基于改进YOLOv8的交通场景目标检测方法

打开文本图片集

中图分类号：TP181 文献标识码：A 文章编号：1674-0033(2025)06-0043-12

（安徽理工大学机电工程学院，安徽淮南232000）

Traffic Scene Object Detection Method Based on Improved YOLOv8

QIANRui-ke,HUHai-xia

(School of Mechatronics Engineering,Anhui University of Science and Technology,Huainan 232Ooo,Anhui)

Abstract: To improve object detection efficiency in complex traffic scenarios，a traffic scene object detection method based on the improved YOLOv8 model is proposed.By replacing the YOLOv8 backbone withadensely connected network(DenseNet)，feature reuse and gradient fluidity are enhanced.An efcient pyramid compressed atention module(PSA) is introduced before the SPPF module to achieve multi-scale feature aggregation and adaptive adjustment of channel weights,strengthening context modeling and salient region representation.The loss function is replaced with the Unified IoU loss function,which improves bounding box fiting precision. Experimental results show that the improved YOLOv8 model achieves a precision of 88.2% on the KITTI public dataset, a 4.5% improvement over the YOLOv8n model and a 2.1% improvement over the YOLOv1On model. The inference speed is 98 frames per second(fps),and the recall is 87.3% .Theimproved detection accuracy for objects such asvehicles and pedestrians demonstrates this paper's model's superior performance and potential for application in traffic scene object detection.

Keywords:object detection;YOLOv8;DenseNet; PSA Module;Unified-IoU

随着自动驾驶技术的不断发展，行人及车辆的检测精度成为保障智能交通系统安全运行的核心要素之一。（剩余16424字）