改进YOLOv8s的轻量级无人机航拍小目标检测算法

doi:10.3785/j.issn.1008-973X.2025.08.018

浙江大学学报(工学版)

2025, Vol. 59

Issue (8): 1708-1717 DOI: 10.3785/j.issn.1008-973X.2025.08.018

计算机技术、控制工程、通信技术

改进YOLOv8s的轻量级无人机航拍小目标检测算法

翟亚红(

),陈雅玲,徐龙艳*(

),龚玉

湖北汽车工业学院电气与信息工程学院，湖北十堰 442002

Improved YOLOv8s lightweight small target detection algorithm of UAV aerial image

Yahong ZHAI(

),Yaling CHEN,Longyan XU*(

),Yu GONG

School of Electrical and Information Engineering, Hubei University of Automotive Technology, Shiyan 442002, China

全文: PDF(2456 KB) HTML

摘要：

针对无人机航拍图像背景复杂、目标尺寸小及设备资源有限等问题，提出轻量化小目标检测算法RTA-YOLOv8s. 在主干网络引入RepVGG模块，增强特征提取能力. 应用三分支注意力机制，降低小目标的误检率和漏检率. 增加小目标专用检测头，提高对小目标的检测能力. 采用WIoUv3作为损失函数，提升模型的定位性能和鲁棒性. 实验结果表明，RTA-YOLOv8s算法在VisDrone数据集中的mAP50达到44.9%，检测速度达到88.5帧/s. 与基线算法YOLOv8s相比，mAP50提升了6.1%，检测准确率提高了4.7%，参数量减少了13.9%. 利用改进的算法，有效解决了复杂场景下检测效果不佳的问题，在精度和速度之间取得了很好的平衡. 设计人机界面，实现结果可视化，使检测任务更加直观且易操作，适合无人机航拍的目标检测.

关键词： 无人机(UAV); 小目标检测; YOLOv8s; 轻量化方法; 注意力机制

Abstract:

A lightweight small target detection algorithm called RTA-YOLOv8s was proposed in order to address the challenges of complex backgrounds, small target, and limited device resources in UAV images. The RepVGG module was introduced into the backbone network to enhance feature extraction capabilities. A tri-branch attention mechanism was applied to reduce false positive and false negative rates. A dedicated small target detection head was integrated to improve detection accuracy. The WIoUv3 loss function was adopted to improve localization and robustness. The experimental results showed that the RTA-YOLOv8s algorithm achieved a mAP50 of 44.9% and detection speed of 88.5 frame per second on the VisDrone dataset. mAP50 increased by 6.1%, detection accuracy increased by 4.7%, and params reduced by 13.9% compared with YOLOv8s. The improved algorithm effectively addresses the poor detection performance in complex UAV scenes, and balances accuracy and speed. The user-friendly interface design enables result visualization, making detection tasks more intuitive and easier to operate, and is suitable for UAV target detection.

Key words: unmanned aerial vehicle (UAV) small target detection YOLOv8s lightweight approach attention mechanism

收稿日期: 2024-07-16 出版日期: 2025-07-28

TP 391

基金资助: 湖北省教育厅科研计划资助项目(D202111802)；湖北省科技厅重点研发计划资助项目(2022BEC008)；中南民族大学信息物理融合智能计算国家民委重点实验室开放基金资助项目(CPFIC202402).

通讯作者: 徐龙艳 E-mail: zhaiyh_dy@huat.edu.cn;xuly_dy@huat.edu.cn

作者简介: 翟亚红（1979—），女，教授，从事目标检测的研究. orcid.org/0009-0008-9334-3729. E-mail：zhaiyh_dy@huat.edu.cn

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	作者相关文章
	翟亚红
	陈雅玲
	徐龙艳
	龚玉

引用本文:

翟亚红,陈雅玲,徐龙艳,龚玉. 改进YOLOv8s的轻量级无人机航拍小目标检测算法[J]. 浙江大学学报(工学版), 2025, 59(8): 1708-1717.

