YOLOv5s-CBAM算法在福寿螺虫卵识别中的应用分析

doi:10.13733/j.jcam.issn.2095-5553.2024.06.033

摘要/Abstract

摘要：

福寿螺是我国重点关注的入侵物种，对农作物生长和生态环境会造成不利影响。及时获取福寿螺虫卵的分布信息，对于提前防治其入侵能起到有效的帮助作用。基于YOLOv5s基础网络模型，引入CBAM（Convolutional Block Attention Module）注意力机制模块，以提高在复杂的自然环境下对福寿螺虫卵特征信息的提取，提出YOLOv5sCBAM模型进行福寿螺虫卵识别方法。试验结果表明，引入CBAM的识别效果要好于引入CA和SE注意力模块。同时，引入CBAM的YOLOv5sCBAM模型，识别效果优于原基础YOLOv5s模型，一定程度上能够克服倒影、植物遮挡等因素干扰。且平均精度均值达到83.8%，相比原模型提升2.5个百分点。基于深度学习的方法对复杂自然环境中的福寿螺虫卵进行识别是切实可行的，为福寿螺等入侵物种的监测防控提供新的思路。

关键词: 深度学习, YOLOv5s算法, 注意力机制, 福寿螺虫卵, 图像识别

Abstract:

Pomacea is an invasive species of major concern in China, which can have a negative impact on crop growth and the ecological environment. The timely acquisition of information on the distribution of eggs of Pomacea can help to prevent and control its invasion in advance. In order to improve the extraction of feature information from the Pomacea eggs in complex natural environments, this paper suggests a YOLOv5sCBAM model for eggs of Pomacea recognition based on the YOLOv5s base network model and incorporating the CBAM (Convolutional Block Attention Module) attention mechanism module. The experimental results show that the incorporation of the CBAM module provides better recognition than the introduction of the CA and SE attention modules. The YOLOv5sCBAM model, which incorporates CBAM, has a stronger recognition impact than the original YOLOv5s model and can, in some cases, overcome interference from elements like plant obscuration and reflection in the water. A 2.5 percentage point improvement over the original model, the mAP now stands at 83.8%. The method based on deep learning is feasible to identify the eggs of Pomacea in photographs obtained in complicated natural environment, which provides a fresh perspectives for the monitoring, prevention, and management of invasive species such as Pomacea.

Key words: deep learning, YOLOv5s algorithm, attention mechanism, eggs of Pomacea, image recognition

中图分类号:

TP391.4

黄尧, 何敬, 付饶, 刘刚, , 林远杨. YOLOv5s-CBAM算法在福寿螺虫卵识别中的应用分析[J]. 中国农机化学报, 2024, 45(6): 223-228.

Huang Yao, He Jing, Fu Rao, Liu Gang, , Lin Yuanyang. Application analysis of the YOLOv5s-CBAM algorithm for the identification of eggs of Pomacea[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 223-228.

参考文献

［1］　Burks R L, Bernatis J, Byers J E, et al. Identity, reproductive potential, distribution, ecology and management of invasive Pomacea maculata in the southern united states ［J］. Biology and Management of Invasive Apple Snails. Philippine Rice Research Institute, Maligaya, Science City of Muoz, Nueva Ecija, 2017, 3119: 293-333.

［2］　刘义满, 戢小梅, 李长林, 等. 福寿螺［Pomacea canaliculata (Lamarck, 1819)］的世界分布［J］. 湖北农业科学, 2019, 58(6): 70-72, 77.

Liu Yiman, Ji Xiaomei, Li Changlin, et al. The global distribution of apple snail ［Pomacea canaliculata (Lamarck, 1819)］［J］. Hubei Agricultural Sciences, 2019, 58(6): 70-72, 77.

［3］　任和, 高红娟, 薛娟, 等. 福寿螺的生物学特性与防治［J］. 生物学通报, 2020, 55(12): 1-3.

Ren He, Gao Hongjuan, Xue Juan, et al. The preliminary study on biological characteristics and control methods of Pomacea canaliculata ［J］. Bulletin of Biology, 2020, 55(12): 1-3.

［4］　卓富彦, 王华生, 刘万才. 2011—2020年我国农田福寿螺发生防控情况［J］. 中国植保导刊, 2022, 42(1): 52-55.

Zhuo Fuyan, Wang Huasheng, Liu Wancai. Occurrence and management of Pomacea canaliculata in the farmland of China from 2011 to 2020 ［J］. China Plant Protection, 2022, 42(1): 52-55.

［5］　魏然, 吴承东, 谢洪芳, 等. 入侵性有害生物福寿螺在江苏的风险分析［J］. 扬州大学学报(农业与生命科学版), 2021, 42(6): 119-124, 37.

Wei Ran, Wu Chengdong, Xie Hongfang, et al. Risk analysis of the alien invasive pest Pomacea spp. in Jiangsu Province ［J］. Journal of Yangzhou University(Agricultural and Life Science Edition), 2021, 42(6): 119-124, 37.

［6］　贺超, 杨倩倩, 刘苏汶, 等. 我国外来入侵生物福寿螺种类的多重PCR鉴别方法［J］. 植物保护学报, 2019, 46(1): 97-105.

He Chao, Yang Qianqian, Liu Suwen, et al. Multiplex PCR detection of alien invasive apple snails introduced to China ［J］. Journal of Plant Protection, 2019, 46(1): 97-105.

［7］　Xu Y, Liu N, Yin T, et al. A multiscale feature fusion method for automatic detection of eggs from two Pomacea spp. in UAV aerial images ［J］. IEEE Geoscience and Remote Sensing Letters, 2021, 19: 1-5.

