Journal of Intelligent Transportation Systems最新文献_第2页

LiDAR-camera fusion: dual-scale correction for vehicle multi-object detection and trajectory extraction 激光雷达-相机融合：车辆多目标检测和轨迹提取的双尺度校正

IF 2.8 3区工程技术 Q3 TRANSPORTATION

Journal of Intelligent Transportation Systems

Pub Date : 2026-01-02 Epub Date: 2024-10-11 DOI: 10.1080/15472450.2024.2416164

Ting Fu , Shuke Xie , Weichao Hu , Junhua Wang , Zixuan Cui

The different principles of sensor technology determine their distinct performance in vehicle detection and microscopic tracking. Vision-based sensors can provide rich semantic information but lack reliable spatial information, and their reliability is reduced in complex lighting conditions. On the other hand, LiDAR can offer high-precision spatial information independent of lighting conditions, but it suffers from low resolution and effective sampling rate limitations. Considering the strong complementarity between images and point clouds, efficient object detection can be achieved by leveraging their synergy. However, existing research has not fully explored the correlation between the features of these two types of data. This paper proposes a novel dual-scale correction strategy for feature-level fusion of camera and LiDAR data. This strategy captures spatial features of point clouds and semantic features of images at both global and local scales and establishes mapping relationships separately. The global correction results are iteratively updated based on the results of local precision correction. To validate the effectiveness of the proposed method, data is collected from highway and urban expressway scenarios. The results indicate improvements in both object detection and microscopic trajectory tracking performance compared to using single sensors alone. Furthermore, the fusion approach outperforms other methods in terms of detection accuracy and processing time. This research offers a method for real-time and accurate extraction of vehicle trajectories using roadside cameras and LiDAR devices, with potential applications in real-time trajectory tracking and traffic management.

传感器技术的不同原理决定了它们在车辆检测和微观跟踪方面的不同性能。基于视觉的传感器可以提供丰富的语义信息，但缺乏可靠的空间信息，在复杂的光照条件下降低了传感器的可靠性。另一方面，激光雷达可以提供不受光照条件影响的高精度空间信息，但它受到低分辨率和有效采样率的限制。考虑到图像和点云之间很强的互补性，利用它们的协同作用可以实现高效的目标检测。然而，现有的研究并没有充分探讨这两类数据特征之间的相关性。提出了一种新的双尺度校正策略，用于相机和激光雷达数据的特征级融合。该策略在全局和局部尺度上捕捉点云的空间特征和图像的语义特征，分别建立映射关系。在局部精度校正结果的基础上迭代更新全局校正结果。为了验证该方法的有效性，我们从高速公路和城市高速公路场景中收集了数据。结果表明，与单独使用单个传感器相比，在目标检测和微观轨迹跟踪性能方面都有改进。此外，融合方法在检测精度和处理时间方面优于其他方法。该研究提供了一种利用路边摄像头和激光雷达设备实时准确提取车辆轨迹的方法，在实时轨迹跟踪和交通管理中具有潜在的应用前景。

{"title":"LiDAR-camera fusion: dual-scale correction for vehicle multi-object detection and trajectory extraction","authors":"Ting Fu , Shuke Xie , Weichao Hu , Junhua Wang , Zixuan Cui","doi":"10.1080/15472450.2024.2416164","DOIUrl":"10.1080/15472450.2024.2416164","url":null,"abstract":"<div><div>The different principles of sensor technology determine their distinct performance in vehicle detection and microscopic tracking. Vision-based sensors can provide rich semantic information but lack reliable spatial information, and their reliability is reduced in complex lighting conditions. On the other hand, LiDAR can offer high-precision spatial information independent of lighting conditions, but it suffers from low resolution and effective sampling rate limitations. Considering the strong complementarity between images and point clouds, efficient object detection can be achieved by leveraging their synergy. However, existing research has not fully explored the correlation between the features of these two types of data. This paper proposes a novel dual-scale correction strategy for feature-level fusion of camera and LiDAR data. This strategy captures spatial features of point clouds and semantic features of images at both global and local scales and establishes mapping relationships separately. The global correction results are iteratively updated based on the results of local precision correction. To validate the effectiveness of the proposed method, data is collected from highway and urban expressway scenarios. The results indicate improvements in both object detection and microscopic trajectory tracking performance compared to using single sensors alone. Furthermore, the fusion approach outperforms other methods in terms of detection accuracy and processing time. This research offers a method for real-time and accurate extraction of vehicle trajectories using roadside cameras and LiDAR devices, with potential applications in real-time trajectory tracking and traffic management.</div></div>","PeriodicalId":54792,"journal":{"name":"Journal of Intelligent Transportation Systems","volume":"30 1","pages":"Pages 55-68"},"PeriodicalIF":2.8,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147855400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A traffic incident detection method of highway based on spatial-temporal characteristics 基于时空特征的高速公路交通事件检测方法

