基于改进YOLOv8n的航拍轻量化小目标检测算法: PECS-YOLO

doi:10.19678/j.issn.1000-3428.0069353

摘要/Abstract

摘要：

在无人机(UAV)航拍中, 目标通常是密集分布、特征不明显的小目标, 且物体尺度变化较大。因此, 目标检测容易出现漏检和误检的问题。为了解决这些问题, 提出了一种基于改进YOLOv8n的航拍轻量化小目标检测算法: PECS-YOLO。该算法通过在Neck部分增加P2小目标检测层, 将浅层和深层的特征图进行拼接, 以更好地捕捉小目标的细节信息; 将轻量化卷积PartialConv引入全新的结构CSPPC(Cross Stage Partial PartialConv), 替换Neck网络中的C2f(Concatenation with Fusion), 实现模型轻量化; 引入SPPELAN(Spatial Pyramid Pooling with Efficient Layer Aggregation Network), 以有效地捕捉小目标特征; 通过在Neck部分每个检测头前加入压缩和激励(SE)注意力机制, 使网络更好地关注有用的通道, 减少复杂环境中背景噪声对小目标检测任务的干扰; 最后使用EfficiCIoU作为边界框损失函数, 将边界框的形状差异也考虑在内, 以增强模型对小目标的检测能力。实验结果表明: 相比YOLOv8n, PECS-YOLO目标检测算法在VisDrone2019-DET数据集上交并比为0.5的平均精度(mAP@0.5)提高了3.5%, 交并比为0.5∶0.95的平均精度(mAP@0.5∶0.95)提高了3.7%, 模型参数量减少了约25.7%, 检测速度提高了约65.2%。综上所述, PECS-YOLO模型适合于UAV航拍下的小目标检测任务。

关键词: 小目标检测, YOLOv8n, 无人机检测, SPPELAN, 轻量化

Abstract:

In Unmanned Aerial Vehicle (UAV) aerial photography, targets are usually small targets with dense distribution and unobvious features, and the object scale varies greatly. Therefore, the problems of missing detection and false detection are easy to occur in object detection. In order to solve these problems, a lightweight small object detection algorithm based on improved YOLOv8n, namely PECS-YOLO, is proposed for aerial photography. By adding P2 small object detection layer in the Neck part, the algorithm combines shallow and deep feature maps to better capture details of small targets. A lightweight convolution, namely PartialConv, is introduced to a new structure of Cross Stage Partial PartialConv (CSPPC), to replace Concatenation with Fusion (C2f) in the Neck network to realized lightweight of the model. By using a model of Spatial Pyramid Pooling with Efficient Layer Aggregation Network (SPPELAN), small object features can be captured effectively. By adding Squeeze-and-Excitation (SE)attention mechanism in front of each detection head in the Neck part, the network can better focus on useful channels and reduce the interference of background noise on small object detection tasks in complex environments. Finally, EfficiCIoU is used as the boundary frame loss function, and the shape difference of the boundary frame is also taken into account, which enhances the detection ability of the model for small targets. Experimental results show that, compared YOLOv8n, the mean Average Precision at Intersection over Union (IoU) of 0.5 (mAP@0.5) and the mean Average Precision at IoU of 0.5∶0.95 (mAP@0.5∶0.95) of PECS-YOLO object detection algorithm on VisDrone2019-DET dataset are increased by 3.5% and 3.7% respectively, the number of parameters is reduced by about 25.7%, and detection speed is increased by about 65.2%. In summary, PECS-YOLO model is suitable for small object detection in UAV aerial photography.

Key words: small object detection, YOLOv8n, Unmanned Aerial Vehicle (UAV) detection, SPPELAN, lightweight

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.

WANG Shumeng, XU Huiying, ZHU Xinzhong, HUANG Xiao, SONG Jie, LI Yi. Lightweight Small Object Detection Algorithm for Aerial Photography Based on Improved YOLOv8n: PECS-YOLO[J]. Computer Engineering, 2025, 51(9): 280-293.

