基于改进YOLOv8算法的水稻田间人工施肥行为识别  

Detection and recognition of artificial fertilization behavior in rice fields based on improved YOLOv8

作　　者：卢明 余心杰 郭俊先 Lu Ming;Yu Xinjie;Guo Junxian(College of Mechanical and Electrical Engineering,Xinjiang Agricultural University,Urumqi,830052,China;College of Computer and Data Engineering,Ningbo Tech University,Ningbo,315100,China)

机构地区：[1]新疆农业大学机电工程学院,乌鲁木齐市830052 [2]浙大宁波理工学院计算机与数据工程学院,宁波市315100

出　　处：《中国农机化学报》2025年第1期220-226,共7页Journal of Chinese Agricultural Mechanization

基　　金：科技创新团队(天山创新团队)项目(2022TSYCTD0011);宁波市科技计划项目(2022S229)。

摘　　要：在水稻种植过程中,为实现人工施肥行为自动化的检测和识别,以浙江省宁波市海曙区数字农业中心水稻田间的人工施肥行为识别作为研究目标,开展基于YOLOv8算法的水稻田间人工施肥行为识别研究。在YOLOv8算法的基础上增加目标检测层,保留浅层特征信息,增强网络模型对小尺寸目标特征的感知能力;引入全局注意力模块,增强网络模型对全局特征信息的关注度。结果表明,改进后的YOLOv8-GS识别模型mAP值为98.4%,比原YOLOv8模型提高2.4%,每幅图像检测时间为1.7 ms。对小尺寸目标测试集检测,mAP值为98.6%,比改进前提高3.3%。YOLOv8-GS模型具有高精度、实时性、多尺度等优点,特别是对小尺寸目标具有较强的检测和识别能力。In order to automate the detection and recognition of manual fertilizer application during the rice cultivation process,this study focuses on the recognition of manual fertilizer application in the rice fields at the Digital Agriculture Center in Haishu District,Ningbo City,Zhejiang Province.The research utilizes the YOLOv8 algorithm for behavior recognition and detection of manual fertilizer application in the rice fields.Building upon the YOLOv8 algorithm,a target detection layer is introduced to retain shallow feature information and enhance the perception capability of the network model towards small-sized targets.Additionally,a global attention module is incorporated to improve the emphasis on global feature information by the network model.The research results demonstrate that the improved YOLOv8-GS recognition model achieves an mAP value of 98.4%,exhibiting a 2.4%improvement compared to the original YOLOv8 model.The detection time of each image is 1.7 ms.Specifically for the test set featuring small-sized targets,the mAP value reaches 98.6%,indicating a 3.3%improvement from the previous version.These findings validate that the YOLOv8-GS model possesses advantages such as high precision,real-time performance,and multi-scale capabilities,especially for small-size targets with strong detection and recognition ability.

关 键 词：水稻 施肥 行为识别 YOLOv8 检测层 注意力机制 

分 类 号：S282[农业科学—农业水土工程] TP391.41[农业科学—农业工程]