基于改进YOLOv8的自动驾驶场景目标检测算法

doi:10.3778/j.issn.1002-8331.2404-0044

摘要/Abstract

摘要： 针对自动驾驶场景遮挡目标和小目标检测困难问题，提出了FAN-YOLOv8n自动驾驶检测算法。设计了特征感受野融合模块（EFFVM），增强模型主干部分对局部特征的提取，提高模型对遮挡目标的检测能力；在模型头部增加了更浅特征层P2的检测头，提高模型对于小目标的检测效果；在模型颈部设计了特征指导模块（FGM）来融合浅层和深层的特征信息，使得两层之间能够更好地进行特征交互，让模型更关注细粒特征。提出了特征层融合模块（FLFM），融合多尺度特征层并进行特征增强，使模型能够自适应不同尺度目标的检测。实验结果表明，在SODA10M数据集和部分BDD100K数据集上，改进模型的mAP0.5对比原始YOLOv8n模型提升了7个百分点和6.5个百分点，适用于实际自动驾驶检测任务。

关键词: 自动驾驶, YOLOv8n, 小目标, 遮挡目标

Abstract: A FAN-YOLOv8n autonomous driving detection algorithm is proposed to address the difficulties in detecting occluded and small targets in autonomous driving scenarios. Firstly, an enhanced feature field of view module (EFFVM) is designed to enhance the extraction of local features in the backbone of the model and improve its ability to detect occluded targets. Secondly, a shallower feature layer P2 detection head has been added to the model head to improve the detection performance of the model for small targets. Then, a feature guidance module (FGM) is adopted at the neck of the model to fuse shallow and deep feature information, enabling better feature interaction between the two layers and making the model more focused on fine-grained features. Finally, a feature layer fusion module (FLFM) is proposed to fuse multi-scale feature layers and perform feature enhancement, enabling the model to adaptively detect targets of different scales.The experimental results show that on the SODA10M dataset and some BDD100K dataset, the improved model’s mAP0.5 improves by 7 percentage points and 6.5 percentage points compared to the original YOLOv8n model, making it suitable for practical autonomous driving detection tasks.

Key words: autonomous driving, YOLOv8n, small targets, occluded targets

杨磊, 陈艳菲, 李海鸣, 石教兴, 安培. 基于改进YOLOv8的自动驾驶场景目标检测算法[J]. 计算机工程与应用, 2025, 61(1): 131-141.

YANG Lei, CHEN Yanfei, LI Haiming, SHI Jiaoxing, AN Pei. Object Detection Algorithm for Autonomous Driving Scenes Based on Improved YOLOv8[J]. Computer Engineering and Applications, 2025, 61(1): 131-141.

参考文献

[1] 史涛, 崔杰, 李松. 优化改进YOLOv8实现实时无人机车辆检测的算法[J]. 计算机工程与应用, 2024, 60(9): 79-89.
SHI T, CUI J, LI S. Algorithm for real-time vehicle detection from UAVs based on optimizing and improving YOLOv8[J]. Computer Engineering and Applications, 2024, 60(9): 79-89.
[2] 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.
[3] REN?S, HE?K, GIRSHICK?R, et?al. Faster?R-CNN: towards real-time?object?detection?with?region?proposal?networks[C]//Advances in Neural Information Processing Systems, 2015: 91-99.
[4] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, Oct 11-14, 2016. Cham: Springer International Publishing, 2016: 21-37.
[5] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[6] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[7] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition, 2023: 7464-7475.
[8] ZHU X, SU W, LU L, et al. Deformable DETR: deformable transformers for end-to-end object detection[J]. arXiv:2010. 04159, 2020.
[9] LI F, ZHANG H, LIU S, et al. DN-DETR: accelerate DETR training by introducing query denoising[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 13619-13627.
[10] LV W, XU S, ZHAO Y, et al. DETRs beat YOLOs on real-time object detection[J]. arXiv:2304.08069, 2023.
[11] LI Y, LI J, MENG P. Attention-YOLOV4: a real-time and high-accurate traffic sign detection algorithm[J]. Multimedia Tools and Applications, 2023, 82(5): 7567-7582.
[12] LIANG S, WU H, ZHEN L, et al. Edge YOLO: real-time intelligent object detection system based on edge-cloud cooperation in autonomous vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(12): 25345-25360.
[13] LUO Y, CI Y, JIANG S, et al. A novel lightweight real-time traffic sign detection method based on an embedded device and YOLOv8[J]. Journal of Real-Time Image Processing, 2024, 21(2): 24.
[14] 田鹏, 毛力. 改进YOLOv8的道路交通标志目标检测算法[J]. 计算机工程与应用, 2024, 60(8): 202-212.
TIAN P, MAO L. Improved YOLOv8 object detection algorithm for traffic sign target[J]. Computer Engineering and Applications, 2024, 60(8): 202-212.
[15] 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.
[16] 刘辉, 刘鑫满, 刘大东. 面向复杂道路目标检测的YOLOv5算法优化研究[J]. 计算机工程与应用, 2023, 59(18): 207-217.
LIU H, LIU X M, LIU D D. Research on optimization of YOLOv5 detection algorithm for object in complex road[J]. Computer Engineering and Applications, 2023, 59(18): 207-217.
[17] 刘海斌, 张友兵, 周奎, 等. 改进YOLOv5 -S的交通标志检测算法[J]. 计算机工程与应用, 2024, 60(5): 200-209.
LIU H B, ZHANG Y B, ZHOU K, et al. Traffic sign detection algorithm based on improved YOLOv5-S[J]. Computer Engineering and Applications, 2024, 60(5): 200-209.
[18] DING X, ZHANG X, HAN J, et al. Scaling up your kernels to 31×31: revisiting large kernel design in CNNs[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 11963-11975.
[19] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
[20] HAN J, LIANG X, XU H, et al. SODA10M: a large-scale 2D self/semi-supervised object detection dataset for autonomous driving[J]. arXiv:2106.11118, 2021.
[21] YU F, CHEN H, WANG X, et al. BDD100K: a diverse driving dataset for heterogeneous multitask learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 2636-2645.
[22] LAU K W, PO L M, REHMAN Y A U. Large separable kernel attention: rethinking the large kernel attention design in cnn[J]. Expert Systems with Applications, 2024, 236: 121352.
[23] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision, 2018: 3-19.