基于改进YOLO算法的玉米苗间杂草检测模型研究  

Interseedling Weed Detection Model of Maize Based on Improved YOLO Algorithm

作　　者：肖立同 王熙[1] Xiao Litong;Wang Xi(College of Engineering,Heilongjiang Bayi Agricultural University,Daqing 163319,China)

机构地区：[1]黑龙江八一农垦大学工程学院,黑龙江大庆163319

出　　处：《农机化研究》2025年第8期10-16,共7页Journal of Agricultural Mechanization Research

基　　金：“十三五”国家重点研发计划项目(2016YFD020060802);黑龙江省农垦总局重点科研计划项目(HKKY190504)。

摘　　要：为实现田间复杂环境下玉米幼苗与杂草的精准识别,通过对PP-YOLOE算法进行改进和优化,包括引入坐标注意力机制和ASPP(Atrous Spatial Pyramid Pooling)结构,提出了一种用于玉米苗间杂草检测的AAPP-YOLOE模型。试验结果表明,AAPP-YOLOE模型在玉米苗间杂草检测中取得了显著的性能提升。模型在召回率、准确率和F1-Score指标上表现更佳,证明了算法在玉米苗间杂草检测中的有效性和实用性,可为农业生产管理提供一定的帮助,有助于减轻杂草对玉米苗生长的影响。In order to realize the accurate identification of maize seedlings and weeds in complex field environment,according to the characteristics and requirements of this task,the PP-YOLOE algorithm was improved and optimized,including the introduction of coordinate attention mechanism and ASPP(Atrous Spatial Pyramid Pooling)structure,and an AAPP-YOLOE model for the detection of weeds between maize seedlings was proposed.The experimental results showed that the AAPP-YOLOE model had achieved significant performance improvement in the detection of weeds between maize seedlings.The model showed superior performance in recall,accuracy and F1-Score indicators,which proved the effectiveness and practicality of the algorithm in the detection of weeds between maize seedlings,which can provide some help for agricultural management and help reduce the impact of weeds on the growth of maize seedlings.

关 键 词：玉米苗 杂草 目标检测 注意力机制 ASPP 

分 类 号：S126[农业科学—农业基础科学] TP391.4[自动化与计算机技术—计算机应用技术]