Developing and validating an adaptive multi-layer vehicle trajectory reconstruction method for outlier removal

IF 7.6 1区 工程技术 Q1 TRANSPORTATION SCIENCE & TECHNOLOGY
Ruijie Li , Zuduo Zheng , Dong Ngoduy , Linbo Li
{"title":"Developing and validating an adaptive multi-layer vehicle trajectory reconstruction method for outlier removal","authors":"Ruijie Li ,&nbsp;Zuduo Zheng ,&nbsp;Dong Ngoduy ,&nbsp;Linbo Li","doi":"10.1016/j.trc.2024.104946","DOIUrl":null,"url":null,"abstract":"<div><div>Trajectory data is vital for traffic flow studies, and aerial photography-based methods are increasingly used to collect such data. However, these datasets often contain errors from various sources, which can be exacerbated by numerical derivative processes. Previous efforts have not fully addressed some of these issues such as consistency, varying length of outlier sequences, and unknown ground truth trends. Moreover, existing validation methods are often indirect and problematic. To address these limitations, we propose an adaptive multi-layer vehicle trajectory reconstruction method, which consists of three modules: the Initial Window Arrangement module to ensure the precise alignment between the reconstruction window and detected outlier fragments, maintaining internal consistency at boundary points; the Window Size Feasibility Test module to adaptively determine the window size according to varying length of outlier sequences, and XGBoost-based Ground Truth Estimation module to be combined with a least-square-based objective function to significantly improve reconstruction accuracy and more closely replicate the underlying trend. Additionally, we introduce the jerk-based reconstruction, which outperforms the acceleration-based reconstruction. To reliably assess and select the best ground truth estimation scheme and objective function, a novel synthetic dataset containing both the ground truth and realistic outlier fragments is proposed. Subsequently, a comparative evaluation of six different outlier removal methods was conducted using Zen Traffic Data. The validation results, utilizing both the synthetic dataset and Zen Traffic Data, demonstrate the exceptional performance of the proposed method across various evaluation perspectives. The good performance of the proposed outlier removal method is further demonstrated by comparing the IDM calibration results using the trajectories with and without outliers being removed. With just one parameter (jerk anomaly threshold), the parameter settings of our method are more objective and generalizable.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 104946"},"PeriodicalIF":7.6000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transportation Research Part C-Emerging Technologies","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0968090X24004674","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"TRANSPORTATION SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Trajectory data is vital for traffic flow studies, and aerial photography-based methods are increasingly used to collect such data. However, these datasets often contain errors from various sources, which can be exacerbated by numerical derivative processes. Previous efforts have not fully addressed some of these issues such as consistency, varying length of outlier sequences, and unknown ground truth trends. Moreover, existing validation methods are often indirect and problematic. To address these limitations, we propose an adaptive multi-layer vehicle trajectory reconstruction method, which consists of three modules: the Initial Window Arrangement module to ensure the precise alignment between the reconstruction window and detected outlier fragments, maintaining internal consistency at boundary points; the Window Size Feasibility Test module to adaptively determine the window size according to varying length of outlier sequences, and XGBoost-based Ground Truth Estimation module to be combined with a least-square-based objective function to significantly improve reconstruction accuracy and more closely replicate the underlying trend. Additionally, we introduce the jerk-based reconstruction, which outperforms the acceleration-based reconstruction. To reliably assess and select the best ground truth estimation scheme and objective function, a novel synthetic dataset containing both the ground truth and realistic outlier fragments is proposed. Subsequently, a comparative evaluation of six different outlier removal methods was conducted using Zen Traffic Data. The validation results, utilizing both the synthetic dataset and Zen Traffic Data, demonstrate the exceptional performance of the proposed method across various evaluation perspectives. The good performance of the proposed outlier removal method is further demonstrated by comparing the IDM calibration results using the trajectories with and without outliers being removed. With just one parameter (jerk anomaly threshold), the parameter settings of our method are more objective and generalizable.
开发并验证了一种自适应多层车辆轨迹重建方法的异常值去除
轨迹数据对交通流研究至关重要,基于航空摄影的方法越来越多地用于收集此类数据。然而,这些数据集通常包含来自各种来源的误差,这些误差可能会因数值导数过程而加剧。以前的努力并没有完全解决其中的一些问题,如一致性、异常序列的长度变化和未知的基础真值趋势。此外,现有的验证方法往往是间接的和有问题的。针对这些局限性,提出了一种自适应多层车辆轨迹重建方法,该方法由三个模块组成:初始窗口排列模块,确保重建窗口与检测到的离群片段之间的精确对齐,保持边界点的内部一致性;基于xgboost的Ground Truth Estimation模块与基于最小二乘的目标函数相结合,显著提高重建精度,更紧密地复制底层趋势。此外,我们还介绍了基于瞬变的重建方法,该方法优于基于加速度的重建方法。为了可靠地评估和选择最佳的地面真值估计方案和目标函数,提出了一种包含地面真值和真实离群片段的合成数据集。随后,使用Zen Traffic Data对六种不同的离群值去除方法进行了比较评估。利用合成数据集和Zen交通数据的验证结果表明,所提出的方法在各种评估角度上都具有卓越的性能。通过比较去除和不去除异常点轨迹的IDM校准结果,进一步证明了该方法的良好性能。仅使用一个参数(跳变异常阈值),该方法的参数设置更加客观和一般化。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
15.80
自引率
12.00%
发文量
332
审稿时长
64 days
期刊介绍: Transportation Research: Part C (TR_C) is dedicated to showcasing high-quality, scholarly research that delves into the development, applications, and implications of transportation systems and emerging technologies. Our focus lies not solely on individual technologies, but rather on their broader implications for the planning, design, operation, control, maintenance, and rehabilitation of transportation systems, services, and components. In essence, the intellectual core of the journal revolves around the transportation aspect rather than the technology itself. We actively encourage the integration of quantitative methods from diverse fields such as operations research, control systems, complex networks, computer science, and artificial intelligence. Join us in exploring the intersection of transportation systems and emerging technologies to drive innovation and progress in the field.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信