https://www.ecice06.com/CN/Y2025/V51/I9/280

图/表 18

图1 YOLOv8n架构

Fig.1 Architecture of YOLOv8n

图2 PECS-YOLO架构

Fig.2 Architecture of PECS-YOLO

图3 卷积操作对比

Fig.3 Convolutional operation comparison

图4 C2f和CSPPC模块示意图

Fig.4 Diagrams of C2f and CSPPC modules

图5 SPPF和SPPELAN模块示意图

Fig.5 Diagrams of SPPF and SPPELAN modules

图6 SE模块

Fig.6 SE module

图7 无人机近地飞行时的雾图像成像过程

Fig.7 Fog image imaging process of UAV flying close to ground

图8 增强效果对比

Fig.8 Comparison of enhancement effects

图9 航拍城市道路检测效果可视化

Fig.9 Visualization of urban road detection effect in aerial photography

图10 各类场景下P2检测效果对比

Fig.10 Comparison of P2 detection effects in various scenarios

图11 各类场景下PECS-YOLO的检测效果对比

Fig.11 Comparison of PECS-YOLO detection effects in various scenarios

参考文献 35

1	DUAN K W, BAI S, XIE L X, et al. CenterNet: keypoint triplets for object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2019: 6569-6578.
2	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2017: 2980-2988.
3	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector. Berlin, Germany: Springer, 2016.
4	SINGHA S, AYDIN B. Automated drone detection using YOLOv4. Drones, 2021, 5(3): 95. doi: 10.3390/drones5030095
5	LI Y S, YUAN H W, WANG Y F, et al. GGT-YOLO: a novel object detection algorithm for drone-based maritime cruising. Drones, 2022, 6(11): 335. doi: 10.3390/drones6110335
6	GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2015: 1440-1448.
7	REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
8	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. 计算机工程与应用, 2024, 60(9): 142- 150.
	PAN W, WEI C, QIAN C Y, et al. Improved YOLOv8s model for small target detection from UAV perspective. Computer Engineering and Applications, 2024, 60(9): 142- 150.
9	程换新, 乔庆元, 骆晓玲, 等. 基于改进YOLOv8的无人机航拍图像目标检测算法. 无线电工程, 2024, 54(4): 871- 881.
	CHENG H X, QIAO Q Y, LUO X L, et al. Object detection algorithm for UAV aerial image based on improved YOLOv8. Radio Engineering, 2024, 54(4): 871- 881.
10	刘涛, 高一萌, 柴蕊, 等. 改进YOLOv5s的无人机视角下小目标检测算法. 计算机工程与应用, 2024, 60(1): 110- 121.
	LIU T, GAO Y M, CHAI R, et al. Improved small target detection algorithm based on YOLOv5s in UAV view. Computer Engineering and Applications, 2024, 60(1): 110- 121.
11	陈卫彪, 贾小军, 朱响斌, 等. 基于DSM-YOLOv5的无人机航拍图像目标检测. 计算机工程与应用, 2023, 59(18): 226- 233.
	CHEN W B, JIA X J, ZHU X B, et al. Target detection for UAV image based on DSM-YOLOv5. Computer Engineering and Applications, 2023, 59(18): 226- 233.
12	崔勇强, 黄谦, 高雪, 等. 城市低空小型无人机目标实时高精度检测算法. 计算机工程与应用, 2024, 60(16): 198- 205.
	CUI Y Q, HUANG Q, GAO X, et al. Real-time high-precision detection algorithm for small UAV targets in urban low-altitude areas. Computer Engineering and Applications, 2024, 60(16): 198- 205.
13	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 (CVPR). Washington D.C., USA: IEEE Press, 2021: 13733-13742.
14	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV). Berlin, Germany: Springer, 2018: 3-19.
15	HONG T, LIANG H M, YANG Q Y, et al. A real-time tracking algorithm for multi-target UAV based on deep learning. Remote Sensing, 2023, 15(1): 2.
16	WU X, LI W, HONG D F, et al. Deep learning for unmanned aerial vehicle-based object detection and tracking: a survey. IEEE Geoscience and Remote Sensing Magazine, 2022, 10(1): 91- 124. doi: 10.1109/MGRS.2021.3115137
17	ZHU P, WEN L, DU D, et al. Detection and tracking meet drones challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(11): 7380- 7399. doi: 10.1109/TPAMI.2021.3119563
18	GERALDES R, GONCALVES A, LAI T, et al. UAV-based situational awareness system using deep learning. IEEE Access, 2019, 7, 122583- 122594. doi: 10.1109/ACCESS.2019.2938249
19	TERVEN J, CORDOVA-ESPARZA D. A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS[EB/OL]. [2024-01-07]. https://arxiv.org/abs/2304.00501v7.
20	HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2018: 7132-7141.
21	CHEN J R, KAO S H, HE H, et al. Run, don't walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2023: 12021-12031.
22	LI X, WANG W H, WU L J, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Advances in Neural Information Processing Systems, 2020, 33, 21002- 21012.
23	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.
24	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: 12993-13000.
25	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: 213-226.
26	殷旭平. 复杂天气条件下的无人机图像目标检测方法研究[D]. 长沙: 国防科技大学, 2021.
	YIN X P. Research on target detection method of UAV image under complex weather conditions[D]. Changsha: National University of Defense Technology, 2021. (in Chinese)
27	LIU Y C, SHAO Z R, HOFFMANN N. Global attention mechanism: retain information to enhance channel-spatial interactions[EB/OL]. [2024-01-07]. https://arxiv.org/abs/2112.05561v1.
28	XIA Z F, PAN X R, SONG S J, et al. Vision transformer with deformable attention[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2022: 4794-4803.
29	OUYANG D L, HE S, ZHANG G Z, et al. Efficient multi-scale attention module with cross-spatial learning[C]//Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2023: 1-5.
30	REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2019: 658-666.
31	TONG Z J, CHEN Y H, XU Z W, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[EB/OL]. [2024-01-07]. https://arxiv.org/abs/2301.10051v3.
32	HE K M, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2017: 2961-2969.
33	CHEN H, WANG Y, GUO J, et al. Vanillanet: the power of minimalism in deep learning[EB/OL]. [2024-01-07]. https://arxiv.org/abs/2305.12972.
34	ZHAO Y A, LV W Y, XU S L, et al. DETRs beat YOLOs on real-time object detection[EB/OL]. [2024-01-07]. https://arxiv.org/abs/2304.08069v3.
35	SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2017: 618-626.

