改进YOLOv8的城市车辆目标检测算法

doi:10.19678/j.issn.1000-3428.0069125

摘要/Abstract

摘要：

为了解决城市车辆目标检测算法中存在检测效果差、误检漏检率高、泛化能力弱的问题, 提出一种改进YOLOv8的城市车辆目标检测算法。首先, 在主干网络尾部融入高效多尺度注意力(EMA)机制, 有助于模型更好地捕捉目标车辆的细节特征, 结合160×160像素尺寸的小目标检测层来加强对小目标的检测能力, 通过维度交互进一步聚合像素级特征, 增强对目标车辆的挖掘能力。其次, 为轻量化网络设计了一种多尺度轻量化卷积(MLConv)模块, 并基于MLConv重构了C2f模块, 提高模型的特征提取能力。最后, 为抑制低质量图像产生的有害梯度, 采用WIoU损失函数替代完全交并比(CIoU)损失函数, 优化网络的边界框损失, 提升模型的收敛速度和回归精度。在Streets车辆数据集上进行验证, 结果表明, 改进算法的mAP@0.5、mAP@0.5∶0.95和召回率相较于基准模型YOLOv8n分别提升了1.9、1.4和2.4百分点。在国内车辆数据集和VisDrone2019小目标数据集上进行验证, 改进算法的各项性能指标都有不同程度的提升, 充分证明了改进算法具有良好的泛化性和鲁棒性。与其他主流算法相比, 改进算法同样表现出了更高的准确率和召回率, 表明该算法对于城市车辆目标检测具有更好的性能。

关键词: 车辆目标检测, YOLOv8n模型, 注意力机制, 轻量化, 加权交并比损失函数

Abstract:

To solve the problems of poor detection effect, high misdetection and omission rate, and weak generalization ability of urban vehicle target detection algorithms, this study proposes an improved YOLOv8 urban vehicle target detection algorithm. First, an Efficient Multi-scale Attention (EMA) mechanism is incorporated into the tail of the backbone network, which helps the model better capture the detailed features of a target vehicle. Combined with a 160×160 pixel small-target detection layer, it enhances the detection capability of small targets and aggregates pixel-level features through dimensional interaction to enhance the mining capability of the target vehicle. Second, the study designs a new Multi-scale Lightweight Convolution (MLConv) module for the lightweight network, and the C2f module is reconstructed based on MLConv, which significantly improves the feature extraction capability of the model. Finally, to suppress the harmful gradients generated by low-quality images, the study uses the Wise-Intersection over Union (WIoU) loss function instead of the Complete Intersection over Union (CIoU) to optimize the network's bounding box loss and improve the model's convergence speed and regression accuracy. On the Streets vehicle dataset, the algorithm improves mAP@0.5, mAP@0.5∶0.95, and recall by 1.9, 1.4 and 2.4 percentage points respectively, compared with the YOLOv8n benchmark model. In validations on a domestic vehicle dataset and the VisDrone2019 small target dataset, these performance indexes improve to different degrees, proving that the improved algorithm has good generalization and robustness. Compared with other mainstream algorithms, the improved algorithm exhibits higher accuracy and detection rate, indicating that the algorithm performs better in urban vehicle target detection.

Key words: vehicle target detection, YOLOv8n model, attention mechanism, lightweight, Wise-Intersection over Union (WIoU) loss function

许德刚, 王双臣, 尹柯栋, 王再庆. 改进YOLOv8的城市车辆目标检测算法[J]. 计算机工程, 2025, 51(11): 377-391.

