Pedestrian safety alarm system based on binocular distance measurement for trucks using recognition feature analysis  

作　　者：Tingting Bao Ding Lin Xumei Zhang Zhiguo Zhou Kejia Wang 

机构地区：[1]Automobile School,Zhejiang Institute of Communications,Hangzhou,311112,China [2]School of Automobile and Traffic Engineering,Wuhan University of Science and Technology,Wuhan,430075,China

出　　处：《Autonomous Intelligent Systems》2024年第1期81-90,共10页自主智能系统(英文)

基　　金：funded by the science and technology Project of Zhejiang Province under Grant No.2023C35088.

摘　　要：As an essential part of modern smart manufacturing,road transport with large and heavy trucks has in-creased dramatically.Due to the inside wheel difference in the process of turning,there is a considerable safety hazard in the blind area of the inside wheel difference.In this paper,multiple cameras combined with deep learning algorithms are introduced to detect pedestrians in the blind area of wheel error.A scheme of vehicle-pedestrian safety alarm detection system is developed via the integration of YOLOv5 and an improved binocular distance measurement method.The system accurately measures the distance between the truck and nearby pedestrians by utilizing multiple cameras and PP Human recognition,providing real-time safety alerts.The experimental results show that this method significantly reduces distance measurement errors,improves the reliability of pedestrian detection,achieves high accuracy and real-time performance,and thus enhances the safety of trucks in complex traffic environments.

关 键 词：Security alarm Feature recognition Human distance measurement PP-human attribute identification 

分 类 号：U49[交通运输工程—交通运输规划与管理]