[1]	马淦, 谷雨, 彭冬亮. 结合改进YOLOv5s和动态数据增强的海面舰船检测[J]. 计算机工程, 2025, 51(9): 294-305.
[2]	倪源松, 韩军, 邹小燕, 胡广怡, 王文帅. 两阶段自适应分块输电线路螺栓缺陷检测方法[J]. 计算机工程, 2025, 51(8): 281-291.
[3]	宋杰, 徐慧英, 朱信忠, 黄晓, 陈晨, 王泽宇. 基于YOLOv8改进的跌倒检测算法: OEF-YOLO[J]. 计算机工程, 2025, 51(7): 127-139.
[4]	栾孟娜, 郑秋梅, 王风华. 基于DMC-YOLO的交通标志实时检测算法[J]. 计算机工程, 2025, 51(7): 90-99.
[5]	奚琦, 王明杰, 魏敬和, 赵伟. 基于改进YOLOv3的航拍小目标检测算法[J]. 计算机工程, 2025, 51(6): 184-192.
[6]	周思瑜, 徐慧英, 朱信忠, 黄晓, 盛轲, 曹雨淇, 陈晨. 基于改进YOLOv8n的手机屏幕瑕疵检测算法: PGS-YOLO[J]. 计算机工程, 2025, 51(5): 326-339.
[7]	许华杰, 郑力文, 张品, 秦远卓. 基于多维注意力模块的轻量化混凝土裂缝检测方法[J]. 计算机工程, 2025, 51(5): 351-360.
[8]	黄昆, 齐肇建, 王娟敏, 胡倩, 胡伟超, 皮建勇. 基于改进YOLOv8的密集行人检测模型[J]. 计算机工程, 2025, 51(5): 133-142.
[9]	陈梓延, 王晓龙, 何迪, 安国成. 基于改进YOLOv8的轻量化车辆检测网络[J]. 计算机工程, 2025, 51(5): 314-325.
[10]	王泽宇, 徐慧英, 朱信忠, 黄晓, 梁佳杰, 李琛. 基于改进YOLOv8的轻量化鱼苗检测算法: FD-YOLO[J]. 计算机工程, 2025, 51(4): 327-338.
[11]	袁亚剑, 毛力. 一种增强前景的轻量级交通标志检测模型[J]. 计算机工程, 2025, 51(3): 54-63.
[12]	刘圣杰, 何宁, 王鑫, 于海港, 韩文静. 基于轻量级高分辨率网络的人体姿态估计算法[J]. 计算机工程, 2025, 51(2): 278-288.
[13]	张元, 吕德芳, 孟建军, 祁文哲. 基于双注意力和GSSN轻量化的钢轨扣件缺陷检测[J]. 计算机工程, 2025, 51(2): 289-299.
[14]	孙浩淼, 李宗民, 肖倩, 孙文洁, 张雯欣. AI-Curling: 一种冰壶现场分析与决策方法[J]. 计算机工程, 2025, 51(2): 102-110.
[15]	张倡倡, 吕卫东, 蔡子杰, 刘炎奎. 基于域泛化的轻量化图像分类算法[J]. 计算机工程, 2025, 51(1): 182-189.

选择文件类型/文献管理软件名称

选择包含的内容