IEEE Transactions on Intelligent Transportation Systems最新文献

{"title":"Self-Supervised Visual Odometry Based on Scene Appearance-Structure Incremental Fusion","authors":"Fuji Fu;Jinfu Yang;Jiaqi Ma;Jiahui Zhang","doi":"10.1109/TITS.2025.3559077","DOIUrl":"https://doi.org/10.1109/TITS.2025.3559077","url":null,"abstract":"Self-supervised visual odometry (VO) has exhibited remarkable benefits over supervised methods, surpassing the reliance on the annotated ground-truth of training data. However, most existing self-supervised VO methods, namely scene appearance-based methods, have limitations in exploiting the complementary properties of cross-modal information between scene appearance and structure. To this end, we propose a novel self-supervised VO based on scene appearance-structure incremental fusion scheme. Specifically, a Global-Local Context awareness-based Depth estimation Network (GLC-DN) is designed to introduce the scene structural cues, thus laying the foundation for realizing the scene appearance-structure incremental fusion. Then, a Dual stream Pose estimation Network based on Scene Appearance-Structure Incremental Fusion (SASIF-DPN) is devised, which consists of a Dual Stream Network (DSN) and multiple Cross-Modal Complementary Fusion Modules (CM-CFMs). CM-CFM fully leverages the complementary properties between the RGB information and the predicted depth information, and the combination of multiple CM-CFMs facilitates the information interaction between the two modalities in an incremental fusion manner. Detailed evaluations of GLC-DN and SASIF-DPN provably confirm the effectiveness and design principles of each component we propose. Extensive comparison experiments have also been conducted, which clearly verify the superiority of our method compared to current counterparts.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 6","pages":"8006-8020"},"PeriodicalIF":7.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206197","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}

{"title":"Cross-Scale Guidance Network for Few-Shot Moving Foreground Object Segmentation","authors":"Yi-Sheng Liao;Yen-Wei Lin;Ya-Han Chang;Chun-Rong Huang","doi":"10.1109/TITS.2025.3559144","DOIUrl":"https://doi.org/10.1109/TITS.2025.3559144","url":null,"abstract":"Foreground object segmentation is one of the most important pre-processing steps in intelligent transportation and video surveillance systems. Although background modeling methods are efficient to segment foreground objects, their results are easily affected by dynamic backgrounds and updating strategies. Recently, deep learning-based methods have achieved more effective foreground object segmentation results compared with background modeling methods. However, a large number of labeled training frames are usually required. To reduce the number of training frames, we propose a novel cross-scale guidance network (CSGNet) for few-shot moving foreground object segmentation in surveillance videos. The proposed CSGNet contains the cross-scale feature expansion encoder and cross-scale feature guidance decoder. The encoder aims to represent the scenes by extracting cross-scale expansion features based on cross-scale and multiple field-of-view information learned from a limited number of training frames. The decoder aims to obtain accurate foreground object segmentation results under the guidance of the encoder features and the foreground loss. The proposed method outperforms the state-of-the-art background modeling methods and the deep learning-based methods around 2.6% and 3.1%, and the average computation time is 0.073 and 0.046 seconds for each frame in the CDNet2014 dataset and the UCSD dataset under a single GTX 1080 GPU computer. The source code will be available at <uri>https://github.com/nchucvml/CSGNet</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 6","pages":"7726-7739"},"PeriodicalIF":7.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206189","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}