Yahong ZHAI,Yaling CHEN,Longyan XU,Yu GONG. Improved YOLOv8s lightweight small target detection algorithm of UAV aerial image. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1708-1717.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2025.08.018 或 https://www.zjujournals.com/eng/CN/Y2025/V59/I8/1708

图 1 改进的轻量化RTA-YOLOv8s网络结构

图 2 RepVGG网络的结构

图 3 Triplet注意力机制的结构

图 4 四尺度特征融合网络

图 5 CIoU与WIoU的示意图

表 1 改进模块的消融实验结果

图 6 不同损失函数曲线的对比

图 7 YOLOv8s算法改进前、后的指标对比

表 2 不同算法在VisDrone 2019数据集上的对比实验结果

图 8 不同模型的AP对比

图 9 热力图可视化结果

图 10 不同环境下的检测结果

图 11 无人机目标智能检测系统的总体框架

图 12 系统检测界面

1	ZRELLI I, REJEB A, ABUSULAIMAN R, et al Drone applications in logistics and supply chain management: a systematic review using latent Dirichlet allocation[J]. Arabian Journal for Science and Engineering, 2024, 49 (9): 12411- 12430 doi: 10.1007/s13369-023-08681-0
2	奉志强, 谢志军, 包正伟, 等基于改进YOLOv5的无人机实时密集小目标检测算法[J]. 航空学报, 2023, 44 (7): 251- 265 FENG Zhiqiang, XIE Zhijun, BAO Zhengwei, et al Real-time dense small object detection algorithm for UAV based on improved YOLOv5[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44 (7): 251- 265
3	WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 7464-7475.
4	ZHU X K, LYU S C, WANG X, et al. TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Montreal: IEEE, 2021: 2778-2788.
5	WANG G, CHEN Y F, AN P, et al UAV-YOLOv8: a small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios[J]. Sensors, 2023, 23 (16): 7190 doi: 10.3390/s23167190
6	LI Y T, FAN Q S, HUANG H S, et al A modified YOLOv8 detection network for UAV aerial image recognition[J]. Drones, 2023, 7 (5): 304 doi: 10.3390/drones7050304
7	SHAO Y F, YANG Z X, LI Z H, et al Aero-YOLO: an efficient vehicle and pedestrian detection algorithm based on unmanned aerial imagery[J]. Electronics, 2024, 13 (7): 1190 doi: 10.3390/electronics13071190
8	XU L Y, ZHAO Y F, ZHAI Y H, et al Small object detection in UAV images based on YOLOv8n[J]. International Journal of Computational Intelligence Systems, 2024, 17 (1): 1- 9 doi: 10.1007/s44196-023-00380-w
9	SUI J C, CHEN D K, ZHENG X, et al A new algorithm for small target detection from the perspective of unmanned aerial vehicles[J]. IEEE Access, 2024, 12 (99): 29690- 29697
10	刘树东, 刘业辉, 孙叶美, 等基于倒置残差注意力的无人机航拍图像小目标检测[J]. 北京航空航天大学学报, 2023, 49 (3): 514- 524 LIU Shudong, LIU Yehui, SUN Yemei, et al Small object detection in UAV aerial images based on inverted residual attention[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49 (3): 514- 524
11	潘玮, 韦超, 钱春雨, 等面向无人机视角下小目标检测的YOLOv8s改进模型[J]. 计算机工程与应用, 2024, 60 (9): 142- 150 PAN Wei, WEI Chao, QIAN Chunyu, et al Improved YOLOv8s model for small object detection from perspective of drones[J]. Computer Engineering and Applications, 2024, 60 (9): 142- 150 doi: 10.3778/j.issn.1002-8331.2312-0043
12	邓天民, 程鑫鑫, 刘金凤, 等基于特征复用机制的航拍图像小目标检测算法[J]. 浙江大学学报: 工学版, 2024, 58 (3): 437- 448 DENG Tianming, CHENG Xinxin, LIU Jinfeng, et al Small target detection algorithm for aerial images based on feature reuse mechanism[J]. Journal of Zhejiang University: Engineering Science, 2024, 58 (3): 437- 448
13	LIU S, QI L, QIN H F. et al. Path aggregation network for instance segmentation [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8759-8768.
14	LIN T Y, DOLLAR P, CIRSHICK R, et al. Feature pyramid networks for object detection [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 936-944.
15	DING X H, ZHANG X Y, MA N N, et al. Repvgg: making VGG-style convnets great again [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13733-13742.
16	MISRA D, NALAMADA T, ARASANIPALAI A U, et al. Rotate to attend: convolutional triplet attention module [C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa: IEEE, 2021: 3138-3147.
17	TONG Z J, CHEN Y H, XU Z W, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism [EB/OL]. (2023-04-08) [2024-07-13]. https://arxiv.org/pdf/2301.10051.
18	DU D, ZHU P F, WEN L Y, et al. VisDrone-DET2019: the vision meets drone object detection in image challenge results [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Seoul: IEEE, 2019: 213-226.
19	YU W P, YANG T, CHEN C. Towards resolving the challenge of long-tail distribution in UAV images for object detection [C]// Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Waikoloa: IEEE, 2021: 3258-3267.
20	ZHAO H P, ZHOU Y, ZHANG L, et al Mixed YOLOv3-LITE: a lightweight real-time object detection method[J]. Sensors, 2020, 20 (7): 1861 doi: 10.3390/s20071861
21	杨永刚, 谢睿夫, 龚泽川改进YOLOv7-tiny的无人机目标检测算法[J]. 计算机工程与应用, 2024, 60 (6): 121- 129 YANG Yonggang, XIE Ruifu, GONG Zechuan Improved YOLOv7-tiny UAV target detection algorithm[J]. Computer Engineering and Applications, 2024, 60 (6): 121- 129 doi: 10.3778/j.issn.1002-8331.2307-0316
22	冯迎宾, 郭枭尊, 晏佳华. 基于多尺度注意力机制的无人机小目标检测算法[EB/OL]. (2024-08-02)[2024-08-11]. http://www.co-journal.com/CN/10.12382/bgxb.2023.1124. FENG Yingbin, GUO Xiaozun, YAN Jiahua. UVA small target detection algorithm based on multi-scale attention mechanism [EB/OL]. (2024-08-02)[2024-08-11]. http://www.co-journal.com/ CN/10.12382/bgxb.2023.1124.
23	TAHIR N U A, LONG Z, ZHANG Z, et al PVswin-YOLOv8s: UAV-based pedestrian and vehicle detection for traffic management in smart cities using improved YOLOv8[J]. Drones, 2024, 8 (3): 84 doi: 10.3390/drones8030084

