基于改进YOLOv5的平贝母检测模型

doi:10.16088/j.issn.1001-6600.2023040101

摘要/Abstract

摘要： 现有平贝母表土剥离机智能化程度不高,在收获平贝母时存在造成平贝母损伤的问题,故需要研制一款智能化的平贝母表土剥离机,而实现智能表土剥离的第一步就是实现智能识别,因此,提出一种基于改进YOLOv5的平贝母检测模型YOLOv5-Swin-L。通过引入Swin transformer,在骨干网络中替换C3,减少序列长度和降低计算复杂度,从而简化模型的参数量;同时用ACON激活函数将原来网络结构中的激活函数替换,可提高模型的精确度,增加模型的鲁棒性。实验结果表明,改进后的YOLOv5-Swin-L对平贝母识别的准确率最高可达96.39%,召回率最高可达95.76%,优于YOLOv5系列的其他网络模型。

关键词: 平贝母, 检测, YOLOv5, Swin transformer, ACON

Abstract: The existing Fritillaria ussuriensis Maxim topsoil stripping machine is not highly intelligent and may cause Fritillaria ussuriensis Maxim damage when harvesting Fritillaria ussuriensis Maxim, so it is necessary to develop an intelligent Fritillaria ussuriensis Maxim topsoil stripping machine, and the first step to realize intelligent topsoil stripping is to realize intelligent identification. Therefore, a Fritillaria ussuriensis Maxim detection model based on improved YOLOv5-YOLOv5-Swin-L is proposed. Swin Transformer is introduced to replace C3 in the backbone network to reduce the sequence length and computational complexity, thus simplifying the number of parameters in the model. At the same time, the activation function in the original network structure is replaced by ACON activation function, which can improve the accuracy and robustness of the model. Experimental results show that the improved YOLOv5-Swin-L can identify Fritillaria ussuriensis maxim with the highest accuracy of 96.39% and the highest recall rate of 95.76%, which is superior to other network models of YOLOv5 series.

Key words: Fritillaria ussuriensis Maxim, detection, YOLOv5, Swin transformer, ACON

中图分类号: TP391.41;TP183;S225

赵伟, 田帅, 张强, 王耀申, 王思博, 宋江. 基于改进YOLOv5的平贝母检测模型[J]. 广西师范大学学报（自然科学版）, 2023, 41(6): 22-32.

ZHAO Wei, TIAN Shuai, ZHANG Qiang, WANG Yaoshen, WANG Sibo, SONG Jiang. Fritillaria ussuriensis Maxim Detection Model Based on Improved YOLOv5[J]. Journal of Guangxi Normal University(Natural Science Edition), 2023, 41(6): 22-32.

参考文献

[1] 沈莹, 孙海峰.平贝母化学成分及药理作用研究进展[J].化学工程师,2018,32(6):62-66.DOI:10.16247/j.cnki.23-1171/tq.20180662.
[2] 王晔.平贝母高效栽培技术[J].特种经济动植物,2021,24(8):46-47.DOI:10.3969/j.issn.1001-4713.2021.08.021.
[3] 秦绪霞,宋青,秦斌,等.平贝母人工栽培技术实践[J].农业开发与装备,2021(12):221-222.DOI:10.3969/j.issn.1673-9205.2021.12.104.
[4] 石子建,李建辉.贝母关键栽培技术及种植模式研究进展[J].现代农业科技,2017(20):59-61.DOI:10.3969/j.issn.1007-5739.2017.20.038.
[5] 吴立国,满大为,苗振坤,等.平贝母产业生产技术研究进展[J].林业机械与木工设备,2020,48(12):4-7.DOI:10.13279/j.cnki.fmwe.2020.0135.
[6] 宋江,刘丽华,王密,等.4B-1200型平贝母药材收获机的改进设计与试验[J].农业工程学报,2017,33(1):45-51.DOI:10.11975/j.issn.1002-6819.2017.01.006.
[7] 王密.4B-1200型平贝母收获机关键部件优化设计与试验[D].大庆:黑龙江八一农垦大学,2017.
[8] 马川.平贝收获机的研究[D].哈尔滨:东北林业大学,2020.DOI:10.27009/d.cnki.gdblu.2020.000822.
[9] 林森,刘美怡,陶志勇.采用注意力机制与改进YOLOv5的水下珍品检测[J].农业工程学报,2021,37(18):307-314.DOI:10.11975/j.issn.1002-6819.2021.18.035.
[10] GAO F F, FU L S, ZHANG X, et al. Multi-class fruit-on-plant detection for apple in SNAP system using Faster R-CNN[J]. Computers and Electronics in Agriculture, 2020, 176: 105634. DOI: 10.1016/j.compag.2020.105634.
[11] CHEN J Q, WANG Z K, WU J H, et al. An improved Yolov3 based on dual path network for cherry tomatoes detection[J]. Journal of Food Process Engineering, 2021, 44(10): e13803. DOI: 10.1111/jfpe.13803.
[12] CHEN Y P, LI J N, XIAO H X, et al. Dual path networks[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2017: 4470-4478. DOI: 10.5555/3294996.3295200.
[13] 夏烨,雷哓晖,祁雁楠,等.基于改进Ghost-YOLOv5s-BiFPN算法检测梨树花序[J].智慧农业:中英文,2022,4(3):108-119.DOI:10.12133/j.smartag.SA202207006.
[14] KHAN S, NASEER M, HAYAT M, et al. Transformers in vision: a survey[J]. ACM Computing Surveys, 2022, 54(10s): 1-41. DOI: 10.1145/3505244.
[15] LI Y H, MAO H Z, GIRSHICK R, et al. Exploring plain vision transformer backbones for object detection[C]// Computer Vision–ECCV 2022. Cham: Springer, 2022: 280-296. DOI: 10.1007/978-3-031-20077-9_17.
[16] LIU Z, LIN Y T, CAO Y, et al. Swin Transformer: hierarchical vision transformer using shifted windows[C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Los Alamitos, CA: IEEE Computer Society, 2021: 9992-10002. DOI: 10.1109/ICCV48922.2021.00986.
[17] NASEER M M, RANASINGHE K, KHAN S H, et al. Intriguing properties of vision transformers[C]// Advances in Neural Information Processing Systems 34. Red Hook, NY: Curran Associates, Inc., 2021: 23296-23308.
[18] ZHENG H, WANG G H, LI X C. Swin-MLP: a strawberry appearance quality identification method by swin transformer and multi-layer perceptron[J]. Journal of Food Measurement and Characterization, 2022, 16(4): 2789-2800. DOI: 10.1007/s11694-022-01396-0.
[19] WANG F Y, RAO Y, LUO Q, et al. Practical cucumber leaf disease recognition using improved swin transformer and small sample size[J]. Computers and Electronics in Agriculture, 2022, 199: 107163. DOI: 10.1016/j.compag.2022.107163.
[20] 常志远,刘昌奎,李志农,等.基于ACON激活函数和CNN的滚动轴承故障诊断方法研究[J/OL].轴承:1-9[2023-03-01].http://kns.cnki.net/kcms/detail/41.1148.TH.20230220.1559.002.html.
[21] 邹鹏,杨凯军,梁晨.改进YOLOv5的轻量级不规范驾驶行为实时检测[J/OL].计算机工程与应用:1-9[2023-03-01].http://kns.cnki.net/kcms/detail/11.2127.TP.20230206.1311.003.html.

