[1]芮 雪,王 娜. 改进YOLOv8网络的小目标识别算法研究[J].机械与电子,2026,44(03):41-46.
　RUI Xue,WANG Na. Research on Improved YOLOv8 Network Algorithm for Small Object Detection[J].Machinery & Electronics,2026,44(03):41-46.
点击复制

 改进YOLOv8网络的小目标识别算法研究()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
44
期数:
2026年03期
页码:
41-46
栏目:
智能检测
出版日期:
2026-03-25

文章信息/Info

Title:
 Research on Improved YOLOv8 Network Algorithm for Small Object Detection
文章编号:
1001-2257(2026)03-0041-06
作者:
 芮 雪; 王 娜
 (新疆师范高等专科学校(新疆教育学院),新疆 乌鲁木齐 830043)
Author(s):
 RUI Xue; WANG Na
 (Xinjiang Normal College (Xinjiang Education Institute),Urumqi 830034,China)
关键词:
 ; 小目标; YOLOv8; GhostNet; CA 注意力机制; 双向加权特征金字塔
Keywords:
small targets; YOLOv8; ghost network; CA attention mechanism; bidirectional weighted feature pyramid
分类号:
TP183;TP391.4
文献标志码:
A
摘要:
 针对传统YOLOv8网络在复杂厂房环境下进行小目标检测时,存在漏检率高、误检多、检测速度不足以及特征提取能力弱等问题,提出了一种融合多路径特征与注意力机制的改进方法。具体而言,为解决小目标特征表达能力弱、易受背景干扰的问题,引入了CA 注意力机制以增强对关键区域的关注并抑制背景噪声;为提升多尺度特征融合能力并保留更多细节信息,构建了双向加权特征金字塔网络BiFPN;同时,为兼顾检测速度与模型效率,采用了双分支输入结构,将图像输入分成GhostNet路径输入和主干神经网络路径输入,实现轻量化特征提取。此外,通过卷积Conv,进一步优化了特征表示与分类精度。最终,将所提改进模型应用于厂房环境的目标识别任务,结果表明,改进后的YOLOv8 网络,召回率、准确率、mAP50:95和mAP50分别提高了6.7百分点 、11.0百分点 、6.2百分点 和9.1百分点。
Abstract:
 To address the issues of high missed detection rate,frequent false positives,insufficient detection speed,and weak feature extraction capability encountered when using the traditional YOLOv8 network for small object detection in complex factory environments,this paper proposes an improved method combining multi path features and attention mechanisms.Specifically,to address the weak feature representation of small objects and their susceptibility to background interference,a CA attention mechanism is introduced to enhance focus on key regions and suppress background noise.To improve multi scale feature fusion and retain more detailed information,a bidirectional weighted feature pyramid network (BiFPN) is constructed.At the same time,to balance detection speed and model efficiency,a dual branch input structure is used,where the image input is divided into a GhostNet path and a backbone network path for lightweight feature extraction.Additionally,feature representation and classification accuracy are further optimized through Convolutional (Conv) operations.Finally,the proposed improved model is applied to target recognition tasks in factory environments.The results show that the improved YOLOv8 network achieves increases of 6.7 percentage points,11.0 percentage points,6.2 percentage points,and 9.1 percentage points in recall,precision,mAP50:95,and mAP50,respectively.

参考文献/References:

 [1] JIAO J J,LI Z G,XIA G Q,et al.A lightweight object detection approach for precision gripping in multiple peg in hole assembly tasks[J].Robotics and computer integrated manufacturing,2026,98:103185.
[2] ZENG Y Q,LEI D,ZHOU K Y,et al.Quantifying crack damage in BFRP reinforced concrete beams with YOLOv8 and 3D DIC[J].Journal of nondestructive evaluation,2025,44(4):138.
[3] 张轩宇,周思航,黄健,等.基于高阶空间特征提取的无人机航拍小目标检测算法[J].计算机工程与应用,2025,61(12):210 221.
[4] 和萌,武江鹏,梁超,等.融合特征重组和注意力的小样本战斗部破片群目标检测[J].光学精密工程,2024,32(12):1929 1940.
[5] 张震,王晓杰,晋志华,等.基于轻量化YOLOv5的交通标志检测[J].郑州大学学报(工学版),2024,45(2):12 19.
[6] 程婧怡,段先华,朱伟.改进YOLOv3的金属表面缺陷检测研究[J].计算机工程与应用,2021,57(19):252 258.
[7] 徐振峰,许云峰,于子洲,等.针对密集行人检测任务中多尺度目标的检测算法[J].计算机工程与应用,2025,61(17):304 316.
[8] 马鸽,李洪伟,严梓维,等.基于多注意力的改进YOLOv5s小目标检测算法[J].工程科学学报,2024,46(9):1647 1658.
[9] 王媛彬,韦思雄,吴华英,等.基于改进YOLOv5s的矿井下安全帽佩戴检测算法[J].煤炭科学技术,2025,53(增刊1):366 377.
[10] 蓝章礼,邢彩卓,张洪.基于改进YOLOv5s的被遮挡交通标志检测算法[J].计算机工程,2025,51(5):361 369.
[11] 镇帅,林远山,盛亦凡,等.基于双目视觉的海参体积测量方法[J].农业工程学报,2024,40(21):165 174.
[12] 周龙刚,魏本昌,魏鸿奥,等.改进YOLOV5的密集行人检测算法研究[J].软件导刊,2024,23(12):249 254.
[13] 武果,高守正,张德福,等.基于特征重组和注意力机制的YOLOv5光伏面板缺陷检测方法[J].自动化与信息工程,2024,45(5):47 53.
[14] SUN Y,CHEN G Y,MA Y N,et al.Rep YOLOv8:an enhanced object detector with deep feature representation for autonomous driving[J].The journal of supercomputing,2025,81:1347.
[15] SRI J S,ESTHER R E.LittleYOLO SPP:a delicate real time vehicle detection algorithm [J].Optik,2021,225:165818.
[16] WU Z Q,TOHTI G,GENI M,et al.Wind turbine rotor blade encoding marker recognition method based on improved YOLOv8 model[J].Signal,image and video processing,2024,18:6949 6960.
[17] ZHANG E Y,ZHANG H.An intelligent apple identification method via the collaboration of YOLOv5 algorithm and fast guided filter theory[J].Journal of circuits,systems and computers,2024,33(11):2450188.

相似文献/References:

[1]雷永涛,周 权,张静静. 基于印制电路连接器变形问题的分析和设计改进[J].机械与电子,2019,(01):7.
　,analysis and design improvement of deformation problem based on printed circuit connector[J].Machinery & Electronics,2019,(03):7.
[2]孟繁萃１,张 达２,张 明１. 自然风力对绝缘子结构的影响[J].机械与电子,2019,(01):3.
　,the influence of natural wind on insulator structure[J].Machinery & Electronics,2019,(03):3.
[3]任智勇１,邓晓政１,马丁峰２. 一种发动机试飞数据快速处理方法[J].机械与电子,2019,(01):11.
　,A Fast Processing Method of Multi-subject Engine Flight Test Data[J].Machinery & Electronics,2019,(03):11.
[4]冷雪锋,吴正明. 基于ＳＴＣ１２Ｃ５Ａ６０Ｓ２的１００Ｗ 小型风力发电系统设计[J].机械与电子,2019,(01):15.
　.The Design of 100W Small Wind Power Generation System Based on STC12C5A60S2[J].Machinery & Electronics,2019,(03):15.
[5]查金水,朱志远,邓友银,等. 某大型相控阵雷达测试系统结构设计[J].机械与电子,2019,(01):19.
　,,et al.Structural Design of a Large Phased Array Radar Test System[J].Machinery & Electronics,2019,(03):19.
[6]万 欢,李伟达,李 娟. 一种面向上肢康复的便携式电刺激器设计[J].机械与电子,2019,(01):33.
　,Design of Portable Electric Stimulator for Upper Limb Rehabilitation[J].Machinery & Electronics,2019,(03):33.
[7]郑锦汤１,李玉忠１,２. 紧凑型纯电动汽车动力系统匹配与性能仿真[J].机械与电子,2019,(01):38.
　,Matching and Performance Simulation of Dynamic Systems of Compact Electric Vehicle[J].Machinery & Electronics,2019,(03):38.
[8]吕明珠１,２,苏晓明 １,等. 改进粒子群算法优化的支持向量机在滚动轴承故障诊断中的应用[J].机械与电子,2019,(01):42.
　,,et al.Application of SVM Optimized by IPSO in Rolling Bearing Fault Diagnosis[J].Machinery & Electronics,2019,(03):42.
[9]韩雪莹１,张佳炜２,刘 梦１,等. 集中控制协调多个并网逆变器的谐波补偿[J].机械与电子,2019,(01):49.
　,,et al.Centralized Control Coordination of Harmonic Compensation for Multiple Grid-connected Inverters[J].Machinery & Electronics,2019,(03):49.
[10]蒋 波１,３,周自强２,等. 基于ＰＬＣ的报废汽车拆解线作业控制系统[J].机械与电子,2019,(01):54.
　,,et al.PLC-based ELV Disassembly Line Operation Control System[J].Machinery & Electronics,2019,(03):54.

备注/Memo

备注/Memo:
 收稿日期:2025-12-02
基金项目:新疆维吾尔自治区自然科学基金项目(2024D01A97)
作者简介:芮 雪 (1979-),女,山东商河人,硕士,副教授,研究方向为操作系统、算法等,通信作者,E-mail:31763825@qq.com。
更新日期/Last Update: 2026-04-29