IEEE Transactions on Intelligent Transportation Systems最新文献_第6页

Flexible Hyperdisk-Based Support Tensor Machine for Railway Turnout Fault Diagnosis Using Dual-Channel Sound Signals 基于hyperdisk的柔性支撑张量机在铁路道岔故障诊断中的应用

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-01-14 DOI: 10.1109/TITS.2025.3648779

Chen Chen;Meng Mei;Tiange Wang;Zuxi Chen;Haidong Shao

{"title":"Flexible Hyperdisk-Based Support Tensor Machine for Railway Turnout Fault Diagnosis Using Dual-Channel Sound Signals","authors":"Chen Chen;Meng Mei;Tiange Wang;Zuxi Chen;Haidong Shao","doi":"10.1109/TITS.2025.3648779","DOIUrl":"https://doi.org/10.1109/TITS.2025.3648779","url":null,"abstract":"Timely fault diagnosis of railway turnouts is crucial for enhancing maintenance efficiency. Most existing methods rely primarily on distance measures or machine-learning models driven by electrical signals. However, these methods often depend on standardized curves or are limited by poor feature quality and small datasets, which restrict their generalizability and performance. Moreover, electrical signals alone provide limited measurement and physical information, which reduces diagnostic accuracy. To overcome these limitations, a contactless fault diagnosis method for railway turnouts is developed using a support tensor machine combined with dual-channel sound signals. In addition, a novel tensor-based classifier, called the flexible hyperdisk-based support tensor machine (FHD-STM), is proposed to mitigate boundary underestimation and computational burden in existing support tensor learning. The proposed method comprises three primary stages. First, sound monitoring data are collected and processed. Next, fused dual-channel feature tensors are constructed using the continuous wavelet transform and data stacking to capture the spatial characteristics of the sound signal and extract effective features. Finally, an FHD-STM model is built to perform fault diagnosis using these feature tensors. The experimental results indicate superior performance in terms of precision, recall, and F1-score compared to existing approaches, which underscores its utility for reliable railway turnout fault diagnosis.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"13572-13583"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Human-Inspired Graphformer-Tutor: Accelerating and Safeguarding Multi-Agent Driving Learning 启发人类的Graphformer-Tutor：加速和保障多智能体驾驶学习

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-07-22 DOI: 10.1109/TITS.2026.3709675

Fan Guo;Chuyu Ma;Dezong Zhao;Jiayang Wang;Zhengqing Yan;Jinbo Hao;Yun Chen;Lianhui Zhang;Kang Song

{"title":"Human-Inspired Graphformer-Tutor: Accelerating and Safeguarding Multi-Agent Driving Learning","authors":"Fan Guo;Chuyu Ma;Dezong Zhao;Jiayang Wang;Zhengqing Yan;Jinbo Hao;Yun Chen;Lianhui Zhang;Kang Song","doi":"10.1109/TITS.2026.3709675","DOIUrl":"https://doi.org/10.1109/TITS.2026.3709675","url":null,"abstract":"Realistic modeling of interactive behaviors among multiple vehicles is essential for autonomous driving simulation. While Multi-Agent Reinforcement Learning (MARL) provides a promising framework for this task, the pure trial-and-error exploration paradigm often leads to inefficient and biased learning processes, limiting its ability to reproduce realistic driving behaviors. In light of this, inspired by the Tutor–Students learning paradigm and leveraging human expertise, a novel MARL algorithm termed Tutor–Multiple-Students Proximal Policy Optimization (TMSPPO) is proposed. A Graphformer-based tutor agent is developed to capture spatio-temporal driving features from human data and provide anthropomorphic assistance. TMSPPO embeds this tutor agent into the MARL loop through two complementary mechanisms: policy guidance and safety protection. Specifically, the guidance mechanism prevents student agents from cold-starting by integrating seamlessly with exploration, while the safety protection mechanism filters extreme samples yet retains informative near-misses to capture corrective data in near-danger scenarios. To further achieve a principled trade-off between autonomous exploration and tutor dependence, the intervention frequency and intensity are formulated as constrained objectives co-optimized with the learning goal. Consequently, TMSPPO substantially enhances learning efficiency and interactive driving capability, enabling student agents to display diverse and human-like behaviors in complex scenarios.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12342-12355"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 Hybrid Heuristic Approach for Solving the Lock-Channel-Quay Co-Scheduling Problem Considering Water Discharge 考虑水量的船闸-码头协同调度问题的混合启发式求解方法