{"title":"V-DCRNN: Virtual Network-Based Diffusion Convolutional Recurrent Neural Network for Estimating Unobserved Traffic Data","authors":"Chanyoung Yoon;Soobin Yim;Sangbong Yoo;Chanyoung Jung;Hanbyul Yeon;Yun Jang","doi":"10.1109/TITS.2025.3559184","DOIUrl":"https://doi.org/10.1109/TITS.2025.3559184","url":null,"abstract":"Several studies have analyzed traffic patterns using Vehicle Detector (VD) and Global Positioning System (GPS) data. VD records the speed of vehicles passing through detectors, GPS data captures traffic speed on the roads. However, unobserved data gaps may arise due to physical malfunctions of sensors in VD data or interruptions in satellite signal reception for GPS data. Unobserved data adds complexity to the analysis and prediction of urban traffic networks. To tackle this challenge, researchers have attempted to estimate unobserved data using spatiotemporal patterns, but approaches that rely solely on past time points are inherently less reliable. In this study, we propose a Virtual network-based Diffusion Convolutional Recurrent Neural Network (V-DCRNN) for estimating unobserved speed data in urban traffic networks using a virtual network. The virtual network is created by adding nodes and edges in virtual directions based on observed nodes at intersections, thereby enhancing the traffic network. The V-DCRNN, which utilizes the diffusion convolution process in the virtual network, uses the augmented traffic network as input to predict traffic speed. Unobserved speed data is estimated based on the values of virtual nodes predicted by V-DCRNN. We evaluate the proposed V-DCRNN model through unobserved speed data estimation experiments in the urban traffic network, where we randomly mask individual nodes and entire intersections. The main contributions of this work are as follows: 1) the design of a virtual network to model additional traffic dynamics at intersections, facilitating the estimation of unobserved speed data; 2) the development of the V-DCRNN model, which leverages a self-attention mechanism to capture spatiotemporal dependencies in urban traffic networks by incorporating the virtual network as input; and 3) an evaluation of the V-DCRNN’s ability to estimate unobserved speed data in urban traffic networks with up to 20% unobserved nodes, demonstrating robust and reliable performance.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 7","pages":"10336-10352"},"PeriodicalIF":7.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536283","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}

{"title":"Secure and Anonymous Batch Authentication and Key Exchange Protocols for 6G Enabled VANETs","authors":"Mahender Kumar;Carsten Maple","doi":"10.1109/TITS.2025.3557760","DOIUrl":"https://doi.org/10.1109/TITS.2025.3557760","url":null,"abstract":"Advancements in 6G communication technology hold great promise for Vehicular Ad Hoc Networks (VANETs), providing critical real-time data to vehicles with low latency, high speed, and enhanced network capacity. While 6G communications significantly improve transportation efficiency, they also introduce significant challenges in securing communication. Several studies have addressed anonymous authentication and key exchange protocols for 6G-enabled VANETs, including the work (doi.org/10.1109/TITS.2021.3099488) by Vijayakumar et al. on Anonymous Batch Authentication and Key Exchange Protocols. Although this protocol is claimed to be secure, our analysis identifies critical vulnerabilities, including susceptibility to man-in-the-middle attacks, impersonation, and unauthorized access. This paper proposes a secure and anonymous batch authentication and key exchange protocol for 6G-enabled VANETs to address this challenge. The formal security analysis demonstrates that the proposed solution effectively mitigates man-in-the-middle attacks, impersonation, and unauthorized access. Additionally, performance evaluations show that the proposed scheme is practically feasible.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 6","pages":"8140-8146"},"PeriodicalIF":7.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196542","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}

{"title":"Content Placement and Edge Collaborative Caching Scheme Based on Deep Reinforcement Learning for Internet of Vehicles","authors":"Zhu Sifeng;Tian Xiaohua;Zhang Zonghui;Qiao Rui;Zhu Hai","doi":"10.1109/TITS.2025.3558898","DOIUrl":"https://doi.org/10.1109/TITS.2025.3558898","url":null,"abstract":"With the rapid development of Internet of Vehicles technology, communication and data exchange between vehicles have become an important part of modern traffic management. A content placement and edge collaborative caching solution based on deep reinforcement learning is proposed in this paper, aiming to address the data processing and storage challenges faced by Internet of Vehicles systems. Utilizing the collaborative caching between smart vehicles and roadside units employs deep reinforcement learning methods to find and design a collaborative caching solution for the Internet of Vehicles edge. It uses content segmentation technology to divide and cache content fragments in advance to reduce the central server load and network pressure, thereby adapting to the randomness of vehicle mobility and communication duration. The experimental results show that the proposed scheme can effectively reduce the load on the central server, reduce network latency, and improve cache hit rate, providing a flexible and efficient solution for real-time communication and data exchange in the Internet of Vehicles system.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 6","pages":"8050-8064"},"PeriodicalIF":7.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196593","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}

