804.02767.
-
[12]
何雨, 田军委, 张震, 等.YOLOv5目标检测的轻量化研究[J].计算机工程与应用, 2023, 59(1):92-99.
-
[13]
杨锦辉, 李鸿, 杜芸彦, 等.基于改进YOLOv5s的轻量化目标检测算法[J].电光与控制, 2023, 30(2):24-30.
-
[14]
YANG Q S, LI W K, YANG X F, et al.Improved YOLOv5 method for detecting growth status of apple flowers[J].ComputEngAppl, 2022, 58(4):237-246.
-
[15]
DEVRIES T, TAYLOR G W.Improved regularization of convolutional neural networks with cutout[J/OL].arXiv:1708.04552, 2017[2023-03-10].https://arxiv.org/abs/1708.04552.
-
[16]
XU R J, LIN H F, LU K J, et al.A forest fire detection system based on ensemble learning[J].Forests, 2021, 12(2):217.
-
[17]
MEHTA S, RASTEGARI M, SHAPIRO L, et al.Espnetv2:A light-weight, power efficient, and general purpose convolutional neural network[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.[S.l.:s.n.], 2019:9190-9200.
-
[18]
HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.[S.l.:s.n.], 2016:770-778.
-
[19]
IOFFE S, SZEGEDY C.Batch normalization:Accelerating deep network training by reducing internal covariate shift[C]//International conference on machine learning.PMLR.[S.l.:s.n.], 2015:448-456.
-
[20]
MASTROMICHALAKIS S.ALReLU:A different approach on Leaky ReLU activation function to improve neural networks performance[J/OL].arXiv:2012.07564, 2020[2023-03-10].https://arxiv.org/abs/2012.07564.
-
[21]
FU J, LIU J, TIAN H J, et al.Dual attention network for scene segmentation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.[S.l.:s.n.], 2019:3146-3154.
-
[22]
DAI Y, LIU W M, WANG H, et al.YOLO-former:Marrying YOLO and transformer for foreign object detection[J].IEEE Transactions on Instrumentation and Measurement, 2022, 71:1-14.
-
[23]
GE Z, LIU S T, WANG F, et al.Yolox:Exceeding yolo series in 2021[J/OL].arXiv:2107.08430, 2021[2023-03-10].https://arxiv.org/abs/2107.08430.
-
[24]
YU J M, ZHANG W.Face mask wearing detection algorithm based on improved YOLOv4[J].Sensors, 2021, 21(9):3263.
-
[25]
WANG C Y, BOCHKOVSKIY A, LIAO H Y M.YOLOv7:Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J/OL].arXiv:2207.02696, 2022[2023-03-10].https://openaccess.thecvf.com/content/CVPR2023/html/Wang_YOLOv7_Trainable_Bag-of-Freebies_Sets_New_State-of-the-Art_for_Real-Time_Object_Detectors_CVPR_2023_paper.html.
-
[1]
-
点击查看大图
计量
- PDF下载量: 48
- 文章访问数: 2946
- 引证文献数: 0
下载:
