计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (3): 129-137.DOI: 10.3778/j.issn.1002-8331.2309-0145

• 目标检测专题 • 上一篇    下一篇

改进YOLOv8的多尺度轻量型车辆目标检测算法

张利丰,田莹   

  1. 辽宁科技大学 计算机与软件工程学院,辽宁 鞍山 114000
  • 出版日期:2024-02-01 发布日期:2024-02-01

Improved YOLOv8 Multi-Scale and Lightweight Vehicle Object Detection Algorithm

ZHANG Lifeng, TIAN Ying   

  1. School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan, Liaoning 114000, China
  • Online:2024-02-01 Published:2024-02-01

摘要: 针对传统车辆目标检测模型设备需求高、检测精度低、重叠目标漏检率高等问题,提出了一种改进YOLOv8的车辆目标检测算法RBT-YOLO。采用多尺度融合的方式对主干网络进行重构。对BiFPN进行改进,增加卷积操作以及调整输入输出通道个数以适应YOLOv8,加强其特征融合能力。在Neck部分输出的特征图之后加入轻量型注意力机制Triplet Attention,提升模型的特征提取能力。针对真实情况下车辆目标重叠度较高的问题,使用SoftNMS(soft non-maximum suppression)替换原有NMS,使模型对候选框的处理方式更为温和,增强了模型对目标的检测能力,提升了召回率。在Pascal VOC和MS COCO数据集上进行实验,结果表明提出的RBT-YOLO性能超越原始模型,参数量和计算量下降60%左右,mAP分别提高了2.6和3.0个百分点,并在体积和精度上优于其他经典检测模型,具有很强的实用性。

关键词: 车辆检测, 多尺度, 注意力机制, YOLOv8, 非极大值抑制

Abstract: To address issues such as high hardware requirements, low detection accuracy, and a high rate of missed overlapping targets in traditional vehicle object detection models, a modified vehicle object detection algorithm called RBT-YOLO based on YOLOv8 is proposed. The main network is reconstructed using a multi-scale fusion approach. BiFPN is improved by adding convolutional operations and adjusting input/output channel numbers to adapt to YOLOv8, enhancing its feature fusion capability. After the feature maps are output from the Neck section, a lightweight attention mechanism called Triplet Attention is introduced to enhance the feature extraction ability of the model. To address the issue of high target overlap in real scenarios, SoftNMS (soft non-maximum suppression) is used to replace the original NMS, making the model to handle the candidate boxes more gentle, thereby strengthening detection capabilities of the model and improving recall rates. Experimental results on the Pascal VOC and MS COCO datasets demonstrate that the proposed RBT-YOLO outperforms the original model, reducing parameters and computations by approximately 60%, the mAP improved by 2.6 and 3.0 percentage points, and excelling in both size and precision compared to other classic detection models, thus demonstrating strong practical utility.

Key words: vehicle detection, multi-scale, attention mechanism, YOLOv8, non-maximum suppression