IF 2.8 3区工程技术 Q3 TRANSPORTATION

Journal of Intelligent Transportation Systems

Pub Date : 2026-01-02 Epub Date: 2024-10-16 DOI: 10.1080/15472450.2024.2416532

Jiali Peng , Wei Shangguan , Cong Peng , Linguo Chai , Rui Luo

In this study, we propose a method for detecting traffic incidents by leveraging tensor decomposition in conjunction with spatial-temporal constraints. The method comprises three main stages. Firstly, we develop an initialization and noise reduction procedure for the traffic data pre-processing model, which includes Tucker decomposition and truncating higher-order Singular Value Decomposition (SVD). Subsequently, we construct spatial and temporal coefficient matrices based on the Pearson test and introduce a Laplace penalty term to quantify the disparity between predicted and actual data. Next, we validate the method using traffic loop detector data and incident records from I90 in Seattle, USA, in 2015, comparing its performance with seven other traffic prediction methods. The results demonstrate the superior prediction accuracy, correct detection rate, and low false alarm rate of our traffic incident detection method. Specifically, the mean square error of speed prediction is

5.22 km / h,

the average relative error is

6.88 %,

and the detection rate reaches

98.92 % .

Our method effectively evaluates the spatial-temporal characteristics of traffic data, enabling accurate prediction and detection of traffic incidents. Its technical applicability holds promise for enhancing the capacity and efficiency of future traffic control systems.

在本研究中，我们提出了一种利用张量分解与时空约束相结合来检测交通事件的方法。该方法包括三个主要阶段。首先，我们开发了一种交通数据预处理模型的初始化和降噪过程，其中包括塔克分解和截断高阶奇异值分解（SVD）。随后，我们在Pearson检验的基础上构建时空系数矩阵，并引入拉普拉斯惩罚项来量化预测数据与实际数据之间的差异。接下来，我们使用交通环路检测器数据和2015年美国西雅图I90的事故记录来验证该方法，并将其与其他7种交通预测方法的性能进行比较。结果表明，本文提出的交通事件检测方法具有较高的预测精度、正确的检测率和较低的虚警率。具体而言，速度预测的均方误差为5.22km/h，平均相对误差为6.88%，检出率达到98.92%。我们的方法有效地评估了交通数据的时空特征，使交通事件的准确预测和检测成为可能。其技术适用性为提高未来交通控制系统的能力和效率带来了希望。

{"title":"A traffic incident detection method of highway based on spatial-temporal characteristics","authors":"Jiali Peng , Wei Shangguan , Cong Peng , Linguo Chai , Rui Luo","doi":"10.1080/15472450.2024.2416532","DOIUrl":"10.1080/15472450.2024.2416532","url":null,"abstract":"<div><div>In this study, we propose a method for detecting traffic incidents by leveraging tensor decomposition in conjunction with spatial-temporal constraints. The method comprises three main stages. Firstly, we develop an initialization and noise reduction procedure for the traffic data pre-processing model, which includes Tucker decomposition and truncating higher-order Singular Value Decomposition (SVD). Subsequently, we construct spatial and temporal coefficient matrices based on the Pearson test and introduce a Laplace penalty term to quantify the disparity between predicted and actual data. Next, we validate the method using traffic loop detector data and incident records from I90 in Seattle, USA, in 2015, comparing its performance with seven other traffic prediction methods. The results demonstrate the superior prediction accuracy, correct detection rate, and low false alarm rate of our traffic incident detection method. Specifically, the mean square error of speed prediction is <span><math><mrow><mn>5.22</mn><mtext>km</mtext><mo>/</mo><mi>h</mi></mrow><mo>,</mo></math></span> the average relative error is <span><math><mrow><mn>6.88</mn><mi>%</mi></mrow><mo>,</mo></math></span> and the detection rate reaches <span><math><mrow><mn>98.92</mn><mi>%</mi></mrow><mo>.</mo></math></span> Our method effectively evaluates the spatial-temporal characteristics of traffic data, enabling accurate prediction and detection of traffic incidents. Its technical applicability holds promise for enhancing the capacity and efficiency of future traffic control systems.</div></div>","PeriodicalId":54792,"journal":{"name":"Journal of Intelligent Transportation Systems","volume":"30 1","pages":"Pages 92-107"},"PeriodicalIF":2.8,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147855402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Scene adaptation in adverse conditions: a multi-sensor fusion framework for roadside traffic perception 不利条件下的场景适应：用于路边交通感知的多传感器融合框架

IF 2.8 3区工程技术 Q3 TRANSPORTATION

Journal of Intelligent Transportation Systems

Pub Date : 2025-11-02 Epub Date: 2024-08-12 DOI: 10.1080/15472450.2024.2390844

Kong Li , Zhe Dai , Chen Zuo , Xuan Wang , Hua Cui , Huansheng Song , Mengying Cui