[1]	张学军,梁书滨,白万荣,张奉鹤,黄海燕,郭梅凤,陈卓. 基于异构图表征的源代码漏洞检测方法[J]. 浙江大学学报(工学版), 2025, 59(8): 1644-1652.
[2]	林宜山,左景,卢树华. 基于多头自注意力机制与MLP-Interactor的多模态情感分析[J]. 浙江大学学报(工学版), 2025, 59(8): 1653-1661.
[3]	杨荣泰,邵玉斌,杜庆治. 基于结构感知的少样本知识补全[J]. 浙江大学学报(工学版), 2025, 59(7): 1394-1402.
[4]	杨宇豪,郭永存,李德永,王爽. 基于视觉信息的煤矸识别分割定位方法[J]. 浙江大学学报(工学版), 2025, 59(7): 1421-1433.
[5]	王圣举,张赞. 基于加速扩散模型的缺失值插补算法[J]. 浙江大学学报(工学版), 2025, 59(7): 1471-1480.
[6]	蔡永青,韩成,权巍,陈兀迪. 基于注意力机制的视觉诱导晕动症评估模型[J]. 浙江大学学报(工学版), 2025, 59(6): 1110-1118.
[7]	鞠文博,董华军. 基于上下文信息融合与动态采样的主板缺陷检测方法[J]. 浙江大学学报(工学版), 2025, 59(6): 1159-1168.
[8]	周翔宇,刘毅志,赵肄江,廖祝华,张德城. 面向目的地预测的层次化空间嵌入BiGRU模型[J]. 浙江大学学报(工学版), 2025, 59(6): 1211-1218.
[9]	李宗民,徐畅,白云,鲜世洋,戎光彩. 面向点云理解的双邻域图卷积方法[J]. 浙江大学学报(工学版), 2025, 59(5): 879-889.
[10]	刘洪伟,王磊,刘阳,张鹏超,乔石. 基于重组二次分解及LSTNet-Atten的短期负荷预测[J]. 浙江大学学报(工学版), 2025, 59(5): 1051-1062.
[11]	刘登峰,郭文静,陈世海. 基于内容引导注意力的车道线检测网络[J]. 浙江大学学报(工学版), 2025, 59(3): 451-459.
[12]	姚明辉,王悦燕,吴启亮,牛燕,王聪. 基于小样本人体运动行为识别的孪生网络算法[J]. 浙江大学学报(工学版), 2025, 59(3): 504-511.
[13]	梁礼明,龙鹏威,金家新,李仁杰,曾璐. 基于改进YOLOv8s的钢材表面缺陷检测算法[J]. 浙江大学学报(工学版), 2025, 59(3): 512-522.
[14]	王浚银,文斌,沈艳军,张俊,王子豪. 基于改进YOLOv7-tiny的铝型材表面缺陷检测方法[J]. 浙江大学学报(工学版), 2025, 59(3): 523-534.
[15]	尹向雷,屈少鹏,解永芳,苏妮. 基于渐进特征融合及多尺度空洞注意力的遮挡鸟巢检测[J]. 浙江大学学报(工学版), 2025, 59(3): 535-545.

Viewed

Full text

Abstract

Cited

Shared

Discussed