基于改进YOLO的车辆与行人识别算法分析  

Analysis of Vehicle and Pedestrian Recognition Algorithm Based on lmproved YOLO

作　　者：李昌赫 Li Changhe(Olin College,Northeast Forestry University,Heilongjiang150040,China.)

机构地区：[1]东北林业大学奥林学院,黑龙江150040

出　　处：《电子技术(上海)》2025年第1期80-82,共3页Electronic Technology

摘　　要：阐述一种基于改进YOLO的车辆行人识别算法。通过分析当前算法的不足,提出特征金字塔网络(FPN)和损失函数调整的改进方案。该算法通过卷积层提取多层图像特征,进行特征融合与多尺度检测,并在现有损失函数的基础上引入Focal Loss代替原有分类损失,从而改善检测性能,解决了小目标识别不精准的问题。This paper expounds a vehicle pedestrian recognition algorithm based on improved YOLO.It analyzes the shortcomings of current algorithms and proposes improved schemes such as Feature Pyramid Network(FPN)and loss function adjustment.It extracts multi-layer image features through convolutional layers,performs feature fusion and multi-scale detection,and introduces Focal Loss instead of the original classification loss on the basis of the existing loss function to improve the current detection performance and solve the problem of inaccurate recognition of small targets.

关 键 词：智能技术 多层图像 YOLO 车辆行人识别 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.4[自动化与计算机技术—控制科学与工程]