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-07-13 DOI: 10.1109/TITS.2026.3707563

Shun Liu;Yu Zhang;Lijun He;Wenjing Guo;Xuan Lu;Hao Yu

{"title":"A Hybrid Heuristic Approach for Solving the Lock-Channel-Quay Co-Scheduling Problem Considering Water Discharge","authors":"Shun Liu;Yu Zhang;Lijun He;Wenjing Guo;Xuan Lu;Hao Yu","doi":"10.1109/TITS.2026.3707563","DOIUrl":"https://doi.org/10.1109/TITS.2026.3707563","url":null,"abstract":"The co-scheduling of lock-channel-quay in inland waterways is essential to transportation efficiency, especially when the variation of water discharge during the flood season exists and affects the channel navigation of ships. This paper addresses the lock-channel-quay co-scheduling problem in flood season (LCQCP-F), aiming to minimize the total waiting time of all ships and the extra cost of transshipment. This problem can be viewed as a main problem where a transport mode for the ship is selected by tackling two sub-problems of channel-lock coordination (CLC) and channel-berth matching (CBM). We formulate the LCQCP-F as a mixed integer linear programming model, and a hybrid heuristic approach is designed to solve this model. Specifically, a variable neighborhood search is developed to search for optimal transport mode combinations for the main problem iteratively. In each iteration, a dynamic multi-population particle swarm optimization algorithm with recombined learning and hybrid mutation is developed to solve the CLC sub-problem, and a multi-population genetic algorithm is proposed to solve the CBM sub-problem. Numerical experiments on the Three Gorges Dam, China, show that our method is effective in assisting ships to avoid missing feasible water discharge windows and coordinate multiple navigation resources by slightly altering the departure time of the ships. With the proposed method, the level of transshipment penalty can be optimized, and the influence of water discharge in the flood season is also evaluated quantitatively.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"13412-13428"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Sequential-Agent Game Lane-Changing Model for CAVs Approaching Off-Ramps 自动驾驶汽车驶近匝道的序贯智能体博弈变道模型

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-08-10 DOI: 10.1109/TITS.2026.3705746

Qinglu Ma;Zixuan Li;Shengping Niu;Xinyu Wang;Saleem Ullah

{"title":"Sequential-Agent Game Lane-Changing Model for CAVs Approaching Off-Ramps","authors":"Qinglu Ma;Zixuan Li;Shengping Niu;Xinyu Wang;Saleem Ullah","doi":"10.1109/TITS.2026.3705746","DOIUrl":"https://doi.org/10.1109/TITS.2026.3705746","url":null,"abstract":"To improve the safety and efficiency of Connected and Autonomous Vehicles (CAVs) approaching off-ramps, this study proposes a Sequential-Agent Game Lane-Changing Model (S-GLM), which couples sequential game theory with agent-oriented LSTM-DQN collaborative training under explicit safety constraints. Through a sequential game process, S-GLM extends lane-changing decision-making beyond single-step reasoning toward continuous interaction optimization. Field data were collected from Masangxi Bridge to Dadukou Interchange on Chongqing’s Inner Ring Expressway using autonomous aerial vehicles (AAVs) and fixed cameras. The proposed S-GLM was validated through joint simulation using SUMO, Python, and TraCI. The results show that S-GLM increases the Modified Time to Collision (MTTC) by 9.15% and 14.89% compared with the Pure Reinforcement Learning baseline (PRL-b) and the Mixed-Strategy Game Lane-Changing Model (M-GLM), respectively, while improving the average vehicle speed by 2.09% and 1.72%. Overall, these improvements highlight the significance of S-GLM for research on CAV off-ramp diverging.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12946-12958"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Efficient Mixture-of-Experts for Video-Based Driver State and Physiological Multi-Task Estimation in Conditional Autonomous Driving 基于视频的条件自动驾驶驾驶员状态和生理多任务估计的高效专家组合