Robust roadside traffic perception requires integrating the strengths of multi-source sensors under various adverse conditions, which is challenging but indispensable for formulating effective traffic management strategies. One limitation of existing radar-camera perception systems is that they focus on integrating multi-source information without directly considering scene information, leading to difficulties in achieving scene adaptive fusion. How to establish the connection between scene information and multi-source information is the key challenge to solving this problem. In this article, we propose a Scene adaptive Sensor Fusion (SSF) framework that characterizes scene information and integrates it into radar-camera fusion schemes, aiming to achieve high-quality roadside traffic perception. Specifically, we introduce a multi-source object association method that accurately associates multi-source sensor information on the roadside. We then utilize coding techniques to characterize the scene information, including visibility characterization regarding lighting and weather conditions, and road characterization regarding sensor viewpoint. By incorporating sensor and scene information into the fusion model, the SSF framework effectively establishes the connection between them. We evaluate the SSF framework on the Roadside Radar and Video Dataset (RRVD) and the Traffic flow Parameter Estimation Dataset (TPED), both collected from real-world traffic scenarios. Experiments demonstrate that SSF significantly improves vehicle detection accuracy under various adverse conditions compared to traditional single-source sensing methods and other state-of-the-art fusion techniques. Furthermore, vehicle trajectories based on SSF detection results enable accurate traffic parameter estimation, such as volume, speed, and density, in complex and dynamic environments.

强大的路边交通感知需要在各种不利条件下整合多源传感器的优势，这虽然具有挑战性，但对于制定有效的交通管理方案却不可或缺。

{"title":"Scene adaptation in adverse conditions: a multi-sensor fusion framework for roadside traffic perception","authors":"Kong Li , Zhe Dai , Chen Zuo , Xuan Wang , Hua Cui , Huansheng Song , Mengying Cui","doi":"10.1080/15472450.2024.2390844","DOIUrl":"10.1080/15472450.2024.2390844","url":null,"abstract":"<div><div>Robust roadside traffic perception requires integrating the strengths of multi-source sensors under various adverse conditions, which is challenging but indispensable for formulating effective traffic management strategies. One limitation of existing radar-camera perception systems is that they focus on integrating multi-source information without directly considering scene information, leading to difficulties in achieving scene adaptive fusion. How to establish the connection between scene information and multi-source information is the key challenge to solving this problem. In this article, we propose a Scene adaptive Sensor Fusion (SSF) framework that characterizes scene information and integrates it into radar-camera fusion schemes, aiming to achieve high-quality roadside traffic perception. Specifically, we introduce a multi-source object association method that accurately associates multi-source sensor information on the roadside. We then utilize coding techniques to characterize the scene information, including visibility characterization regarding lighting and weather conditions, and road characterization regarding sensor viewpoint. By incorporating sensor and scene information into the fusion model, the SSF framework effectively establishes the connection between them. We evaluate the SSF framework on the Roadside Radar and Video Dataset (RRVD) and the Traffic flow Parameter Estimation Dataset (TPED), both collected from real-world traffic scenarios. Experiments demonstrate that SSF significantly improves vehicle detection accuracy under various adverse conditions compared to traditional single-source sensing methods and other state-of-the-art fusion techniques. Furthermore, vehicle trajectories based on SSF detection results enable accurate traffic parameter estimation, such as volume, speed, and density, in complex and dynamic environments.</div></div>","PeriodicalId":54792,"journal":{"name":"Journal of Intelligent Transportation Systems","volume":"29 6","pages":"Pages 698-718"},"PeriodicalIF":2.8,"publicationDate":"2025-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142179723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Transfer learning for cross-modal demand prediction of bike-share and public transit 共享单车和公共交通跨模式需求预测的迁移学习

IF 2.8 3区工程技术 Q3 TRANSPORTATION

Journal of Intelligent Transportation Systems

Pub Date : 2025-11-02 Epub Date: 2024-06-24 DOI: 10.1080/15472450.2024.2371913

Mingzhuang Hua , Francisco Camara Pereira , Yu Jiang , Xuewu Chen , Junyi Chen

The urban transportation system is a combination of multiple transport modes, and the interdependencies across those modes exist. This means that the travel demand across different travel modes could be correlated as one mode may receive/create demand from/for another mode, not to mention natural correlations between different demand time series due to general demand flow patterns across the network. It is expected that cross-modal ripple effects will become more prevalent with Mobility as a Service. Therefore, by propagating demand data across modes, a better demand prediction could be obtained. To this end, this study explores various transfer learning strategies and machine learning models for cross-modal demand prediction. The trip data of bike-share, metro, and taxi are processed as the station-level passenger flows, and then the proposed prediction method is tested in the large-scale case studies of Nanjing and Chicago. The results suggest that prediction models with transfer learning perform better than unimodal prediction models. Fine-tuning without freezing strategy performs the best among all transfer learning strategies, and the split-brain strategy can handle the data missing problem. Furthermore, the 3-layer stacked Long Short-Term Memory model performs particularly well in cross-modal demand prediction. These results verify our deep transfer learning method’s forecasting improvement over existing benchmarks and demonstrate the good transferability for cross-modal demand prediction in multiple cities.

