Semi-Supervised Vehicle Detection Algorithm Based on Improved YOLOv5

doi:10.19678/j.issn.1000-3428.0069208

Abstract

Abstract:

Vehicle detection in traffic scenarios faces notable challenges, including substantial variations in target scale and severe occlusions. Additionally, fully annotating large-scale datasets involves significant costs. To address these challenges, a semi-supervised vehicle detection algorithm based on improved YOLOv5 is proposed. Firstly, the SimOTA sample matching method is integrated to refine suboptimal matches, reducing detection difficulties caused by variations in target scale and shape. A novel spatial pyramid pooling network, Spatial Pyramid Pooling Fast Attention (SPPFA), is also introduced, incorporating the Large Separable Kernel Attention (LSKA) mechanism to expand the receptive field and achieve spatial and channel adaptability. This approach effectively mitigates the impact of large-scale targets and occlusion issues. Moreover, substituting the CIoU with the SIoU enhances the regression loss function. An improved semi-supervised deep learning algorithm is also designed, optimizing the loss function to better leverage valuable information from unlabeled data and significantly improving vehicle detection accuracy. Experimental results demonstrate that the proposed algorithm achieves a mAP@0.5 of 58.2% on a custom vehicle dataset, representing an 11.1 percentage points improvement over the YOLOv5n baseline model. Additionally, the model size is significantly smaller than that of mainstream object detection algorithms, highlighting its potential for engineering applications.

Key words: YOLOv5, vehicle detection, sample matching, spatial pyramid pooling, semi-supervised learning

摘要：

目前, 交通场景中的车辆检测存在目标尺度差异显著以及遮挡重叠严重等问题, 且对大规模数据进行完全标注需要较高的成本。针对以上情况, 提出一种基于改进YOLOv5的半监督车辆检测算法。引入SimOTA样本匹配方法, 优化次优匹配现象, 改善目标尺度形状变化导致的检测困难; 提出一种新的空间金字塔池化网络SPPFA, 通过引入LSKA, 在增大感受野的同时实现空间和通道的自适应性, 缓解大尺度目标和遮挡问题产生的影响; 将CIoU替换为SIoU, 优化回归损失函数。在此基础上, 提出一种改进的半监督深度学习算法, 通过优化损失函数设计, 增强算法学习未标注样本中有益信息的能力, 有效提高模型对车辆的检测精度。实验结果表明, 改进后的算法在自制车辆数据集上mAP@0.5指标达到了58.2%, 相较YOLOv5n基线模型提升了11.1百分点, 且模型体积远小于主流目标检测算法, 具有良好的工程应用前景。

关键词: YOLOv5, 车辆检测, 样本匹配, 空间金字塔池化, 半监督学习

GAO Rui, AN Guocheng, ZOU Danping, PEI Ling. Semi-Supervised Vehicle Detection Algorithm Based on Improved YOLOv5[J]. Computer Engineering, 2025, 51(3): 300-309.

高睿, 安国成, 邹丹平, 裴凌. 基于改进YOLOv5的半监督车辆检测算法[J]. 计算机工程, 2025, 51(3): 300-309.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0069208

https://www.ecice06.com/EN/Y2025/V51/I3/300

Figures/Tables 15

Fig.1 Network structure of improved YOLOv5n algorithm

Fig.2 Feature pyramid pooling structure

Fig.3 Position relationship between prediction box and truth box

Fig.4 Semi-supervised training framework

Fig.5 Dataset distribution

Fig.6 The change of mAP@0.5 metric during the semi-supervised training process

Fig.7 The mAP@0.5 metric under different proportions of labeled samples

Fig.8 Visual comparison of detection effects before and after algorithm improvement