{"title":"Stochastic Energy Scheduling for Urban Railway Smart Grids Considering Distributed EVs Charging and PV Output Uncertainty","authors":"Minwu Chen;Hao Deng;Yinyu Chen;Gaoqiang Peng;Zongyou Liang","doi":"10.1109/TITS.2025.3558735","DOIUrl":"https://doi.org/10.1109/TITS.2025.3558735","url":null,"abstract":"In order to improve the utilization rate of regenerative braking energy (RBE) and reduce the operation cost of railway system, this paper proposed an urban railway smart grids (URSG) with efficient and flexible energy management strategy is proposed, which integrates a traction power supply system (TPSS), electric vehicle charging station (EVCS), PV and battery storage. In this study, a bi-level stochastic optimization (BLSO) model is employed to determine the sizing of battery storage and the energy scheduling of URSG. The upper level aims to determine the optimal size of battery storage and minimize the comprehensive cost, considering the degradation of the battery capacity. In the lower level, based on piecewise linearization method, the power transmission loss of catenary is formulated as a linear mathematical model, and a stochastic mixed-integer linear programming model of URSG is established to schedule the power flow to minimize the electrical cost. Furthermore, regarding to the stochastic nature of EV charging behavior and PV output, the constraints with uncertain parameters are posed as chance constraints, for which Sample Average Approximation (SAA) method is introduced to transform chance constraints into deterministic constraints. Based on the actual urban rail transit line and traction load data, the simulation results show that the above system can reduce the cost by 18.16 %.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 6","pages":"7898-7908"},"PeriodicalIF":7.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205969","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}

{"title":"A Hierarchical Controller for Connected Truck Platoon: Analysis and Verification","authors":"Yongfu Li;Junhong Fan;Longwang Huang;Gang Huang;Wei Hua;Wei Wu;Shuyou Yu;Shuming Shi;Xinbo Gao","doi":"10.1109/TITS.2025.3556465","DOIUrl":"https://doi.org/10.1109/TITS.2025.3556465","url":null,"abstract":"This paper proposes a novel hierarchical controller for connected truck platoons. To this end, the predecessor following topology is used to characterize the communication connectivity between connected trucks. Then, a longitudinal efficient controller consisting of upper-level and lower-level controllers is proposed. In particular, the upper-level controller is designed based on the kinematic model to handle the car-following interactions between connected trucks and delays in communication and input. The lower-level controller comprises a feedforward and a feedback control law. The feedforward control law converts the desired acceleration from the upper-level controller into the vehicle throttle or braking pressure using the inverse dynamic model, while the feedback control law compensates for the control error caused by unknown vehicle parameters. In addition, in the linear region, the internal stability is analyzed based on the second-order kinematic model using s-domain analysis and linearization method, respectively. Then, the string stability is proved. The influence of parameters on the stability performance is extensively discussed using the stability diagram. Finally, the feasibility of the proposed controller is verified via co-simulations in PreScan and TruckSim, in terms of acceleration, velocity, and spacing error profiles.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 6","pages":"7465-7475"},"PeriodicalIF":7.9,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196594","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}

{"title":"Leveraging Anchor-Based LiDAR 3D Object Detection via Point Assisted Sample Selection","authors":"Shitao Chen;Haolin Zhang;Nanning Zheng","doi":"10.1109/TITS.2025.3555229","DOIUrl":"https://doi.org/10.1109/TITS.2025.3555229","url":null,"abstract":"3D object detection based on LiDAR point cloud and prior anchor boxes is a critical technology for autonomous driving environment perception and understanding. Nevertheless, an overlooked practical issue in existing methods is the ambiguity in training sample allocation based on box Intersection over Union (IoUbox). This problem impedes further enhancements in the performance of anchor-based LiDAR 3D object detectors. To tackle this challenge, this paper introduces a new training sample selection method that utilizes point cloud distribution for anchor sample quality measurement, named Point Assisted Sample Selection (PASS). This method has undergone rigorous evaluation on four widely utilized datasets. Experimental results demonstrate that the application of PASS elevates the average precision of anchor-based LiDAR 3D object detectors to a novel state-of-the-art, thereby proving the effectiveness of the proposed approach. The codes will be made available at <uri>https://github.com/</uri> XJTU-Haolin/Point_Assisted_Sample_Selection.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 6","pages":"7939-7952"},"PeriodicalIF":7.9,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206196","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}

