计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (8): 202-212.DOI: 10.3778/j.issn.1002-8331.2309-0415

• 图形图像处理 • 上一篇    下一篇

改进YOLOv8的道路交通标志目标检测算法

田鹏,毛力   

  1. 江南大学 人工智能与计算机学院,江苏 无锡 214122
  • 出版日期:2024-04-15 发布日期:2024-04-15

Improved YOLOv8 Object Detection Algorithm for Traffic Sign Target

TIAN Peng, MAO Li   

  1. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, China
  • Online:2024-04-15 Published:2024-04-15

摘要: 虽然,当前检测技术日趋成熟,但对于复杂环境下的小目标检测仍然是研究的重难点。针对道路交通场景中普遍存在的交通标志小目标比例较高,环境干扰因素较大的问题,提出了一种基于YOLOv8改进的道路交通标志目标检测算法。由于小目标检测中容易出现漏检的现象,利用BRA(bi-level routing attention)注意力机制提高网络对小目标的感知能力。此外,还利用可形变卷积模块DCNv3(deformable convolution v3),针对特征图中的不规则形状具有更好的特征提取能力,使骨干网络更好地适应不规则的空间结构,更精准地关注重要目标,从而提高模型对遮挡重叠目标的检测能力。DCNv3和BRA模块均在基本不增加模型权重大小的情况下提高模型准确性。同时引入基于辅助边框的Inner-IOU损失函数。在RoadSign、CCTSDB、TSDD、GTSDB四个数据集上,分别进行了小样本训练、大样本训练、单目标检测和多目标检测,实验结果均有所提高。其中,在RoadSign数据集上的实验结果最佳,YOLOv8改进模型的均值平均精度mAP50与mAP50:95分别达到了90.7%和75.1%,相较于基线模型,mAP50与mAP50:95分别提升了5.9和4.8个百分点。实验结果表明,YOLOv8改进模型有效地实现了在复杂道路场景下的交通标志检测。

关键词: YOLOv8, 小目标检测, 可形变卷积, 注意力机制, 复杂道路场景

Abstract: Although the current testing technology is becoming increasingly mature, the detection of small targets in complex environments is still the most difficult point in research. Aiming at the problem of high target proportion of traffic signs in road traffic scenarios, the problem of high target proportion of small targets and large environmental interference factors, it proposes a type of road traffic logo target test algorithm based on YOLOv8 improvement. Due to the prone to missed inspection in small target testing, the bi-level routing attention (BRA) attention mechanism is used to improve the network’s perception of small targets. In addition, it also uses a shape-changing convolutional module deformable convolution V3 (DCNV3). It has a better feature extraction ability for irregular shapes in the feature map, so that the backbone network can better adapt to irregular space structures, and pay more accurately to important attention,objectives, thereby improving the detection ability of the model to block the overlapping target. Both DCNV3 and BRA modules improve the accuracy of the model without increasing the weight of the model. At the same time, the Inner-IOU loss function based on auxiliary border is introduced. On the four data sets of RoadSign, CCTSDB, TSDD, and GTSDB, small sample training, large sample training, single target detection, and multi-target detection are performed. The experimental results are improved. Among them, the experiments on the RoadSign data set are the best. The average accuracy of the improved YOLOv8 model mAP50 and mAP50:95 reaches 90.7% and 75.1%, respectively. Compared with the baseline model, mAP50 and mAP50:95 have increased by 5.9 and 4.8 percentage points, respectively. The experimental results show that the improved YOLOV8 model effectively implements the traffic symbol detection in complex road scenarios.

Key words: YOLOv8, small target detection, deformable convolution, attention mechanism, complex road scenes