References 25

1	李松江, 吴宁, 王鹏, 等. 基于改进Cascade RCNN的车辆目标检测方法. 计算机工程与应用, 2021, 57 (5): 123- 130.
	LI S J , WU N , WANG P , et al. Vehicle target detection method based on improved Cascade RCNN. Computer Engineering and Applications, 2021, 57 (5): 123- 130.
2	CAI Z , VASCONCELOS N . Cascade R-CNN: high quality object detection and instance segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43 (5): 1483- 1498. doi: 10.1109/TPAMI.2019.2956516
3	周康, 朱宗晓, 徐征宇, 等. 改进Faster R-CNN的道路目标检测. 计算机与数字工程, 2022, 50 (4): 750- 756.
	ZHOU K , ZHU Z X , XU Z Y , et al. Road target detection based on improved Faster R-CNN. Computer & Digital Engineering, 2022, 50 (4): 750- 756.
4	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
5	李国进, 胡洁, 艾矫燕. 基于改进SSD算法的车辆检测. 计算机工程, 2022, 48 (1): 266- 274. URL
	LI G J , HU J , AI J Y . Vehicle detection based on improved SSD algorithm. Computer Engineering, 2022, 48 (1): 266- 274. URL
6	SZEGEDY C , IOFFE S , VANHOUCKE V , et al. Inception-v4, Inception-ResNet and the impact of residual connections on learning. Proceedings of the AAAI Conference on Artificial Intelligence, 2017, 31 (1): 4278- 4284.
7	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[EB/OL]. [2023-09-05]. https://arxiv.org/abs/1512.02325.
8	郭克友, 王苏东, 李雪, 等. 基于Dim env-YOLO算法的昏暗场景车辆多目标检测. 计算机工程, 2023, 49 (3): 312- 320. URL
	GUO K Y , WANG S D , LI X , et al. Multi-target detection of vehicles in dim scenes based on Dim env-YOLO algorithm. Computer Engineering, 2023, 49 (3): 312- 320. URL
9	BOCHKOVSKIY A, WANG C Y, LIAO H M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. [2023-09-05]. https://arxiv.org/abs/2004.10934v1.
10	SOHN K, ZHANG Z Z, LI C L, et al. A simple semi-supervised learning framework for object detection[EB/OL]. [2023-09-05]. https://arxiv.org/abs/2005.04757v2.
11	LI G, LI X, WANG Y J, et al. PseCo: pseudo labeling and consistency training for semi-supervised object detection[EB/OL]. [2023-09-05]. https://arxiv.org/abs/2203.16317.
12	ZHANG J C, LIN X R, ZHANG W, et al. Semi-DETR: semi-supervised object detection with detection transformers[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2023: 23809-23818.
13	KAR P, CHUDASAMA V, ONOE N, et al. Revisiting class imbalance for end-to-end semi-supervised object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2023: 4569-4578.
14	ZHOU H Y , JIANG F , LU H T . SSDA-YOLO: semi-supervised domain adaptive YOLO for cross-domain object detection. Computer Vision and Image Understanding, 2023, 229, 103649. doi: 10.1016/j.cviu.2023.103649
15	LUO G, ZHOU Y Y, JIN L, et al. Towards end-to-end semi-supervised learning for one-stage object detection[EB/OL]. [2023-09-05]. https://arxiv.org/abs/2302.11299v1.
16	XU B W, CHEN M T, GUAN W L, et al. Efficient Teacher: semi-supervised object detection for YOLOv5[EB/OL]. [2023-09-05]. https://arxiv.org/abs/2302.07577v3.
17	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2023-09-05]. https://arxiv.org/abs/1804.02767v1.
18	GE Z, LIU S T, LI Z M, et al. OTA: optimal transport assignment for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2021: 303-312.
19	LAU K W , PO L M , REHMAN Y A U . Large separable kernel attention: rethinking the large kernel attention design in CNN. Expert Systems with Applications, 2024, 236, 121352. doi: 10.1016/j.eswa.2023.121352
20	GUO M H , LU C Z , LIU Z N , et al. Visual attention network. Computational Visual Media, 2023, 9 (4): 733- 752. doi: 10.1007/s41095-023-0364-2
21	ZHENG Z H , WANG P , LIU W , et al. Distance-IoU loss: faster and better learning for bounding box regression. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34 (7): 12993- 13000. doi: 10.1609/aaai.v34i07.6999
22	GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[EB/OL]. [2023-09-05]. https://arxiv.org/abs/2205.12740v1.
23	TIAN Z , SHEN C , CHEN H , et al. FCOS: a simple and strong anchor-free object detector. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44 (4): 1922- 1933.
24	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. Washington D.C., USA: IEEE Press, 2017: 2980-2988.
25	GE Z, LIU S T, WANG F, et al. YOLOX: exceeding YOLO series in 2021[EB/OL]. [2023-09-05]. https://arxiv.org/abs/2107.08430v2.