城市交通系统是多种交通方式的组合，这些交通方式之间存在相互依存关系。这就意味着，不同交通方式之间的出行需求可能...

{"title":"Transfer learning for cross-modal demand prediction of bike-share and public transit","authors":"Mingzhuang Hua , Francisco Camara Pereira , Yu Jiang , Xuewu Chen , Junyi Chen","doi":"10.1080/15472450.2024.2371913","DOIUrl":"10.1080/15472450.2024.2371913","url":null,"abstract":"<div><div>The urban transportation system is a combination of multiple transport modes, and the interdependencies across those modes exist. This means that the travel demand across different travel modes could be correlated as one mode may receive/create demand from/for another mode, not to mention natural correlations between different demand time series due to general demand flow patterns across the network. It is expected that cross-modal ripple effects will become more prevalent with Mobility as a Service. Therefore, by propagating demand data across modes, a better demand prediction could be obtained. To this end, this study explores various transfer learning strategies and machine learning models for cross-modal demand prediction. The trip data of bike-share, metro, and taxi are processed as the station-level passenger flows, and then the proposed prediction method is tested in the large-scale case studies of Nanjing and Chicago. The results suggest that prediction models with transfer learning perform better than unimodal prediction models. Fine-tuning without freezing strategy performs the best among all transfer learning strategies, and the split-brain strategy can handle the data missing problem. Furthermore, the 3-layer stacked Long Short-Term Memory model performs particularly well in cross-modal demand prediction. These results verify our deep transfer learning method’s forecasting improvement over existing benchmarks and demonstrate the good transferability for cross-modal demand prediction in multiple cities.</div></div>","PeriodicalId":54792,"journal":{"name":"Journal of Intelligent Transportation Systems","volume":"29 6","pages":"Pages 640-653"},"PeriodicalIF":2.8,"publicationDate":"2025-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141613115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A reinforcement learning based autonomous vehicle control in diverse daytime and weather scenarios 基于强化学习的自主车辆控制，适用于不同的白天和天气情况

IF 2.8 3区工程技术 Q3 TRANSPORTATION

Journal of Intelligent Transportation Systems

Pub Date : 2025-11-02 Epub Date: 2024-06-21 DOI: 10.1080/15472450.2024.2370010

Badr Ben Elallid , Miloud Bagaa , Nabil Benamar , Nabil Mrani

Autonomous driving holds significant promise for substantially reducing road fatalities. Unlike traditional machine learning methods that have conventionally been applied to enhance the motion control of Autonomous Vehicles (AVs), recent attention has shifted toward the utilization of Deep Learning (DL) and Deep Reinforcement Learning (DRL) techniques. These advanced approaches have the potential to greatly improve AV vehicle control and empower vehicles to learn from their surroundings. However, the majority of existing research has concentrated on straightforward scenarios, often neglecting the intricate challenges posed by vulnerable road users such as pedestrians, cyclists, and motorcyclists, as well as the influence of varying weather conditions. In this study, we propose a novel model founded on DRL, specifically leveraging Deep-Q Networks (DQN), to effectively manage AVs in complex scenarios characterized by heavy traffic, diverse road users, and diverse weather conditions. Our approach involves training the model in diverse weather conditions, encompassing clear daytime and nighttime as well as challenging weather conditions like heavy rainfall during both the day and sunset. Through this comprehensive training, the AV becomes proficient in navigating safely through intersections and reaching its destination without any accidents. To rigorously evaluate and validate our proposed approach, extensive testing was conducted employing the CARLA simulator. The simulation results unequivocally demonstrate that our model not only reduces travel delays but also minimizes the occurrence of collisions, marking a significant step forward in achieving safer and more efficient autonomous driving.

