计算机工程与应用 ›› 2025, Vol. 61 ›› Issue (4): 262-271.DOI: 10.3778/j.issn.1002-8331.2405-0103

• 图形图像处理 • 上一篇    下一篇

PMM-YOLO:多尺度特征融合的交通标志检测算法

赵磊,李栋   

  1. 内蒙古工业大学 信息工程学院,呼和浩特 010080
  • 出版日期:2025-02-15 发布日期:2025-02-14

PMM-YOLO:Traffic Sign Detection Algorithm with Multi-Scale Feature Fusion

ZHAO Lei, LI Dong   

  1. School of Information Engineering, Inner Mongolia University of Technology, Hohhot 010080, China
  • Online:2025-02-15 Published:2025-02-14

摘要: 交通标志在智能驾驶领域有着重要的作用,面对交通标志尺寸小,易受遮挡,在复杂环境下容易出现漏检、错检等问题,提出了一种基于YOLOv5改进的PMM-YOLO交通标志检测算法。为了能够有效提取多尺度信息,并增强模型对特征信息的表达能力,提出了一种结合注意力机制的并行空洞卷积模块(adaptive parallel atrous convolution,APA),使用具有不同膨胀率的并行空洞卷积,能够有效地提取不同尺度的特征,并通过gate机制突出关键目标的特征表示,提高检测的准确性;设计了一种多分支的自适应采样(multi-branch adaptive sampling,MBAS),多分支的采样可为网络提供多条特征提取途径,丰富特征表达的多样性,并通过不同位置的权重筛选重要特征进行强化,抑制冗余特征;设计了多尺度特征融合(multi-scale feature fusion,MSFF)模块,对不同大小尺度的特征图进行拼接,充分利用多尺度信息,将多个尺度的特征图融合,以获取更全面的目标特征,提升对目标的检测效果。构建了输出重组(output reorganization,ORO)模块,增加小目标检测层并去除大目标检测层,提升对小目标的检测效果,并相应减少模型复杂度。实验结果表明,PMM-YOLO算法在TT100Ke数据集上的mAP@0.5达到了86.4%,较原YOLOv5提升了5.9个百分点,且FPS较改进前提升了4.4%,能够快速准确地对交通标志进行检测。

关键词: 交通标志检测, YOLOv5, 多分支采样, 特征融合, 空洞卷积, 注意力机制

Abstract: Traffic signs play a crucial role in the field of autonomous driving. However, they often present challenges such as small size, susceptibility to occlusion, and missed detections and false alarms in complex environments. This paper proposes a PMM-YOLO traffic sign detection algorithm based on improvements to YOLOv5. To effectively extract multi-scale information and enhance the model’s feature representation capability, an adaptive parallel atrous convolution (APA) module combining attention mechanism is introduced. Utilizing parallel atrous convolutions with different dilation rates enables effective extraction of features at various scales, while a gate mechanism highlights the representation of key targets, improving detection accuracy. A multi-branch adaptive sampling (MBAS) approach is designed to provide multiple feature extraction pathways for the network, enriching feature expression diversity. The important features are reinforced by the weight at different positions, and redundant features are suppressed. A multi-scale feature fusion (MSFF) module is devised to concatenate feature maps of different sizes, leveraging multi-scale information to fuse feature maps of multiple scales comprehensively, thus obtaining more comprehensive target features and enhancing detection performance. An output reorganization (ORO) module is constructed to enhance the detection of small targets by adding a small target detection layer and removing the large target detection layer, thereby reducing model complexity accordingly. Experimental results demonstrate that the PMM-YOLO algorithm achieves an mAP@0.5 of 86.4% on the TT100K dataset, representing a 5.9 percentage points improvement over the original YOLOv5. Additionally, the FPS is increased by 4.4% compared to the baseline, enabling rapid and accurate detection of traffic signs.

Key words: traffic sign detection, YOLOv5, multi-branch sampling, feature fusion, atrous convolution, attention mechanism