XU Degang, WANG Shuangchen, YIN Kedong, WANG Zaiqing. Improved YOLOv8 Urban Vehicle Target Detection Algorithm[J]. Computer Engineering, 2025, 51(11): 377-391.

https://www.ecice06.com/CN/Y2025/V51/I11/377

图/表 24

图1 YOLOv8网络结构

Fig.1 YOLOv8 network structure

图2 改进YOLOv8网络结构

Fig.2 Improved YOLOv8 network structure

图3 EMA模块结构

Fig.3 EMA module structure

图4 GhostConv模块结构

Fig.4 GhostConv module structure

图5 MLConv模块结构

Fig.5 MLConv module structure

图6 ML-Bottleneck结构

Fig.6 ML-Bottleneck structure

图7 ML-C2f结构

Fig.7 ML-C2f structure

图8 改进检测层

Fig.8 Improved detection layer

图9 车辆训练集图片

Fig.9 Picture of vehicle training set

图10 BIT-Vehicle数据集检测结果对比

Fig.10 Comparison of BIT-Vehicle dataset detection results

图11 UA-DETRAC数据集检测结果对比

Fig.11 Comparison of UA-DETRAC dataset detection results

图12 VisDrone2019数据集检测结果对比

Fig.12 Comparison of VisDrone2019 dataset detection results

图13 mAP@0.5、mAP@0.5 ∶0.95、Recall和train/dfl_loss训练可视化对比

Fig.13 mAP@0.5, mAP@0.5 ∶0.95, Recall and train/dfl_loss training visualization comparison

图14 YOLOv8n与YOLOv8+EMA可视化对比

Fig.14 Visual comparison between YOLOv8n and YOLOv8+EMA

图15 YOLOv8n添加不同损失函数训练过程曲线

Fig.15 YOLOv8n adds training process curves with different loss functions

图16 不同算法对车辆检测效果对比

Fig.16 Comparison of vehicle detection effect of different algorithms

参考文献 27

1	申彩英, 朱思瑶, 黄兴驰. 双目视觉的智能汽车目标检测算法研究. 重庆理工大学学报(自然科学), 2023, 37 (21): 11- 19.
	SHEN C Y , ZHU S Y , HUANG X C . Research on intelligent vehicle target detection algorithm based on binocular vision. Journal of Chongqing University of Technology (Natural Science), 2023, 37 (21): 11- 19.
2	陈卫彪, 贾小军, 朱响斌, 等. 基于DSM-YOLO v5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 lmage based on DSM-YOLOv5. Computer Engineering and Applications, 2023, 59 (18): 226- 233.
3	BIE M L , LIU Y Y , LI G N , et al. Real-time vehicle detection algorithm based on a lightweight you-only-look-once approach. Expert Systems with Applications, 2023, 213, 119108. doi: 10.1016/j.eswa.2022.119108
4	LI W . Vehicle detection in foggy weather based on an enhanced YOLO method. Journal of Physics, 2022, 2284 (1): 012015.
5	韩俊, 袁小平, 王准, 等. 基于YOLOv5s的无人机密集小目标检测算法. 浙江大学学报(工学版), 2023, 57 (6): 1224- 1233.
	HAN J , YUAN X P , WANG Z , et al. UAV dense small target detection algorithm based on YOLOv5s. Journal of Zhejiang University (Engineering Science), 2023, 57 (6): 1224- 1233.
6	王承梅, 杜豫川. 基于YOLO算法的复杂交通环境中车辆目标检测方法. 交通与运输, 2023, 39 (2): 20- 24.
	WANG C M , DU Y C . Vehicle object detection method in complex traffic environment based on YOLO algorithm. Traffic and Transportation, 2023, 39 (2): 20- 24.
7	ZHANG Y , GUO Z Y , WU J Q , et al. Real-time vehicle detection based on improved YOLOv5. Sustainability, 2022, 14 (19): 12274. doi: 10.3390/su141912274
8	ZHOU F B, ZHAO H L, NIE Z. Safety helmet detection based on YOLOv5[C]//Proceedings of IEEE International Conference on Power Electronics, Computer Applications. Washington D. C., USA: IEEE Press, 2021: 6-11.
9	LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2017: 2117-2125.
10	LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 8759-8768.
11	OUYANG D L, HE S, ZHANG G Z, et al. Efficient multi-scale attention module with cross-spatial learning[C]//Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. Washington D. C., USA: IEEE Press, 2023: 1-5.
12	HAN K, WANG Y H, TIAN Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 365-377.
13	TONG Z. CHEN Y. XU Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[EB/OL]. [2023-11-20]. https://doi.org/10.48550/arXiv.2301.10051.
14	SNYDER C, DO M. STREETS: a novel camera network dataset for traffic flow[C]//Proceedings of Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 2021: 866-897.
15	DONG Z , WU Y W , PEI M T , et al. Vehicle type classification using a semisupervised convolutional neural network. IEEE Transactions on Intelligent Transportation Systems, 2021, 16 (4): 2247- 2256.
16	WEN L Y , DU D W , CAI Z W , et al. UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. Computer Vision and Image Understanding, 2020, 193, 102907. doi: 10.1016/j.cviu.2020.102907
17	ZHU P F, DU D W, WEN L Y, et al. VisDrone-VID2019: the vision meets drone object detection in video challenge results[C]// Proceedings of IEEE/CVF International Conference on Computer Vision Workshop. Washington D. C., USA: IEEE Press, 2019: 213-22.
18	HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 7132-7141.
19	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 3-19.
20	MA J , LU A G , CHEN C , et al. YOLOv5-lotus an efficient object detection method for lotus seedpod in a natural environment. Computers and Electronics in Agriculture, 2023, 206, 107635. doi: 10.1016/j.compag.2023.107635
21	GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[EB/OL]. [2023-11-20]. https://arxiv.org/abs/2205.12740v1.
22	ZHENG Z H, WANG P, LIU W, et al. Distance-loU loss: faster and better learning for bounding bot regression[C] //Proceedings of the 34th AAAl Conference on Artificial lntelligence. Palo Alto, USA: AAAl Press, 2020: 12993-13000.
23	ZHANG Y F , REN W Q , ZHANG Z , et al. Focal and efficient IoU loss for accurate bounding box regression. Neurocomputing, 2022, 506, 146- 157. doi: 10.1016/j.neucom.2022.07.042
24	GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2015: 1440-1448.
25	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37.
26	REDMON J, FARHADI A. YOLOv3: an incremental improvement[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 1-6.
27	LI C, LI L, JIANG H, et al. YOLOv6: a singlestage object detection framework for industrial applications[EB/OL]. [2023-11-20]. https://arxiv.org/abs/2209.02976.