[1]	CUI Jinrong, YE Weihao, ZHENG Hong, LIU Tonglai, QI Long, XU Yong. Rice Seedling Counting in Complex Environments Based on Domain-Adaptive NWD-YOLOv5 [J]. Computer Engineering, 2025, 51(3): 320-333.
[2]	ZHANG Yuan, LÜ Defang, MENG Jianjun, QI Wenzhe. Defect Detection of Rail Fasteners Based on Double Attention and GSSN Lightweight [J]. Computer Engineering, 2025, 51(2): 289-299.
[3]	AN Guocheng, WANG Xiaolong, JIANG Bo, XING Jian. Prohibited Parking Detection Algorithm for Highway Service Area in Complex Environment [J]. Computer Engineering, 2025, 51(2): 356-364.
[4]	ZHANG Xinbo, ZHANG Xueying, HUANG Lixia, CHEN Guijun. Classification Algorithm and Application Based on Semi-Supervised Deep Auto-Encoder Network [J]. Computer Engineering, 2025, 51(1): 71-80.
[5]	GUO Min, ZHANG Xihan, LI Yang. Integrated Attentional Teacher Mutual Consistency Semi-Supervised Medical Image Segmentation [J]. Computer Engineering, 2024, 50(9): 313-323.
[6]	Rixin RAO, Yiwen WANG, Lizhi ZENG, Xintian TONG, Haitao ZHAO. Lightweight Network Model for Waste Cable Detection [J]. Computer Engineering, 2024, 50(8): 22-30.
[7]	Zhiwei LIN, Zuyuan YANG, Siqiu WANG, Chao YANG. Athlete Detection Algorithm Based on Multi-scale Linear Global Attention [J]. Computer Engineering, 2024, 50(7): 352-359.
[8]	Naiwei TU, Meng JIAO, Xin YAN. Bird's Nest Target Image Detection Model for Transmission Lines in Complex Environments [J]. Computer Engineering, 2024, 50(7): 216-226.
[9]	GU Yonggen, GAO Lingxuan, WU Xiaohong, TAO Jie. Research on Data Sharing of Federated Semi-Supervised Learning with Non-IID [J]. Computer Engineering, 2024, 50(6): 188-196.
[10]	LIU Shibing, ZHOU Shihan. Research on Insulator Detection Algorithm for High-Speed Rail Contact Network [J]. Computer Engineering, 2024, 50(5): 200-208.
[11]	CHEN Wei, WANG Xiaolong, ZHANG Yanwei, AN Guocheng, JIANG Bo. Vehicle Violation Detection Based on Improved YOLOv8 in Highway Service Areas [J]. Computer Engineering, 2024, 50(4): 11-19.
[12]	Wei CHEN, Xiaolong WANG, Yanwei ZHANG, Guocheng AN, Bo JIANG. Vehicle Violation Detection Based on Improved YOLOv8 in Highway Service Areas [J]. Computer Engineering, 2024, 50(4): 11-19.
[13]	Jintao ZHOU, Diju GAO, Zhiquan LIU. Detection Method of Water-Surface Obstacles for Unmanned Ships Based on Panoramic Vision [J]. Computer Engineering, 2024, 50(2): 113-121.
[14]	WANG Lin, ZHAO Li, WANG Wuwei. Air-to-Air Target Detection of Unmanned Aerial Vehicles Under High Dynamic Scenarios [J]. Computer Engineering, 2024, 50(12): 265-275.
[15]	WANG Hanwen, GE Qing, ZHU Ningke, YU Pengfei. Chinese Traffic Sign Detection Algorithm in Natural Scenes [J]. Computer Engineering, 2024, 50(11): 327-337.

Please choose a citation manager

Content to export