相关文章 15

[1]	周桥, 翟江涛, 荚东升, 孙浩翔. 基于卷积门控循环神经网络的Web攻击检测方法[J]. 广西师范大学学报（自然科学版）, 2023, 41(6): 51-61.
[2]	吴正清, 曹晖, 刘宝锴. 基于注意力卷积神经网络的中文虚假评论检测[J]. 广西师范大学学报（自然科学版）, 2023, 41(5): 26-36.
[3]	欧阳舒歆, 王洺钧, 荣垂田, 孙华波. 基于改进LSTM的多维QAR数据异常检测[J]. 广西师范大学学报（自然科学版）, 2023, 41(5): 49-60.
[4]	黄叶祺, 王明伟, 闫瑞, 雷涛. 基于改进的YOLOv5金刚石线表面质量检测[J]. 广西师范大学学报（自然科学版）, 2023, 41(4): 123-134.
[5]	杨烁祯, 张珑, 王建华, 张恒远. 声音事件检测综述[J]. 广西师范大学学报（自然科学版）, 2023, 41(2): 1-18.
[6]	魏明军, 周太宇, 纪占林, 张鑫楠. 基于YOLOv3的公共场所口罩佩戴检测方法[J]. 广西师范大学学报（自然科学版）, 2023, 41(1): 76-86.
[7]	罗家锱, 宋习习, 李梅珊, 王恒山. 松香烷型二萜在农药及药学中的研究进展[J]. 广西师范大学学报（自然科学版）, 2022, 40(5): 253-270.
[8]	李永杰, 周桂红, 刘博. 基于YOLOv3模型的人脸检测与头部姿态估计融合算法[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 95-103.
[9]	段美玲, 潘巨龙. 基于双向LSTM神经网络可穿戴跌倒检测研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 141-150.
[10]	薛其威, 伍锡如. 基于多模态特征融合的无人驾驶系统车辆检测[J]. 广西师范大学学报（自然科学版）, 2022, 40(2): 37-48.
[11]	张文龙, 南新元. 基于改进YOLOv5的道路车辆跟踪算法[J]. 广西师范大学学报（自然科学版）, 2022, 40(2): 49-57.
[12]	陈文康, 陆声链, 刘冰浩, 李帼, 刘晓宇, 陈明. 基于改进YOLOv4的果园柑橘检测方法研究[J]. 广西师范大学学报（自然科学版）, 2021, 39(5): 134-146.
[13]	张伟彬, 吴军, 易见兵. 基于RFB网络的特征融合管制物品检测算法研究[J]. 广西师范大学学报（自然科学版）, 2021, 39(4): 34-46.
[14]	朱勇建, 罗坚, 秦运柏, 秦国峰, 唐楚柳. 基于光度立体和级数展开法的金属表面缺陷检测方法[J]. 广西师范大学学报（自然科学版）, 2020, 38(6): 21-31.
[15]	唐熔钗, 伍锡如. 基于改进YOLO-V3网络的百香果实时检测[J]. 广西师范大学学报（自然科学版）, 2020, 38(6): 32-39.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed