改进YOLOv8s的交通标志检测算法

doi:10.19678/j.issn.1000-3428.0068742

摘要/Abstract

摘要：

针对当前主流的交通标志目标检测算法在复杂环境中对小目标检测精度低、存在误检和漏检的问题, 提出一种改进的基于YOLOv8s的交通标志检测算法。该算法在主干网络中使用Pconv卷积并设计C2faster模块, 以实现轻量化网络结构同时维持网络精度。为更好地利用底层和高层特征之间的信息, 并增强区域上下文关联能力, 根据SPPF的思想设计SPPFCSPC模块作为空间金字塔池化模块。通过添加GAM注意力机制进一步增强网络的特征提取能力, 有效提高检测精度。为改善对微小目标的检测能力, 在网络颈部添加四倍下采样分支, 优化目标定位。此外, 使用Focal-EIoU损失函数替换原CIoU损失函数, 对预测框的宽高比进行准确定义, 缓解正负样本不平衡的问题。实验结果表明, 在CCTSDB-2021交通标志数据集上, 改进算法的精确率、召回率和mAP@0.5分别达到86.1%、73.0%和81.2%, 相比原始的YOLOv8s算法分别提高了0.8%、6.3%和6.9%。此外, 该算法在复杂天气和恶劣环境下的误检和漏检问题得到明显改善, 综合检测性能明显优于对比算法, 具有较大的实用价值。

关键词: YOLOv8, 交通标志检测, 注意力机制, Pconv, C2faster

Abstract:

Due to low detection accuracy for small targets in complex environments, along with false and missed detections in mainstream traffic sign detection algorithms, an improved algorithm based on YOLOv8s is proposed. This algorithm uses Pconv convolution in the backbone network and incorporates a C2faster module to achieve a lightweight network structure while maintaining network accuracy. In addition, to better utilize the information between low- and high-level features and enhance the regional context association ability, the SPPFCSPC module is designed as a spatial pyramid pooling module based on the concept of SPPF. In addition, by adding the GAM attention mechanism, the feature extraction capability of the network is further enhanced, and the detection accuracy is effectively improved. To improve the detection ability of small targets, a four-fold downsampling branch is added at the neck of the network to optimize target positioning. In addition, the Focal-EIoU loss function is used to replace the original CIoU loss function to accurately define the aspect ratio of the prediction box, which alleviates the problem of imbalance between the positive and negative samples. Experimental results show that on the CCTSDB-2021 traffic sign dataset, the improved algorithm achieved 86.1%, 73.0%, and 81.2% precision, recall, and mAP@0.5, respectively. Compared with the original YOLOv8s algorithm, increases of 0.8%, 6.3%, and 6.9% were observed, respectively. This algorithm significantly reduces false and missed detections in complex weather and harsh environments, offering better overall detection performance than the comparison algorithm, with strong practical value.

Key words: YOLOv8, traffic sign detection, attention mechanism, Pconv, C2faster

谢竞, 邓月明, 王润民. 改进YOLOv8s的交通标志检测算法[J]. 计算机工程, 2024, 50(11): 338-349.

XIE Jing, DENG Yueming, WANG Runmin. Improved Traffic Sign Detection Algorithm Based on YOLOv8s[J]. Computer Engineering, 2024, 50(11): 338-349.

