基于改进YOLOv8的轻量化无人机图像目标检测算法

doi:10.19678/j.issn.1000-3428.0070085

计算机工程 ›› 2026, Vol. 52 ›› Issue (3): 97-106. doi: 10.19678/j.issn.1000-3428.0070085

• 计算机视觉与图形图像处理 • 上一篇下一篇

基于改进YOLOv8的轻量化无人机图像目标检测算法

唐克*(), 魏飞鸣, 李东瀛, 郁文贤

上海交通大学电子信息与电气工程学院北斗导航与位置服务上海市重点实验室, 上海 200240

收稿日期:2024-07-09 修回日期:2024-08-28 出版日期:2026-03-15 发布日期:2024-12-03
通讯作者: 唐克
作者简介:
唐克, 男, 硕士, 主研方向为人工智能、深度学习、自动目标识别
魏飞鸣, 研究员
李东瀛, 副教授
郁文贤, 教授
基金资助:
上海航天先进技术联合研究基金(USCAST2022-32)

Lightweight Target Detection Algorithm for UAV Images Based on Improved YOLOv8

TANG Ke*(), WEI Feiming, LI Dongying, YU Wenxian

Shanghai Key Laboratory of Beidou Navigation and Location Services, School of Electronic Information and Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Received:2024-07-09 Revised:2024-08-28 Online:2026-03-15 Published:2024-12-03
Contact: TANG Ke

摘要/Abstract

摘要：

针对无人机图像中小目标实例多、目标间存在遮挡所导致的漏检和误检等现象, 提出一种基于改进YOLOv8的轻量化无人机图像小目标检测算法。首先, 在颈部引入三特征编码器(TFE)、尺度序列特征融合(SSFF)模块, 增强了网络对不同尺度特征的提取能力。接着, 设计小目标检测层(SMOH), 并将其与改进的颈部特征提取网络进行融合, 在头部引入一个额外的检测头, 减小小目标特征的损失, 增强网络对小目标的识别能力。然后, 针对完整交并比(CIoU)的缺陷, 结合适应交并比(Wise-IoU)、内部交并比(Inner-IoU)和最小点距离交并比(MPDIoU), 提出了一种回归损失函数Wise-Inner-MPDIoU。最后, 为了实现算法在移动端和嵌入式场景下的轻量化应用需求, 进行了基于幅度的层自适应稀疏化剪枝, 在保证模型精度的同时进一步压缩了模型大小。实验结果表明, 相比于原YOLOv8s算法模型, 改进后的模型在mAP@0.5提高6.8百分点的同时参数量、计算量、模型大小分别降低76.4%、17.1%、73.5%, 在检测精度与轻量化方面均取得了显著提升, 具有很强的实用价值。

关键词: YOLOv8算法, 无人机, 小目标检测, 特征融合, 模型剪枝

Abstract:

In view of missed and false detection phenomena caused by numerous small target instances and occlusions among targets in drone images, this paper proposes a lightweight small target detection algorithm for Unmanned Aerial Vehicle (UAV) images based on an improved YOLOv8. The Triple Feature Encoder (TFE) and Scale Sequence Feature Fusion (SSFF) modules are introduced in the neck to enhance the ability of the network to extract features at different scales. Furthermore, a Small Object Detection Head (SMOH) is designed and fused with the improved neck feature extraction network, and an additional detection head is also introduced to reduce the loss of small target features and enhance the recognition ability of the network for small targets. Additionally, considering the defects of Complete Intersection over Union (CIoU), a regression loss function, Wise-Inner-MPDIoU, is proposed by combining Wise-IoU, Inner-IoU, and Minimum Point Distance based IoU (MPDIoU). Finally, to realize the lightweight application requirements of the algorithm in mobile and embedded systems, amplitude-based layer-adaptive sparse pruning is performed to further reduce the model size while ensuring model accuracy. Experimental results demonstrate that, compared to the original YOLOv8s model, the improved model proposed in this paper improves mAP@0.5 by 6.8 percentage points, while reducing the number of parameters, amount of computation, and model size by 76.4%, 17.1%, and 73.5%, respectively. The proposed model is lightweight, improves detection accuracy, and has strong practical significance.

Key words: YOLOv8 algorithm, Unmanned Aerial Vehicle (UAV), small target detection, feature fusion, model pruning

唐克, 魏飞鸣, 李东瀛, 郁文贤. 基于改进YOLOv8的轻量化无人机图像目标检测算法[J]. 计算机工程, 2026, 52(3): 97-106.

