改进YOLOv8算法的城市车辆目标检测

doi:10.3778/j.issn.1002-8331.2401-0277

摘要/Abstract

摘要： 针对复杂交通场景下城市车辆目标检测算法存在的漏检、精度低、泛化能力弱的问题，提出一种改进的YOLOv8城市车辆目标检测算法。采用一种改进的GAM-C2f结构来代替主干网络中的C2f模块，平衡模型的计算效率和准确性；设计一种SPPFAPGC模块，防止SPPF结构因最大池化操作所导致的局部特征丢失问题，提高特征图的丰富度，并进一步结合小目标检测头来加强对远处小目标车辆的检测能力，加强局部特征与全局特征的融合。为抑制低质量图像产生的有害梯度，使用WIOU损失函数代替CIoU，以提升网络的边界框回归性能，提高模型的收敛速度和回归精度。在Streets车辆数据集上的实验结果表明，与基准模型YOLOv8n相比，改进算法的mAP50和Recall分别提高了1.6和2.0个百分点，有效改善了城市交通场景下小目标车辆检测性能不佳的问题；在VisDrone2019数据集上进行验证，mAP50和Recall也分别提高了1.1和1.6个百分点，充分证明了改进算法的优越性。与其他先进主流算法相比，改进算法表现出了更高的准确率和查全率，表明改进算法在城市车辆检测任务中具有更好的性能。

关键词: 车辆目标检测, YOLOv8, C2f模块, SPPF模块, 损失函数

Abstract: Aiming to address the challenges of missing detection, low precision, and weak generalization ability in urban vehicle target detection algorithms for complex traffic scenes, an enhanced YOLOv8 algorithm is proposed. Firstly, this paper replaces the C2f module in the backbone network with an improved GAM-C2f structure to strike a balance between computational efficiency and model accuracy. Secondly, a SPPFAPGC module is designed to prevent local feature loss caused by maximum pooling operations in the SPPF structure. This enhances the richness of the feature map and combines it with a small target detection head to strengthen distant small target vehicle detection capability while integrating local and global features effectively. Finally, to suppress harmful gradients generated by low-quality images, this paper utilizes WIOU loss function instead of CIoU for improved bounding box regression performance, faster convergence speed, and higher regression accuracy. Experimental results on street vehicle datasets demonstrate that compared to the benchmark model YOLOv8n, the improved algorithm achieves a 1.6 percentage points increase in mAP50 and a 2.0 percentage points increase in Recall respectively , the problem of poor detection performance for small-target vehicles in urban traffic scenes is effectively improved. Verification on VisDrone2019 dataset also shows improvements of 1.1 percentage points in mAP50 and 1.6 percentage points in Recall further confirming the superiority of the enhanced algorithm over others mainstream algorithms regarding accuracy and recall rate specifically tailored for urban vehicle detection tasks.

Key words: vehicle target detection, YOLOv8, C2f module , SPPF module, loss function

许德刚, 王双臣, 王再庆, 尹柯栋. 改进YOLOv8算法的城市车辆目标检测[J]. 计算机工程与应用, 2024, 60(18): 136-146.

XU Degang, WANG Shuangchen, WANG Zaiqing, YIN Kedong. Improved YOLOv8 Urban Vehicle Target Detection Algorithm[J]. Computer Engineering and Applications, 2024, 60(18): 136-146.