https://www.ecice06.com/CN/Y2024/V50/I11/338

图/表 22

图1 YOLOv8s网络结构

Fig.1 YOLOv8s network structure

图2 改进的YOLOv8s网络结构

Fig.2 Improved YOLOv8s network structure

图3 Pconv原理

Fig.3 The principle of Pconv

图4 Fasternet的结构

Fig.4 The structure of Fasternet

图5 C2faster的结构

Fig.5 The structure of C2faster

图6 SPPFCSPC的结构

Fig.6 The structure of SPPFCSPC

图7 GAM注意力机制原理

Fig.7 Principle of GAM attention mechanism

图8 C2faster+SPPFCSPC+GAM结构

Fig.8 The structure of C2faster+SPPFCSPC+GAM

图9 所有类的PR曲线

Fig.9 PR curves for all classes

图10 各指标检测结果

Fig.10 Test results of various indicators

图11 复杂路况下的检测结果对比

Fig.11 Comparison of detection results under complex road conditions

图12 雪天情况下的检测结果对比

Fig.12 Comparison of detection results under snowy conditions

图13 雾天情况下的检测结果对比

Fig.13 Comparison of detection results under foggy conditions

图14 晴天情况下的检测结果对比

Fig.14 Comparison of detection results under clear weather conditions

图15 夜晚情况下的检测结果对比

Fig.15 Comparison of detection results under nighttime conditions

参考文献 32

1	TRIKI N, KARRAY M, KSANTINI M. A real-time traffic sign recognition method using a new attention-based deep convolutional neural network for smart vehicles. Applied Sciences, 2023, 13(8): 4793. doi: 10.3390/app13084793
2	曹健, 陈怡梅, 李海生, 等. 基于深度学习的道路小目标检测综述. 计算机工程, 2023, 49(10): 1- 12. doi: 10.19678/j.issn.1000-3428.0065984
	CAO J, CHEN Y M, LI H S, et al. Survey of small target detection on roads based on deep learning. Computer Engineering, 2023, 49(10): 1- 12. doi: 10.19678/j.issn.1000-3428.0065984
3	CHUAN L, PAN S H, FAN Z, et al. A method of traffic sign detecting based on color similarity[EB/OL]. [2023-10-05]. https://ieeexplore.ieee.org/abstract/document/5720737.
4	罗会兰, 陈鸿坤. 基于深度学习的目标检测研究综述. 电子学报, 2020, 48(6): 1230- 1239.
	LUO H L, CHEN H K. Review of target detection research based on deep learning. Acta Electronica Sinica, 2020, 48(6): 1230- 1239.
5	BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. [2023-10-05]. https://arxiv.org/abs/2004.10934.
6	QIAO S Y, CHEN L C, YUILLE A. DetectoRS: detecting objects with recursive feature pyramid and switchable atrous convolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2021: 10213-10224.
7	LI C Y, LI L, JIANG H L, et al. YOLOv6: a single-stage object detection framework for industrial applications[EB/OL]. [2023-10-05]. https://arxiv.org/abs/2209.02976.
8	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 Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 7464-7475.
9	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[EB/OL]. [2023-10-05]. https://link.springer.com/chapter/10.1007/978-3-319-46448-0_2.
10	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2014: 580-587.
11	GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2015: 1440-1448.
12	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
13	HE K, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2017: 2961-2969.
14	CAO J, LI P, ZHANG H, et al. An improved YOLOv4 lightweight traffic sign detection algorithm[EB/OL]. [2023-10-05]. https://www.iaeng.org/IJCS/issues_v50/issue_3/IJCS_50_3_01.pdf.
15	CHU J, ZHANG C, YAN M, et al. TRD-YOLO: a real-time, high-performance small traffic sign detection algorithm. Sensors (Basel, Switzerland), 2023, 23(8): 3871. doi: 10.3390/s23083871
16	SRINIVAS A, LIN T Y, PARMAR N, et al. Bottleneck transformers for visual recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2021: 16519-16529.
17	GAO X, CHEN L, WANG K, et al. Improved traffic sign detection algorithm based on Faster R-CNN. Applied Sciences, 2022, 12(18): 8948. doi: 10.3390/app12188948
18	赵宏, 冯宇博. 基于CGS-Ghost YOLO的交通标志检测研究. 计算机工程, 2023, 49(12): 194- 204. doi: 10.19678/j.issn.1000-3428.0066520
	ZHAO H, FENG Y B. Research on traffic sign detection based on CGS-Ghost YOLO. Computer Engineering, 2023, 49(12): 194- 204. doi: 10.19678/j.issn.1000-3428.0066520
19	GE Z, LIU S T, WANG F, et al. YOLOX: exceeding YOLO series in 2021[EB/OL]. [2023-10-05]. http://arxiv.org/abs/2107.08430v2.
20	GHIASI G, LIN T Y, LE Q V. NAS-FPN: learning scalable feature pyramid architecture for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2019: 7036-7045.
21	YANG J F, FU X Y, HU Y W, et al. PanNet: a deep network architecture for pan-sharpening[C]//Proceedings of the IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2017: 5449-5457.
22	ZHANG S F, CHI C, YAO Y Q, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 9759-9768.
23	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. Washington D. C., USA: IEEE Press, 2023: 12021-12031.
24	HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904- 1916. doi: 10.1109/TPAMI.2015.2389824
25	LIU Y C, SHAO Z R, HOFFMANN N. Global attention mechanism: retain information to enhance channel-spatial interactions[EB/OL]. [2023-10-05]. http://arxiv.org/abs/2112.05561v1.
26	JIANG B, LUO R, MAO J, et al. Acquisition of localization confidence for accurate object detection[C]//Proceedings of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 784-799.
27	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
28	ZHANG J, ZOU X, KUANG L D, et al. CCTSDB-2021: a more comprehensive traffic sign detection benchmark[EB/OL]. [2023-10-05]. https://centaur.reading.ac.uk/106129/1/12-23.pdf.
29	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.
30	WANG Q L, WU B G, ZHU P F, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 11534-11542.
31	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[EB/OL]. [2023-10-05]. https://link.springer.com/chapter/10.1007/978-3-030-01234-2_1.
32	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. Washington D. C., USA: IEEE Press, 2019: 658-666.