自动驾驶有望大幅降低道路死亡率。与传统的机器学习方法不同的是，机器学习方法通常被用于增强运动控制。

{"title":"A reinforcement learning based autonomous vehicle control in diverse daytime and weather scenarios","authors":"Badr Ben Elallid , Miloud Bagaa , Nabil Benamar , Nabil Mrani","doi":"10.1080/15472450.2024.2370010","DOIUrl":"10.1080/15472450.2024.2370010","url":null,"abstract":"<div><div>Autonomous driving holds significant promise for substantially reducing road fatalities. Unlike traditional machine learning methods that have conventionally been applied to enhance the motion control of Autonomous Vehicles (AVs), recent attention has shifted toward the utilization of Deep Learning (DL) and Deep Reinforcement Learning (DRL) techniques. These advanced approaches have the potential to greatly improve AV vehicle control and empower vehicles to learn from their surroundings. However, the majority of existing research has concentrated on straightforward scenarios, often neglecting the intricate challenges posed by vulnerable road users such as pedestrians, cyclists, and motorcyclists, as well as the influence of varying weather conditions. In this study, we propose a novel model founded on DRL, specifically leveraging Deep-Q Networks (DQN), to effectively manage AVs in complex scenarios characterized by heavy traffic, diverse road users, and diverse weather conditions. Our approach involves training the model in diverse weather conditions, encompassing clear daytime and nighttime as well as challenging weather conditions like heavy rainfall during both the day and sunset. Through this comprehensive training, the AV becomes proficient in navigating safely through intersections and reaching its destination without any accidents. To rigorously evaluate and validate our proposed approach, extensive testing was conducted employing the CARLA simulator. The simulation results unequivocally demonstrate that our model not only reduces travel delays but also minimizes the occurrence of collisions, marking a significant step forward in achieving safer and more efficient autonomous driving.</div></div>","PeriodicalId":54792,"journal":{"name":"Journal of Intelligent Transportation Systems","volume":"29 6","pages":"Pages 626-639"},"PeriodicalIF":2.8,"publicationDate":"2025-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141737117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Distributed coordinated control of mixed expressway and urban roads: a sensitivity-based approach 混合快速路和城市道路的分布式协调控制：基于敏感性的方法

IF 2.8 3区工程技术 Q3 TRANSPORTATION

Journal of Intelligent Transportation Systems

Pub Date : 2025-11-02 Epub Date: 2024-04-22 DOI: 10.1080/15472450.2024.2345348

Ben Zhai , Bing Wu , Yanli Wang , Bin Ran

The inherent interdependency between mixed expressway and urban road networks calls for an effective coordinated traffic control approach. This study introduces a sensitivity-based distributed method to coordinate ramp metering and traffic signal control. Firstly, the quantitative relationships between network nodes are established through a developed traffic flow model for mixed networks. The network-level sensitivity information is analyzed to assess the influence of controllers on the traffic state. Additionally, a dynamic subproblems decomposition algorithm is proposed, considering the network’s spatial structure and dynamic traffic characteristics. By employing community detection techniques, tightly connected controllers are clustered to enable efficient and adaptive distributed control. The optimization problem is then decomposed into several subproblems, each formulated as a bi-level programming problem within a model predictive control framework. Numerical experiments demonstrate that the proposed strategy enhances the traffic efficiency of mixed networks with a 14.5% reduction in total travel time during peak hours, which shows better performance compared with the other three existing control strategies.

混合高速公路与城市道路网络之间的内在相互依赖性要求一种有效的协调交通控制方法。本文提出了一种基于灵敏度的分布式匝道计量与交通信号控制相协调的方法。首先，通过建立混合网络交通流模型，建立网络节点间的定量关系。分析网络级灵敏度信息，评估控制器对流量状态的影响。此外，考虑网络的空间结构和动态流量特性，提出了一种动态子问题分解算法。通过采用社区检测技术，将紧密连接的控制器聚类，实现高效、自适应的分布式控制。然后将优化问题分解为几个子问题，每个子问题在模型预测控制框架内表述为一个双层规划问题。数值实验表明，该控制策略提高了混合网络的交通效率，高峰时段总行驶时间减少了14.5%，与其他三种控制策略相比表现出更好的性能。

{"title":"Distributed coordinated control of mixed expressway and urban roads: a sensitivity-based approach","authors":"Ben Zhai , Bing Wu , Yanli Wang , Bin Ran","doi":"10.1080/15472450.2024.2345348","DOIUrl":"10.1080/15472450.2024.2345348","url":null,"abstract":"<div><div>The inherent interdependency between mixed expressway and urban road networks calls for an effective coordinated traffic control approach. This study introduces a sensitivity-based distributed method to coordinate ramp metering and traffic signal control. Firstly, the quantitative relationships between network nodes are established through a developed traffic flow model for mixed networks. The network-level sensitivity information is analyzed to assess the influence of controllers on the traffic state. Additionally, a dynamic subproblems decomposition algorithm is proposed, considering the network’s spatial structure and dynamic traffic characteristics. By employing community detection techniques, tightly connected controllers are clustered to enable efficient and adaptive distributed control. The optimization problem is then decomposed into several subproblems, each formulated as a bi-level programming problem within a model predictive control framework. Numerical experiments demonstrate that the proposed strategy enhances the traffic efficiency of mixed networks with a 14.5% reduction in total travel time during peak hours, which shows better performance compared with the other three existing control strategies.</div></div>","PeriodicalId":54792,"journal":{"name":"Journal of Intelligent Transportation Systems","volume":"29 6","pages":"Pages 579-592"},"PeriodicalIF":2.8,"publicationDate":"2025-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141023115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Performance evaluation of path choice set generation algorithms for route choice modelling 用于路径选择建模的路径选择集生成算法性能评估

