现代电子技术2026，Vol.49Issue(11)：177-184,8.
基于航拍数据的异质车流跟驰模型参数辨识与特征分析
Parameter identification and characterization analysis of heterogeneous traffic following model based on aerial data
摘要
Abstract
This study uses the characteristics of high precision and wide range of UAV aerial photography technology to acquire high-precision video data of vehicle following behavior in urban traffic flow,which aims to gain a deeper understanding of the influence of multiple factors on the characteristics of vehicle following behavior by identifying the parameters of the microscopic following model.The study collects traffic data under different road conditions in Xi'an,and adopts advanced computer vision algorithms SIFT and YOLOv5+DeepSort to realize automatic identification and trajectory tracking of different types of vehicles.Use the extracted tracking data to identify the parameters of the full velocity difference(FVD)model,and correlate the identified parameter values with vehicle models and traffic states,so as to quantitatively analyze the effects of these factors on drivers′ traffic following behaviors.The results of the study reveal that there are significant differences in the parameters of the following model across vehicle models and road conditions,which implies the adaptive adjustment of drivers′behavior strategies in the case of different traffic flows and vehicle types.This study provides new perspectives and methods for understanding and modeling human-vehicle interaction behavior in complex traffic environments on the parameter level.关键词
无人机航拍/跟驰模型/参数辨识/异质车流/SIFT/YOLOv5+DeepSortKey words
UAV aerial photography/traffic following model/parameter identification/heterogeneous traffic flow/SIFT/YOLOv5+DeepSort分类
信息技术与安全科学引用本文复制引用
谢乐坤,赵栓峰,胡腾浩,王茂权..基于航拍数据的异质车流跟驰模型参数辨识与特征分析[J].现代电子技术,2026,49(11):177-184,8.基金项目
秦创原"科学家+工程师"队伍建设项目(2023KXJ-249) （2023KXJ-249）
陕西省重点研发计划项目(2020ZDLGY04-06) （2020ZDLGY04-06）