参考文献

[1] ZHENG Q, TIAN X, YU Z, et al. DL-PR: generalized automatic modulation classification method based on deep learning with priori regularization[J]. Engineering Applications of Artificial Intelligence, 2023, 122: 106082.
[2] ZHENG Q, TIAN X, YU Z, et al. Application of wavelet-packet transform driven deep learning method in PM2.5 concentration prediction: a case study of Qingdao, China[J]. Sustainable Cities and Society, 2023, 92: 104486.
[3] 张利丰, 田莹. 改进YOLOv8的多尺度轻量型车辆目标检测算法[J]. 计算机工程与应用, 2024, 60(3): 129-137.
ZHANG L F, TIAN Y. Improved YOLOv8 multi-scale and lightweight vehicle object detection algorithm[J]. Computer Engineering and Applications, 2024, 60(3): 129-137.
[4] 周飞, 郭杜杜, 王洋, 等. 基于改进YOLOv8的交通监控车辆检测算法[J]. 计算机工程与应用, 2024, 60(6): 110-120.
ZHOU F, GUO D D, WANG Y, et al. Vehicle detection algorithm based on improved YOLOv8 in traffic surveillance[J]. Computer Engineering and Applications, 2024, 60(6): 110-120.
[5] ZHAO X, XIA Y, ZHANG W, et al. YOLO-ViT-based method for unmanned aerial vehicle infrared vehicle target detection[J]. Remote Sensing, 2023, 15(15): 3778.
[6] KANG L, LU Z, MENG L, et al. YOLO-FA: type-1 fuzzy attention based YOLO detector for vehicle detection[J]. Expert Systems with Applications, 2024, 237: 121209.
[7] QIU Z, BAI H, CHEN T. Special vehicle detection from UAV perspective via YOLO-GNS based deep learning network[J]. Drones, 2023, 7(2): 117.
[8] LI W. Vehicle detection in foggy weather based on an enhanced YOLO method[C]//Journal of Physics: Conference Series, 2022.
[9] HAN K, WANG Y H, TIAN Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
[10] TONG Z, CHEN Y, XU Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[J]. arXiv:2301.10051, 2023.
[11] 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, 2018: 8759-8768.
[12] LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117-2125.
[13] SNYDER C, DO M N. Streets: a novel camera network dataset for traffic flow[C]//Advances in Neural Information Processing Systems, 2019.
[14] LI C, ZHOU A, YAO A. Omni-dimensional dynamic convolution[J]. arXiv:2209.07947, 2022.
[15] LI H L, LI J, WEI H B, et al. Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles[EB/OL]. (2022) [2023-02-20]. https:llarxiv.org/abs/2206.02424.pdf.
[16] WANG C Y, BOCHKOVSKIY A, LIAO H Y. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J]. arXiv:2207.02696, 2022.
[17] LI C, LI L, JIANG H, et al. YOLOv6: a single-stage object detection framework for industrial applications[J]. arXiv:2209.02976, 2022.
[18] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[19] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Lecture Notes in Computer Science, Amsterdam, 2016: 21-37.
[20] REDMON J, FARHADI A. Yolov3: an incremental improvement[C]//Proceedings of the IEEE International Conference on Computer Vision and Pattem Recognition. Berlin, Heidelberg, Germany: Springer, 2018: 1-6.
[21] ZHOU F, ZHAO H, NIE Z. Safety helmet decton based on YOLOv5[C]//Proceedings of 2021 IEEE International Conference on Power Electronics, Computer Applications, 2021: 6-11.
[22] WANG C, HE W, NIE Y, et al. Gold-YOLO: efficient object detector via gather-and-distribute mechanism[C]//Advances in Neural Information Processing Systems, 2024.
[23] OUYANG D L, HE S, ZHANG G Z, et al. Efficient multi-scale attention module with cross-spatial learning[C]//Proceedings of 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023: 1-5.
[24] 熊恩杰, 张荣芬, 刘宇红, 等. 面向交通标志的Ghost-YOLOv8检测算法[J].计算机工程与应用, 2023, 59(20): 200-207.
XIONG E J, ZHANG R F, LIU Y H, et al. Ghost-YOLOv8 detection algorithm for traffic signs[J]. Computer Engineering and Applications, 2023, 59(20): 200-207.
[25] DU D W, ZHU P F, WEN L Y, et al. VisDrone-DET2019: the vision meets drone object detection in image challenge results[C]//Proceedings of 2019 IEEE/CVF lnternational Conference on Computer Vision Workshop. Seoul: lEEE, 2019: 213-222.