IF 2.8 3区工程技术 Q3 TRANSPORTATION

Journal of Intelligent Transportation Systems

Pub Date : 2025-11-02 Epub Date: 2024-07-05 DOI: 10.1080/15472450.2024.2373866

Raghav Malhotra , Chintan Advani , Ashish Bhaskar

Traffic assignment and its applications are sensitive to the selection of path choice sets between an OD pair. In literature, different path generation algorithms are proposed, namely, Link Labeling, Link Elimination, Link Penalty, Simulation, and Branch and Bound. The effectiveness of these algorithms hinges on algorithmic principles and input parameters. Consequently, choosing an appropriate algorithm for practical implementation becomes challenging. This paper aims to benchmark these algorithms with a case study using a real vehicle trajectory dataset from four OD pairs from Brisbane, Australia. The paper offers both qualitative and quantitative comparisons of the algorithms. The performance of the algorithms is evaluated based on their authenticity, redundancy, and applicability. The results highlight that the simulation method outperforms the other algorithms, specifically utilizing a truncated normal distribution. The paper offers valuable insights into the selection of path-generation techniques, aiding the enhancement of traffic assignment processes.

流量分配及其应用对OD对间路径选择集的选择非常敏感。在文献中，提出了不同的路径生成算法，即链路标记、链路消除、链路惩罚、仿真和分支定界。这些算法的有效性取决于算法原理和输入参数。因此，为实际实现选择合适的算法变得具有挑战性。本文旨在通过使用来自澳大利亚布里斯班的四个OD对的真实车辆轨迹数据集的案例研究来对这些算法进行基准测试。本文对这些算法进行了定性和定量的比较。根据算法的真实性、冗余性和适用性来评估算法的性能。结果表明，该模拟方法优于其他算法，特别是利用截断正态分布。本文对路径生成技术的选择提供了有价值的见解，有助于改善交通分配过程。

引用次数: 0

A platoon formation algorithm for intersections with blue phase control in mixed traffic 混合交通中采用蓝色相位控制的交叉路口的排队编队算法

IF 2.8 3区工程技术 Q3 TRANSPORTATION

Journal of Intelligent Transportation Systems

Pub Date : 2025-11-02 Epub Date: 2024-05-08 DOI: 10.1080/15472450.2024.2352390

Ruochen Hao , Sa Gao , Xinwei Wang , Wanjing Ma , Bart van Arem , Meng Wang

Increasing attention is being paid to intersection signal control with cooperative platoons. Assuming platoons being formed, such platoons cannot only improve the intersection capacity but also minimize the number of control units, especially when dedicated connected and automated vehicle (CAV) lanes are considered. However, the platoon formation process is often neglected, especially for lane-changing and overtaking maneuvers in mixed traffic. This may jeopardize the potential of signal control with platoons. This article proposes a platoon formation algorithm that computes the optimal lane, platoon sequence, and speed profiles of CAVs under the requirement of the central traffic controller. The algorithm is designed for mixed traffic conditions and hence the performance of human-driven vehicles is also considered. A mixed integer linear program model is formulated to minimize the deviation from the desired platoon configuration and the disturbance to overall traffic under any arbitrary initial condition. Numerical experiments are designed to test the effectiveness and the computational performance of the proposed algorithm. Results show that CAVs with signal control can form platoons with rational motion. Besides, the platoon penetration significantly affects platooning feasibility, while the platoon length does not. This suggests that CAVs can form long platoons at intersections to improve traffic throughput.

基于协同排的交叉口信号控制越来越受到人们的重视。假设形成队列，这样的队列不仅可以提高交叉口的通行能力，而且可以最大限度地减少控制单元的数量，特别是当考虑专用的连接和自动车辆（CAV）车道时。然而，队列的形成过程往往被忽视，特别是在混合交通条件下的变道和超车机动。这可能会危及队列信号控制的潜力。本文提出了一种排队形算法，在中央交通控制器的要求下，计算自动驾驶汽车的最优车道、排队形和速度曲线。该算法是针对混合交通条件设计的，因此也考虑了人工驾驶车辆的性能。建立了一个混合整数线性规划模型，在任意初始条件下，使与期望队列配置的偏差和对总体交通的干扰最小。通过数值实验验证了该算法的有效性和计算性能。结果表明，采用信号控制的自动驾驶汽车可以合理地组队。此外，分队侵彻对分队的可行性有显著影响，而分队长度对分队的可行性无显著影响。这表明自动驾驶汽车可以在十字路口形成长队列以提高交通吞吐量。