[1]	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.
[2]	黄金贵, 刘朋, 唐文胜. MMD-YOLOv7:黑暗条件下车辆检测方法[J]. 计算机工程, 2025, 51(9): 340-349.
[3]	符家成, 田瑾, 张玉金, 方志军. 结合前置三元组集的知识图谱推荐[J]. 计算机工程, 2025, 51(9): 101-109.
[4]	翟志鹏, 曹阳, 沈琴琴, 施佺. 基于多时空图融合与动态注意力的交通流预测[J]. 计算机工程, 2025, 51(9): 139-148.
[5]	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.
[6]	陈彦如, 刘珂良, 冉茂亮. 基于深度强化学习的外卖即时配送实时优化[J]. 计算机工程, 2025, 51(9): 328-339.
[7]	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.
[8]	郝宏达, 罗健旭. 基于多尺度区域特征融合的多器官语义分割模型[J]. 计算机工程, 2025, 51(8): 270-280.
[9]	张昭理, 李家豪, 刘海, 石佛波, 何嘉文. 基于个性化遗忘建模的知识追踪方法[J]. 计算机工程, 2025, 51(8): 120-130.
[10]	闫建红, 刘芝妍, 王震. 融合时空注意力机制的多尺度卷积车辆轨迹预测[J]. 计算机工程, 2025, 51(8): 406-414.
[11]	刘春霞, 孟吉星, 潘理虎, 龚大立. 融合RGB与IR图像的遥感小目标检测方法[J]. 计算机工程, 2025, 51(7): 326-338.
[12]	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.
[13]	彭菊红, 张弛, 高谦, 张光明, 谈栋华, 赵明俊. 基于改进的YOLOv8算法的钢材缺陷检测[J]. 计算机工程, 2025, 51(7): 152-160.
[14]	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.
[15]	单鹏畅, 高利剑, 董文龙, 毛启容. 基于显著目标追踪的行为检测方法[J]. 计算机工程, 2025, 51(6): 93-101.

选择文件类型/文献管理软件名称

选择包含的内容