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-09-01 DOI: 10.1109/TITS.2026.3723440

Jiyao Wang;Xiao Yang;Zhenyu Wang;Ximeng Wei;Ange Wang;Dengbo He;Kaishun Wu

{"title":"Efficient Mixture-of-Experts for Video-Based Driver State and Physiological Multi-Task Estimation in Conditional Autonomous Driving","authors":"Jiyao Wang;Xiao Yang;Zhenyu Wang;Ximeng Wei;Ange Wang;Dengbo He;Kaishun Wu","doi":"10.1109/TITS.2026.3723440","DOIUrl":"https://doi.org/10.1109/TITS.2026.3723440","url":null,"abstract":"Road safety remains a critical challenge worldwide, with approximately 1.19 million fatalities annually attributed to traffic accidents, often due to human error. As we advance towards higher levels of vehicle automation, challenges still exist, as driving with automation can cognitively over-demand drivers if engaging in non-driving-related tasks (NDRTs), or lead to drowsiness if driving is the sole task. This calls for the urgent need for an effective Driver Monitoring System (DMS) that can evaluate cognitive load and drowsiness in SAE Level-2/3 autonomous driving contexts. In this study, we propose a novel multi-task DMS, termed VDMoE, which leverages RGB video input to monitor driver states non-invasively. By utilizing key facial features to minimize computational load and integrating remote Photoplethysmography (rPPG) for physiological insights, our approach enhances detection accuracy while maintaining efficiency. Additionally, we optimize the Mixture-of-Experts (MoE) framework to accommodate multi-modal inputs and improve performance across different tasks. A novel prior-driven regularization method is introduced to align model outputs with human-factors priors, thus mitigating overfitting risks. We validated our method by creating a new dataset (MCDD), which comprises RGB video and physiological indicators from 42 participants, as well as two public datasets. Our findings demonstrate the effectiveness of VDMoE in monitoring driver states, contributing to safer autonomous driving systems. Code is in <uri>https://github.com/WJULYW/VDMoE</uri>","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12096-12111"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

DINO-CoDT: Multi-Class Collaborative Detection and VFM-Guided Tracking 恐龙- codt：多类协同检测和vfm引导跟踪

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-06-08 DOI: 10.1109/TITS.2026.3697384

Xunjie He;Christina Dao Wen Lee;Meiling Wang;Chengran Yuan;Zefan Huang;Yufeng Yue;Marcelo H. Ang

{"title":"DINO-CoDT: Multi-Class Collaborative Detection and VFM-Guided Tracking","authors":"Xunjie He;Christina Dao Wen Lee;Meiling Wang;Chengran Yuan;Zefan Huang;Yufeng Yue;Marcelo H. Ang","doi":"10.1109/TITS.2026.3697384","DOIUrl":"https://doi.org/10.1109/TITS.2026.3697384","url":null,"abstract":"Collaborative perception is critical for advancing environmental understanding by extending perceptual coverage and enhancing resilience to sensor failures. However, most existing works (both 3D detection and tracking) focus primarily on the vehicle category, lacking robust multi-class solutions. This gap restricts their applicability in real-world scenarios, which involve a diverse range of objects with distinct appearances and motion characteristics. To overcome these limitations, we propose a multi-class collaborative detection and tracking framework tailored for diverse road users. We first present a detector with a global spatial attention fusion (GSAF) module, enhancing local-global feature learning for objects of varying sizes. Next, we introduce a tracklet re-identification (REID) module that leverages visual semantics with a vision foundation model to effectively reduce ID switch errors, in cases of erroneous mismatches involving small objects such as pedestrians. We further design a velocity-based adaptive tracklet management (VATM) module that adjusts the tracking interval dynamically based on object motion. Extensive experiments on the V2X-Real and OPV2V datasets demonstrate that our approach consistently outperforms state-of-the-art methods. In particular, on the pedestrian class of the V2X-Real dataset, it achieves a 1.9% improvement in mAP@0.3 for detection and a 0.79% gain in sAMOTA for tracking.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12499-12514"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