{"title":"A platoon formation algorithm for intersections with blue phase control in mixed traffic","authors":"Ruochen Hao , Sa Gao , Xinwei Wang , Wanjing Ma , Bart van Arem , Meng Wang","doi":"10.1080/15472450.2024.2352390","DOIUrl":"10.1080/15472450.2024.2352390","url":null,"abstract":"<div><div>Increasing attention is being paid to intersection signal control with cooperative platoons. Assuming platoons being formed, such platoons cannot only improve the intersection capacity but also minimize the number of control units, especially when dedicated connected and automated vehicle (CAV) lanes are considered. However, the platoon formation process is often neglected, especially for lane-changing and overtaking maneuvers in mixed traffic. This may jeopardize the potential of signal control with platoons. This article proposes a platoon formation algorithm that computes the optimal lane, platoon sequence, and speed profiles of CAVs under the requirement of the central traffic controller. The algorithm is designed for mixed traffic conditions and hence the performance of human-driven vehicles is also considered. A mixed integer linear program model is formulated to minimize the deviation from the desired platoon configuration and the disturbance to overall traffic under any arbitrary initial condition. Numerical experiments are designed to test the effectiveness and the computational performance of the proposed algorithm. Results show that CAVs with signal control can form platoons with rational motion. Besides, the platoon penetration significantly affects platooning feasibility, while the platoon length does not. This suggests that CAVs can form long platoons at intersections to improve traffic throughput.</div></div>","PeriodicalId":54792,"journal":{"name":"Journal of Intelligent Transportation Systems","volume":"29 6","pages":"Pages 593-611"},"PeriodicalIF":2.8,"publicationDate":"2025-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141367146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

One-stage estimation of cyclic arrival rates using license plate recognition data 基于车牌识别数据的循环到达率单阶段估计

IF 2.8 3区工程技术 Q3 TRANSPORTATION

Journal of Intelligent Transportation Systems

Pub Date : 2025-11-02 Epub Date: 2024-08-14 DOI: 10.1080/15472450.2024.2392720

Chengchuan An , Yang He , Jiawei Lu , Zhenbo Lu , Jingxin Xia

Traffic arrival on urban roads usually reveals time-varying rates due to the effects of signal control, motivating us to investigate the distribution of arrival rates within the signal cycle. However, such information is not readily available as only a portion of arrival traffic can be observed in the field. Previous studies have utilized different data sources and proposed probability-based models to solve the estimation problem. However, these studies rely heavily on the assumption that the observed vehicles are evenly distributed in the arrival traffic flow and exact signal timings are known. This study uses license plate recognition (LPR) data collected at adjacent signalized intersections to estimate cyclic arrival rates in a historical period. A probability-based model is formulated by parameterizing the vehicle arrival distribution as a mixture of circular distributions. This facilitates us to describe similar traffic arrival patterns over different signal cycles and capture multiple arrival platoons from different signal phases within the signal cycle. The proposed model is validated in a field experiment with different arrival patterns and traffic conditions. Model performance under both full and partial monitoring of LPR sensors at the upstream intersection is analyzed. The robustness of the proposed model with unevenly sampled observations in arrival traffic flow is also investigated.

由于信号控制的影响，城市道路上的交通到达率通常呈现时变速率，这促使我们研究信号周期内到达率的分布。但是，这种资料并不容易获得，因为只能在现场观察到一部分到达的交通。以往的研究利用不同的数据源，并提出了基于概率的模型来解决估计问题。然而，这些研究在很大程度上依赖于假设观察到的车辆均匀分布在到达交通流中，并且确切的信号时间是已知的。本研究使用车牌识别（LPR）数据收集在邻近的信号交叉口估计循环到达率在一个历史时期。通过将车辆到达分布参数化为圆形分布的混合，建立了基于概率的模型。这有助于我们在不同的信号周期中描述相似的交通到达模式，并在信号周期内从不同的信号阶段捕获多个到达队列。在不同到达方式和交通条件下的现场试验中验证了该模型的有效性。分析了上游交叉口LPR传感器完全监测和部分监测下的模型性能。本文还研究了非均匀采样条件下模型的鲁棒性。