{"title":"Robust Cooperative Adaptive Cruise Control System Design: Trade-Off Between Parasitic Actuation Lag and Communication Delay","authors":"Guoqi Ma;Prabhakar R. Pagilla;Swaroop Darbha","doi":"10.1109/TITS.2025.3553812","DOIUrl":"https://doi.org/10.1109/TITS.2025.3553812","url":null,"abstract":"In this paper, we provide a systematic procedure for designing cooperative adaptive cruise control (CACC) systems that are robust to parasitic actuation lag in braking and propulsion and delay in the communicated acceleration from the predecessor vehicle. In particular, we derive a tight lower bound on the employable time headway in CACC systems for guaranteeing robust string stability. The lower bound on the time headway is dependent on the upper bound on the parasitic actuation lag (<inline-formula> <tex-math>$tau _{0}$ </tex-math></inline-formula>) and the communication delay (<inline-formula> <tex-math>$ell $ </tex-math></inline-formula>). The main result of the paper is that if <inline-formula> <tex-math>$tau _{0}$ </tex-math></inline-formula> exceeds <inline-formula> <tex-math>$ell $ </tex-math></inline-formula>, then the employable time headway is lower bounded by <inline-formula> <tex-math>$tau _{0}+ell $ </tex-math></inline-formula>. Otherwise, it is better to use adaptive cruise control (ACC) where the employable time headway is lower bounded by <inline-formula> <tex-math>$2tau _{0}$ </tex-math></inline-formula>. The above results on CACC systems are then extended to next-generation CACC (CACC+) systems that employ information from multiple predecessor vehicles. Several comparative numerical simulations for a representative maneuver corroborate the main results.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 6","pages":"7980-7989"},"PeriodicalIF":7.9,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206175","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}

{"title":"A Flight Process Importance Framework for Evaluating Pilot Performance During Airplane Landing","authors":"Xiong Yang;Shunzhi Yang;MengChu Zhou;Jin Ren;Zhenhua Huang;Jinfeng Yang","doi":"10.1109/TITS.2025.3558469","DOIUrl":"https://doi.org/10.1109/TITS.2025.3558469","url":null,"abstract":"Aviation accidents are frequently related to pilots’ operations, especially during a landing phase. Therefore, accurately evaluating a pilot’s performance during this phase is crucial for minimizing landing risks. Traditional assessment methods, however, primarily focus on discrete monitoring points, failing to capture the continuous and dynamic nature of a pilot’s performance throughout the entire landing phase. To address this issue, we propose a Flight Process Importance (FPI) assessment framework that precisely determines accurate landing timing and captures the diverse operational characteristics of pilots. It consists of two components: Time-varying Importance Coefficient (TIC) and Pilot Characteristics Matrix (PCM). TIC develops a Spatio-Temporally Consistent Attention Network (STCAN) to classify Quick Access Recorder (QAR) data for anomalous event detection. It then determines the importance of different periods during the landing process by analyzing the STCAN model’s response to the data in an interpretable manner. PCM generates a parameter matrix for each flight by deriving the ideal intervals of various parameters through the interquartile range. This matrix is used to identify the duration and intensity of anomalies in operations across different pilots. By integrating TIC and PCM, our framework computes an evaluation matrix for each flight, quantifying the operational risk factors associated with pilots. Experimental results indicate that STCAN significantly surpasses other algorithms on QAR data. FPI provides a more precise and comprehensive assessment of a pilot’s performance. In particular, our findings highlight that the 10 seconds before landing to the touchdown are the most critical period of airplane landing.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 7","pages":"10523-10538"},"PeriodicalIF":7.9,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536504","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}