TANG Ke, WEI Feiming, LI Dongying, YU Wenxian. Lightweight Target Detection Algorithm for UAV Images Based on Improved YOLOv8[J]. Computer Engineering, 2026, 52(3): 97-106.

https://www.ecice06.com/CN/Y2026/V52/I3/97

图/表 13

图1 YOLOv8算法网络结构

Fig.1 Network structure of YOLOv8 algorithm

图2 改进的YOLOv8算法网络结构

Fig.2 Network structure of improved YOLOv8 algorithm

图3 TFE模块结构

Fig.3 Structure of TFE module

图4 SSFF模块结构

Fig.4 Structure of SSFF module

图5 LAMP剪枝流程

Fig.5 Procedure of LAMP pruning

图6 剪枝前后通道对比

Fig.6 Comparison of channels before and after pruning

图7 检测效果对比

Fig.7 Comparison of detection effect

参考文献 29

1	SAEED Z , YOUSAF M H , AHMED R , et al. On-board small-scale object detection for Unmanned Aerial Vehicles (UAVs). Drones, 2023, 7 (5): 310. doi: 10.3390/drones7050310
2	BISIO I , HALEEM H , GARIBOTTO C , et al. Performance evaluation and analysis of drone-based vehicle detection techniques from deep learning perspective. IEEE Internet of Things Journal, 2022, 9 (13): 10920- 10935. doi: 10.1109/JIOT.2021.3128065
3	HOSHINO W, SEO J, YAMAZAKI Y. A study for detecting disaster victims using multi-copter drone with a thermographic camera and image object recognition by SSD[C]//Proceedings of the IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM). Washington D.C., USA: IEEE Press, 2021: 162-167.
4	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 (CVPR). Washington D.C., USA: IEEE Press, 2016: 779-788.
5	JIANG P Y , ERGU D J , LIU F Y , et al. A review of YOLO algorithm developments. Procedia Computer Science, 2022, 199, 1066- 1073. doi: 10.1016/j.procs.2022.01.135
6	PIRASTEH S , RASHIDI P , RASTIVEIS H , et al. Developing an algorithm for buildings extraction and determining changes from airborne LiDAR, and comparing with R-CNN method from drone images. Remote Sensing, 2019, 11 (11): 1272. doi: 10.3390/rs11111272
7	SEO D M , WOO H J , KIM M S , et al. Identification of asbestos slates in buildings based on Faster Region-based Convolutional Neural Network (Faster R-CNN) and drone-based aerial imagery. Drones, 2022, 6 (8): 194. doi: 10.3390/drones6080194
8	LIU W J , QIANG J , LI X X , et al. UAV image small object detection based on composite backbone network. Mobile Information Systems, 2022 (1): 7319529.
9	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. Sensors, 2023, 23 (16): 7190. doi: 10.3390/s23167190
10	GUO J M , LOU H T , CHEN H N , et al. A new detection algorithm for alien intrusion on highway. Scientific Reports, 2023, 13 (1): 10667. doi: 10.1038/s41598-023-37686-w
11	ZHAO T, LIU J Y, DUAN Z Q. UAV target detection based on RetinaNet[C]//Proceedings of the Chinese Control and Decision Conference (CCDC). Washington D.C., USA: IEEE Press, 2019: 3342-3346.
12	王殿伟, 胡里晨, 房杰, 等. 基于改进Double-Head RCNN的无人机航拍图像小目标检测算法. 北京航空航天大学学报, 2024, 50 (7): 2141- 2149.
	WANG D W , HU L C , FANG J , et al. Small target detection algorithm based on improved Double-Head RCNN for UAV aerial images. Journal of Beijing University of Aeronautics and Astronautics, 2024, 50 (7): 2141- 2149.
13	WANG F , WANG H Y , QIN Z Y , et al. UAV target detection algorithm based on improved YOLOv8. IEEE Access, 2023, 11, 116534- 116544. doi: 10.1109/ACCESS.2023.3325677
14	王舒梦, 徐慧英, 朱信忠, 等. 基于改进YOLOv8n的航拍轻量化小目标检测算法: PECS-YOLO. 计算机工程, 2025, 51 (9): 280- 293. doi: 10.19678/j.issn.1000-3428.0069353
	WANG S M , XU H Y , ZHU X Z , et al. Lightweight small object detection algorithm for aerial photography based on improved YOLOv8n: PECS-YOLO. Computer Engineering, 2025, 51 (9): 280- 293. doi: 10.19678/j.issn.1000-3428.0069353
15	张佳承, 韦锦, 陈义时. 改进YOLOv8的实时轻量化鲁棒绿篱检测算法. 计算机工程, 2025, 51 (7): 362- 374. doi: 10.19678/j.issn.1000-3428.0069524
	ZHANG J C , WEI J , CHEN Y S . Improved YOLOv8 real-time lightweight robust hedge detection algorithm. Computer Engineering, 2025, 51 (7): 362- 374. doi: 10.19678/j.issn.1000-3428.0069524
16	GALE T, ELSEN E, HOOKER S. The state of sparsity in deep neural networks[EB/OL]. [2024-06-04]. https://arxiv.org/abs/1902.09574.
17	EVCI U, GALE T, MENICK J, et al. Rigging the lottery: making all tickets winners[C]//Proceedings of International Conference on Machine Learning. [S. l. ]: PMLR, 2020: 2943-2952.
18	KANG M , TING C M , TING F F , et al. ASF-YOLO: a novel YOLO model with attentional scale sequence fusion for cell instance segmentation. Image and Vision Computing, 2024, 147, 105057. doi: 10.1016/j.imavis.2024.105057
19	WANG C Y, BOCHKOVSKIY A, LIAO H 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 (CVPR). Washington D.C., USA: IEEE Press, 2023: 7464-7475.
20	LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2018: 8759-8768.
21	LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for bjectdetection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2017: 936-944.
22	ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2020, 34(7): 12993-13000.
23	TONG Z, CHEN Y, XU Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[EB/OL]. [2024-06-04]. https://arxiv.org/abs/2301.10051.
24	ZHANG H, XU C, ZHANG S. Inner-IoU: more effective intersection over union loss with auxiliary bounding box[EB/OL]. [2024-06-04]. https://arxiv.org/abs/2311.02877.
25	ZHANG H, XU C, ZHANG S J. MPDIoU: a loss for efficient and accurate bounding box regression[EB/OL]. [2024-06-04]. https://arxiv.org/abs/2311.02877.
26	LEE J, PARK S, MO S, et al. Layer-adaptive sparsity for the magnitude-based pruning[EB/OL]. [2024-06-04]. https://arxiv.org/abs/2010.07611.
27	HOWARD A G, ZHU M, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[EB/OL]. [2024-06-04]. https://arxiv.org/abs/1704.04861.
28	CAO Y R, HE Z J, WANG L J, et al. VisDrone-DET2021: the vision meets drone object detection challenge results[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Washington D.C., USA: IEEE Press, 2021: 1-9.
29	张智, 易华挥, 郑锦. 聚焦小目标的航拍图像目标检测算法. 电子学报, 2023, 51 (4): 944- 955.
	ZHANG Z , YI H H , ZHENG J . Focusing on small objects detector in aerial images. Acta Electronica Sinica, 2023, 51 (4): 944- 955.