[1]	李俊俊, 董建刚, 李坤. 基于Kubernetes的集群节能策略研究[J]. 计算机工程, 2024, 50(9): 82-91.
[2]	林畅, 郭伟, 任哲聪, 金海波. 基于Transformer的目标跟踪与分割统一算法[J]. 计算机工程, 2024, 50(9): 130-141.
[3]	李泽霖, 吕兆峰, 陈富强, 李克. 基于多跳信息融合的实体对齐模型[J]. 计算机工程, 2024, 50(9): 142-152.
[4]	王汝英, 马嘉骏, 董建强, 刘万龙, 张海涛, 尹凯, 赵博超. 基于MTS-BiGRU-DMHSA的工业负荷预测方法[J]. 计算机工程, 2024, 50(9): 169-178.
[5]	朱凯, 李理, 张彤, 江晟, 别一鸣. 基于Transformer的多阶段运动模糊图像修复网络[J]. 计算机工程, 2024, 50(9): 276-285.
[6]	张天鹏, 韩晶, 吕学强. 基于多任务学习的超分辨率辅助小目标检测[J]. 计算机工程, 2024, 50(9): 304-312.
[7]	郭敏, 张熙涵, 李阳. 融合注意力的教师互一致性半监督医学图像分割[J]. 计算机工程, 2024, 50(9): 313-323.
[8]	曾钰琦, 刘博, 钟柏昌, 钟瑾. 智慧教育下基于改进YOLOv8的学生课堂行为检测算法[J]. 计算机工程, 2024, 50(9): 344-355.
[9]	饶日昕, 王怡文, 曾砺志, 童心恬, 赵海涛. 面向废旧电缆检测的轻量化网络模型[J]. 计算机工程, 2024, 50(8): 22-30.
[10]	李华昱, 张智康, 闫阳, 岳阳. 基于知识图谱增强的领域多模态实体识别[J]. 计算机工程, 2024, 50(8): 31-39.
[11]	王蕾, 党时鹏, 潘丰. 基于卷积神经网络的隐匿性旁路预测模型[J]. 计算机工程, 2024, 50(8): 40-49.
[12]	陈瀚, 赵春蕾, 蒋昊达, 王春东. 基于融合模型与语义网络的App用户意图识别研究[J]. 计算机工程, 2024, 50(8): 50-63.
[13]	王夙喆, 张雪英, 陈晓玉, 李凤莲, 吴泽林. 基于有效注意力和GAN结合的脑卒中EEG增强算法[J]. 计算机工程, 2024, 50(8): 336-344.
[14]	王宇, 祁琦, 王纯, 许才. 储能变流器信号高精度故障诊断方法[J]. 计算机工程, 2024, 50(8): 389-396.
[15]	王炼红, 林飞鹏, 李潇瑶, 谌桂枝, 周莉. 融入课程知识图谱的KMAKT预测[J]. 计算机工程, 2024, 50(7): 23-31.

选择文件类型/文献管理软件名称

选择包含的内容