PPT-AMA: Privacy Protection and Traceability Anonymous Mutual Authentication Protocol for Heterogeneous Vehicular Networks 异构车辆网络的隐私保护和可追溯性匿名互认证协议

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-09-01 DOI: 10.1109/TITS.2026.3721804

Yong Wu;Bei Gong;Haotian Zhu;Mowei Gong;Zhe Li;Jun Hu;Weizhi Meng

{"title":"PPT-AMA: Privacy Protection and Traceability Anonymous Mutual Authentication Protocol for Heterogeneous Vehicular Networks","authors":"Yong Wu;Bei Gong;Haotian Zhu;Mowei Gong;Zhe Li;Jun Hu;Weizhi Meng","doi":"10.1109/TITS.2026.3721804","DOIUrl":"https://doi.org/10.1109/TITS.2026.3721804","url":null,"abstract":"The Internet of Vehicles (IoV), as a key component of smart cities, plays a pivotal role in vehicle coordination and intelligent transportation systems. However, with the rapid advancement of IoV technology, the growing threat of network attacks has heightened the demand for enhanced security and privacy protection. Owing to the heterogeneous nature of devices within the IoV, which often employ different cryptographic systems, traditional authentication mechanisms face limitations in verifying the legitimacy of such heterogeneous devices. To address this challenge, this paper proposes a privacy protection and traceability anonymous mutual authentication protocol for heterogeneous vehicular networks (PPT-AMA). PPT-AMA can realize mutual identity verification and session key agreement between the vehicle in the certificateless cryptosystem and the roadside unit in the identity-based cryptosystem to ensure the secure transmission of private data. Moreover, by providing traceable pseudonyms and anonymous authentication for each vehicle, PPT-AMA protects vehicle privacy while preventing attackers from tracking vehicle information through public information such as public keys or identities. Under the discrete logarithm and computational Diffie-Hellman assumption, PPT-AMA is shown to meet various security requirements, including perfect forwards secrecy and known session-specific temporary information security. The performance evaluation, which is based on theoretical analysis and simulation experiments, demonstrates approximately 32.50% improvement in computational efficiency over existing schemes, highlighting the protocol’s potential for practical application.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12112-12128"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

EVCha: A Multi-Task Learning Framework With Heterogeneous Multi-Graph Fusion for Electric Vehicle Charging Demand Prediction 基于异构多图融合的电动汽车充电需求预测多任务学习框架

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-07-03 DOI: 10.1109/TITS.2026.3704750

Feng Lyu;Shiwen Wu;Sijing Duan;Zeyang Tang;Mingliu Liu;Manjia Liu;Wei Rao;Yiwen Li

{"title":"EVCha: A Multi-Task Learning Framework With Heterogeneous Multi-Graph Fusion for Electric Vehicle Charging Demand Prediction","authors":"Feng Lyu;Shiwen Wu;Sijing Duan;Zeyang Tang;Mingliu Liu;Manjia Liu;Wei Rao;Yiwen Li","doi":"10.1109/TITS.2026.3704750","DOIUrl":"https://doi.org/10.1109/TITS.2026.3704750","url":null,"abstract":"Electric vehicles (EVs) charging demand prediction is crucial for regional load scheduling, dynamic pricing, and charging infrastructure planning. Although existing studies have made some efforts, they mainly focus on a single type of vehicle (e.g., buses or taxis) and seldom consider the correlations between different vehicle types and their collective impacts (e.g., vehicle mobility) on regional charging demand. Therefore, these models may cause performance degradation when applied in practical settings where multiple types of EVs coexist. To fill this gap, we design a novel multi-task learning framework <monospace>EVCha</monospace> with heterogeneous multi-graph fusion to enable collaborative charging demand prediction for multi-types of EVs. Firstly, a multi-type vehicle shared feature extraction module is designed to extract and fuse similar patterns of different vehicles. Secondly, a heterogeneous multi-graph spatio-temporal learning module is developed to capture multiple dependency relationships, including historical charging demand similarity, vehicle mobility, and points of interest distribution among regions. Thirdly, an MTL-based training module is designed to achieve collaborative prediction of multi-type EVs. We evaluate <monospace>EVCha</monospace> using two large-scale real-world datasets. Extensive experimental results show that <monospace>EVCha</monospace> achieves superior performance and outperforms the state-of-the-art baseline by 22.5% in root mean square error. The source code and data are available at <uri>https://github.com/charging-demand/EVCha</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12216-12232"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Multilateral Network Transformation for Transport Mode Selection of Multimodal Transportation 多式联运运输方式选择的多边网络转型