{"title":"One-stage estimation of cyclic arrival rates using license plate recognition data","authors":"Chengchuan An , Yang He , Jiawei Lu , Zhenbo Lu , Jingxin Xia","doi":"10.1080/15472450.2024.2392720","DOIUrl":"10.1080/15472450.2024.2392720","url":null,"abstract":"<div><div>Traffic arrival on urban roads usually reveals time-varying rates due to the effects of signal control, motivating us to investigate the distribution of arrival rates within the signal cycle. However, such information is not readily available as only a portion of arrival traffic can be observed in the field. Previous studies have utilized different data sources and proposed probability-based models to solve the estimation problem. However, these studies rely heavily on the assumption that the observed vehicles are evenly distributed in the arrival traffic flow and exact signal timings are known. This study uses license plate recognition (LPR) data collected at adjacent signalized intersections to estimate cyclic arrival rates in a historical period. A probability-based model is formulated by parameterizing the vehicle arrival distribution as a mixture of circular distributions. This facilitates us to describe similar traffic arrival patterns over different signal cycles and capture multiple arrival platoons from different signal phases within the signal cycle. The proposed model is validated in a field experiment with different arrival patterns and traffic conditions. Model performance under both full and partial monitoring of LPR sensors at the upstream intersection is analyzed. The robustness of the proposed model with unevenly sampled observations in arrival traffic flow is also investigated.</div></div>","PeriodicalId":54792,"journal":{"name":"Journal of Intelligent Transportation Systems","volume":"29 6","pages":"Pages 719-732"},"PeriodicalIF":2.8,"publicationDate":"2025-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145475639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating vehicle trajectory planning and arterial traffic management to facilitate eco-approach and departure deployment 整合车辆轨迹规划和干道交通管理，促进生态进场和离场部署

IF 2.8 3区工程技术 Q3 TRANSPORTATION

Journal of Intelligent Transportation Systems

Pub Date : 2025-11-02 Epub Date: 2024-06-17 DOI: 10.1080/15472450.2024.2369988

Hao Liu , Alex A. Kurzhanskiy , Wanshi Hong , Xiao-Yun Lu

Eco-approach and departure (EAD) enable continuous vehicle motion in urban signalized corridors. Since such a motion can extend to the EAD vehicles’ followers, it makes EAD a promising technology to benefit the traffic flow where automated vehicles and conventional vehicles coexist. Most existing EAD studies envision an ideal setting that neglects real-world operational conditions such as lane changes, multi-movement intersection configuration, partially automated fleet, and/or limited traffic state awareness. This study aims to fill the gap by designing an EAD algorithm considering real-world traffic operation constraints. The proposed algorithm uses a model predictive controller to minimize vehicle speed reduction and variation based on the real-time traffic signal control plan and measured queues at the intersection. The required inputs are readily available at many modern intersections. We observed that the proposed controller’s performance might degrade because of lane-changing maneuvers and lead-left turn traffic signals. These observations motivated our development of a lane change management strategy and a signal control implementation strategy to facilitate the EAD implementation. The lane change management strategies separate the EAD operations and lane-changing maneuvers in time and space. The signal control implementation strategy applies lag-left turn signals to enable EAD operation for both the through and left-turn vehicles. Compared to the non-EAD case, our EAD approach produces 2.5% to 7.8% energy savings while keeping similar intersection mobility. Notably, this approach brings about 2.5% to 3.6% energy savings in a 2% CAV case. This result demonstrates the feasibility of deploying EAD at low connected automated vehicle penetration rates.

生态进站和离站（EAD）可使车辆在城市信号灯通道内连续行驶。由于这种运动可以延伸到 EAD 车辆的尾随者，因此 EAD 是一项很有前途的技术。

{"title":"Integrating vehicle trajectory planning and arterial traffic management to facilitate eco-approach and departure deployment","authors":"Hao Liu , Alex A. Kurzhanskiy , Wanshi Hong , Xiao-Yun Lu","doi":"10.1080/15472450.2024.2369988","DOIUrl":"10.1080/15472450.2024.2369988","url":null,"abstract":"<div><div>Eco-approach and departure (EAD) enable continuous vehicle motion in urban signalized corridors. Since such a motion can extend to the EAD vehicles’ followers, it makes EAD a promising technology to benefit the traffic flow where automated vehicles and conventional vehicles coexist. Most existing EAD studies envision an ideal setting that neglects real-world operational conditions such as lane changes, multi-movement intersection configuration, partially automated fleet, and/or limited traffic state awareness. This study aims to fill the gap by designing an EAD algorithm considering real-world traffic operation constraints. The proposed algorithm uses a model predictive controller to minimize vehicle speed reduction and variation based on the real-time traffic signal control plan and measured queues at the intersection. The required inputs are readily available at many modern intersections. We observed that the proposed controller’s performance might degrade because of lane-changing maneuvers and lead-left turn traffic signals. These observations motivated our development of a lane change management strategy and a signal control implementation strategy to facilitate the EAD implementation. The lane change management strategies separate the EAD operations and lane-changing maneuvers in time and space. The signal control implementation strategy applies lag-left turn signals to enable EAD operation for both the through and left-turn vehicles. Compared to the non-EAD case, our EAD approach produces 2.5% to 7.8% energy savings while keeping similar intersection mobility. Notably, this approach brings about 2.5% to 3.6% energy savings in a 2% CAV case. This result demonstrates the feasibility of deploying EAD at low connected automated vehicle penetration rates.</div></div>","PeriodicalId":54792,"journal":{"name":"Journal of Intelligent Transportation Systems","volume":"29 6","pages":"Pages 612-625"},"PeriodicalIF":2.8,"publicationDate":"2025-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141511945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0