[1]	吴雪松, 陈媛媛, 周涛. 基于多尺度金字塔池化的自适应无参考图像质量评价[J]. 计算机工程, 2026, 52(3): 107-118.
[2]	孔思维, 叶永金, 吴永政, 汪士, 侯杰, 倪明. 无人机群航迹规划问题的量子退火算法求解[J]. 计算机工程, 2026, 52(3): 308-317.
[3]	曹继卫, 罗飞, 丁炜超. BS-YOLO: 基于BSAM注意力机制和SCConv的小目标检测算法[J]. 计算机工程, 2026, 52(3): 119-127.
[4]	陈国莲, 冯梓洋, 曹均阔. 基于多模态空间特征融合的网络欺凌检测研究[J]. 计算机工程, 2026, 52(3): 255-263.
[5]	张志, 尹昱凯, 孙奕灵, 孟雯锦, 彭畅. 基于多模态特征融合的Android恶意软件检测模型研究[J]. 计算机工程, 2026, 52(3): 243-254.
[6]	刘畅, 梁冰雪, 田荣坤, 秦玉华. 基于多特征融合和混合神经网络的医疗健康问题分类[J]. 计算机工程, 2026, 52(2): 342-355.
[7]	张信佳, 王芳. 基于多层次特征融合和注意力机制的无人机图像小目标检测算法[J]. 计算机工程, 2026, 52(2): 148-157.
[8]	王庆荣, 郝福乐, 朱昌锋, 王俊杰. 基于多特征融合的车辆轨迹预测研究[J]. 计算机工程, 2026, 52(2): 331-341.
[9]	杨钰雪, 何甜, 樊京杭, 刘瑞英, 李腾. 基于交叉注意力与特征聚合的跨模态图文检索研究[J]. 计算机工程, 2026, 52(2): 311-321.
[10]	方仪豪, 邹丹平. 多旋翼无人机仿真平台综述[J]. 计算机工程, 2026, 52(2): 13-23.
[11]	李秉烨, 鲍宇, 曹伟, 李明泽, 徐方正. 基于可变序列的跨层通道剪枝方法[J]. 计算机工程, 2026, 52(1): 381-389.
[12]	刘杰, 黄晓辉, 郭敬博. 基于YOLOv8的轻量级田间棉花品级检测[J]. 计算机工程, 2026, 52(1): 400-413.
[13]	黎东丰, 陈雨人, 余博. 基于多层次特征融合的路面裂缝检测方法[J]. 计算机工程, 2026, 52(1): 154-165.
[14]	王舒梦, 徐慧英, 朱信忠, 黄晓, 宋杰, 李毅. 基于改进YOLOv8n的航拍轻量化小目标检测算法: PECS-YOLO[J]. 计算机工程, 2025, 51(9): 280-293.
[15]	马跃, 黄周睿, 周雯, 许艺瀚. 基于感受野注意力的轻量化林火检测算法[J]. 计算机工程, 2025, 51(9): 350-361.

选择文件类型/文献管理软件名称

选择包含的内容

基于改进YOLOv8的轻量化无人机图像目标检测算法

Lightweight Target Detection Algorithm for UAV Images Based on Improved YOLOv8

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 29

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于改进YOLOv8的轻量化无人机图像目标检测算法

Lightweight Target Detection Algorithm for UAV Images Based on Improved YOLOv8

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 29

相关文章 15

编辑推荐

Metrics

本文评价