［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.

Miao Haiwei, Zhou Huiling. Detection of storedgrain insects image on sticky board u sing deep learning ［J］. Journal of the Chinese Cereals and Oils Association, 2019, 34(12): 93-99.

［9］　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.

［10］　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.

Zhang Bo, Zhang Miaohui, Chen Yunzhong. Crop pest identification based on spatial pyramid pooling and deep convolution neural network ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(19): 209-215.

［11］　骆润玫, 殷惠莉, 刘伟康, 等. 基于YOLOv5-C的复杂背景广佛手病虫害识别［J］. 华南农业大学学报, 2023(1): 1-16.

Luo Runmei, Yin Huili, Liu Weikang, et al. Identification of bergamot pests and diseases in complex back ground using YOLOv5-C algorithm ［J］. Journal of South China Agricultural University, 2023(1): 1-16.

［12］　Fuentes A, Yoon S, Kim S C, et al. A robust deeplearningbased detector for realtime tomato plant diseases and pests recognition ［J］. Sensors, 2017, 17(9): 2022.

［13］　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, 2016: 779-788.

［14］　Yan B, Fan P, Lei X, et al. A realtime apple targets detection method for picking robot based on improved YOLOv5 ［J］. Remote Sensing, 2021, 13(9): 1619.

［15］　Chen Z, Wu R, Lin Y, et al. Plant disease recognition model based on improved YOLOv5［J］. Agronomy, 2022, 12(2): 365.

［16］　Chen J, Zhang H, He X, et al. Attentive collaborative filtering: Multimedia recommendation with itemand componentlevel attention ［C］. Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017: 335-344.

［17］　黄彤镔, 黄河清, 李震, 等. 基于YOLOv5改进模型的柑橘果实识别方法［J］. 华中农业大学学报, 2022, 41(4): 170-177.

Huang Tongbin, Huang Heqing, Li Zhen, et al. Citrus fruit recognition method based on the improved model of YOLOv5 ［J］. Journal of Huazhong Agricultural University, 2022, 41(4): 170-177.

［18］　Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module ［C］. Proceedings of the European Conference on Computer Vision (ECCV), 2018: 3-19.

［19］　蒋芸, 张海, 陈莉, 等. 基于卷积神经网络的图像数据增强算法［J］. 计算机工程与科学, 2019, 41(11):2007-2016.

Jiang Yun, Zhang Hai, Chen Li, et al. An image data augmentation algorithm based on convolutional neural networks ［J］. Computer Engineering & Science, 2019, 41(11): 2007-2016.

[1]	岳耀华, 张伟, 亓立强, . 基于改进YOLOv5的田间大豆花朵生长状态检测方法研究[J]. 中国农机化学报, 2024, 45(7): 188-193.
[2]	黄亦其, 鹿林飞, 沈豪, 王福宽, 乔曦, . 基于卷积神经网络的入侵昆虫识别研究[J]. 中国农机化学报, 2024, 45(7): 222-227.
[3]	吴利刚, 吕媛媛, 周倩, 陈乐, 张梁, 史建华. 基于改进YOLOv5的轻量级黄花成熟检测方法[J]. 中国农机化学报, 2024, 45(7): 235-242.
[4]	张继成, 黄向党. 基于改进YOLOv3的玉米病害识别方法[J]. 中国农机化学报, 2024, 45(7): 269-275.
[5]	雷浩, 苑迎春, 何振学. 基于多尺度卷积和注意力机制的枣品种识别[J]. 中国农机化学报, 2024, 45(6): 135-141.
[6]	李龙杰, 史勇, , 刘彦岑, , 郭俊先, . 基于RGB图像处理预测哈密瓜叶片叶绿素研究[J]. 中国农机化学报, 2024, 45(6): 149-155.
[7]	崔海朋, 秦朝旭, 马志宇. 基于深度学习的鱼类特征点检测与体征识别方法[J]. 中国农机化学报, 2024, 45(6): 201-207.
[8]	石放, 王莹, 王新法, 马玉琨. 基于RegNet网络的马铃薯病害识别研究[J]. 中国农机化学报, 2024, 45(6): 229-234.
[9]	周康乔, 刘向阳, 郑特驹. 改进YOLOv5的小目标多类别农田害虫检测算法研究[J]. 中国农机化学报, 2024, 45(6): 235-241.
[10]	陶旭, , 余富强, , 蔡金金, 么炜, , 刘博, . 面向激光雷达点云数据的多结构树种识别[J]. 中国农机化学报, 2024, 45(5): 168-175.
[11]	漆海霞, , , 李承杰, 黄桂珍. 基于轻量化YOLOv4的死淘鸡目标检测算法[J]. 中国农机化学报, 2024, 45(5): 195-201.
[12]	罗鑫, 李加强, 何超. 基于改进YOLOv4的澳洲坚果视觉监测方法[J]. 中国农机化学报, 2024, 45(5): 217-222.
[13]	廖舒怀, , 王凯, 宋健, 解福祥, 王名声, , 龚中良. 基于移动机器人的树木识别与冠层信息测量[J]. 中国农机化学报, 2024, 45(5): 232-238.
[14]	郭宏杰, 马睿, 王佳, 赵威, 马德新. 基于卷积神经网络的苹果叶部病害图像识别研究[J]. 中国农机化学报, 2024, 45(5): 239-245.
[15]	王化佳, 顾寄南, 王梦妮, 夏子林. 基于深度学习的茶嫩芽分割与采摘点定位方法研究[J]. 中国农机化学报, 2024, 45(5): 246-252.