基于改进的yolov5n模型车辆检测算法
Vehicle Detection Algorithm Based on Improved YOLOv5n Model
王文上 1刘晓群 1郝娟1
作者信息
- 1. 河北建筑工程学院,河北 张家口 075000
- 折叠
摘要
随着智能交通系统的发展,车辆检测技术在交通安全和智能监控中发挥着重要作用.文章通过改进yolov5n的模型,引入 Coordatt(Coordinate Attention)注意力机制让模型更加聚焦于关键信息,提高对目标物体的定位和识别能力,同时又添加了 EIOU损失函数,该损失函数有助于模型更准确地预测边界框并且加快模型的收敛速度.改进后的模型YOLO-CE在自制数据集上的检测上取得了显著的性能提升,与原始的模型相比,精度提高了 1.4％,召回率提高了3.5％,mAP 值提高了 1.7％.
Abstract
With the development of intelligent transportation systems,vehicle detection technolo-gy plays an important role in traffic safety and intelligent monitoring.This article improves the YOLOv5N model by introducing the Coordinate Attention mechanism to focus more on key in-formation,improving the localization and recognition ability of target objects.At the same time,an EIOU loss function is added,which helps the model predict bounding boxes more accurately and accelerates the convergence speed of the model.The improved model YOLO-CE achieved significant performance improvement in detection on self-made datasets,with an accuracy in-crease of 1.4％,a recall increase of 3.5％,and an mAP value increase of 1.7％compared to the original model.
关键词
olov5n/车辆检测/注意力机制/损失函数Key words
yolov5n/Vehicle inspection/Attention mechanism/loss function引用本文复制引用
出版年
2024
NETL
NSTL
万方数据