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-06-23 DOI: 10.1109/TITS.2026.3699814

Zhiyang Chen;Rob Law;Xin Wang;Poly Z.H. Sun

{"title":"Multilateral Network Transformation for Transport Mode Selection of Multimodal Transportation","authors":"Zhiyang Chen;Rob Law;Xin Wang;Poly Z.H. Sun","doi":"10.1109/TITS.2026.3699814","DOIUrl":"https://doi.org/10.1109/TITS.2026.3699814","url":null,"abstract":"As a challenging combinatorial optimization problem, transport mode selection in multimodal transportation is difficult to solve for large-scale networks. This study proposes a novel solution framework to address this challenge. First, we adopt a network transformation method, Node Splitting and Subnode Connecting (NSSC), tailoring it to convert the complex multilateral transportation network into a standard directed graph, making it amenable to established optimization models. Second, recognizing that exact solvers can be computationally prohibitive for large instances, we develop a high-performance heuristic algorithm. This algorithm is based on the concept of Effective Transfer (ET), a logistics-oriented principle to identify strategically advantageous routes. By using an ET-based route search to prune the solution space, our method can efficiently find high-quality, time-feasible solutions. Comparative experiments show that our proposed framework significantly outperforms the widely-used typical solver (Gurobi) and a well-established heuristic (<inline-formula> <tex-math>$K$ </tex-math></inline-formula>-Restricted Label Setting), and offers a better trade-off between solution quality, computational time, and memory usage than the solver and the heuristic on large networks.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12701-12717"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

From Camera-Based Sensing to Reasoning: A Comprehensive Review Toward Proactive Vulnerable Road User Safety 从基于摄像头的传感到推理：对前瞻性弱势道路使用者安全的全面回顾

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-07-20 DOI: 10.1109/TITS.2026.3707876

Shucheng Zhang;Yan Shi;Bingzhang Wang;Yuang Zhang;Muhammad Monjurul Karim;Kehua Chen;Chenxi Liu;Mehrdad Nasri;Yinhai Wang

{"title":"From Camera-Based Sensing to Reasoning: A Comprehensive Review Toward Proactive Vulnerable Road User Safety","authors":"Shucheng Zhang;Yan Shi;Bingzhang Wang;Yuang Zhang;Muhammad Monjurul Karim;Kehua Chen;Chenxi Liu;Mehrdad Nasri;Yinhai Wang","doi":"10.1109/TITS.2026.3707876","DOIUrl":"https://doi.org/10.1109/TITS.2026.3707876","url":null,"abstract":"Ensuring the safety of vulnerable road users (VRUs), such as pedestrians and cyclists, remains a critical challenge, as conventional infrastructure-based measures are often insufficient in dynamic urban environments. Recent advances in learning-based visual sensing systems have created new opportunities for more adaptive and context-aware VRU protection. This paper presents a comprehensive review of camera-based methods for proactive VRU safety, with a focus on developments over the past five years. Unlike prior surveys that primarily emphasize detection, we organize the literature into three interconnected components: visual perception (detection and classification), motion modeling (tracking and trajectory prediction), and behavior understanding (intent recognition and reasoning). These components form a unified hierarchical pipeline that enables early risk anticipation and timely intervention. Furthermore, this survey systematically incorporates emerging AI paradigms, including Vision Transformers (ViTs), Large Language Models (LLMs), and diffusion models, highlighting their roles in representation learning, uncertainty modeling, and semantic reasoning. Finally, we identify four key challenges specific to VRU safety, including data scarcity, behavioral uncertainty, edge deployment efficiency, and real-world sensing constraints, and discuss corresponding research directions. This work provides a unified foundation for the development of reliable, scalable, and deployable VRU safety systems.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"11966-11982"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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