Pub Date : 2026-01-12DOI: 10.1109/OJVT.2026.3652024
Sharvil Bhatt;Jayaprakash Kar
While Vehicular Ad-hoc Networks (VANETs) can potentially improve driver safety and traffic management efficiency (e.g. through timely sharing of traffic status among vehicles), security and privacy are two ongoing issues that need to be addressed. This article proposes a novel blockchain-based authentication scheme leveraging conditional privacy within temporary platoons. The proposed model is an extended model based on Temporary Blockchain Platoons Formation. Our scheme utilizes blockchain technology to ensure data integrity and prevent unauthorized access, while enabling conditional privacy preservation where data sharing is limited based on pre-defined trust levels within the platoon. This significantly reduces reliance on Roadside Units (RSUs), leading to a cost-effective approach. Compared to traditional Public Key Infrastructure (PKI), our scheme offers improved security, enhanced privacy, and reduced infrastructure costs, promoting wider VANET implementation. The augmented model also incorporates an “Accident Prevention Mechanism,” a critical component absent in the preceding Platoon proposed model, thereby enhancing the overall safety and robustness of the system. Apart from the extra proposed features, rest features and mechanisms will be working as in already present Platoon Model.
{"title":"A Blockchain-Based Privacy-Preserving Authentication Scheme for Secure Platoon Communications in VANET","authors":"Sharvil Bhatt;Jayaprakash Kar","doi":"10.1109/OJVT.2026.3652024","DOIUrl":"https://doi.org/10.1109/OJVT.2026.3652024","url":null,"abstract":"While Vehicular Ad-hoc Networks (VANETs) can potentially improve driver safety and traffic management efficiency (e.g. through timely sharing of traffic status among vehicles), security and privacy are two ongoing issues that need to be addressed. This article proposes a novel blockchain-based authentication scheme leveraging conditional privacy within temporary platoons. The proposed model is an extended model based on Temporary Blockchain Platoons Formation. Our scheme utilizes blockchain technology to ensure data integrity and prevent unauthorized access, while enabling conditional privacy preservation where data sharing is limited based on pre-defined trust levels within the platoon. This significantly reduces reliance on Roadside Units (RSUs), leading to a cost-effective approach. Compared to traditional Public Key Infrastructure (PKI), our scheme offers improved security, enhanced privacy, and reduced infrastructure costs, promoting wider VANET implementation. The augmented model also incorporates an “Accident Prevention Mechanism,” a critical component absent in the preceding Platoon proposed model, thereby enhancing the overall safety and robustness of the system. Apart from the extra proposed features, rest features and mechanisms will be working as in already present Platoon Model.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"7 ","pages":"468-490"},"PeriodicalIF":4.8,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11340613","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, the research interest in bidirectional charging of electric vehicles has increased significantly, driven by improved accessibility to charging and payment information as well as the increasing emphasis on integrating variable renewable energy sources more effectively into the grid. Integrating bidirectional charging with the grid/building/home can also reduce grid congestion. Despite this, broader implementation of this technology has not yet been achieved. In this context, this article comprehensively surveys direct current (DC) off-board vehicle to grid/building/home chargers and analyses the gaps which prevent the technologies’ wide implementation. These gaps are analysed by considering areas such as the development direction of bidirectional charging technology, battery cost and its degradation, V2G applicable standards, grid codes and charging protocols, deployment of V2G chargers (off-board versus on-board/wireless), market feasibility of V2G services, and the cost of bidirectional off-board chargers. The first survey of twenty-five commercial bidirectional chargers is presented and investigated in relation to the above-mentioned areas. Four key (technical, regulatory, financial, and behavioural) barriers are identified and discussed for the wide implementation of vehicle to grid/building/home charging.
{"title":"DC Off-Board Vehicle to Grid/Building/Home: A Survey and Gap Analysis","authors":"Carina Engström;Gautam Rituraj;Koen Linders;Marcel Esser;Wenli Shi;Ville Tikka;Gautham Ram Chandra Mouli","doi":"10.1109/OJVT.2026.3652429","DOIUrl":"https://doi.org/10.1109/OJVT.2026.3652429","url":null,"abstract":"In recent years, the research interest in bidirectional charging of electric vehicles has increased significantly, driven by improved accessibility to charging and payment information as well as the increasing emphasis on integrating variable renewable energy sources more effectively into the grid. Integrating bidirectional charging with the grid/building/home can also reduce grid congestion. Despite this, broader implementation of this technology has not yet been achieved. In this context, this article comprehensively surveys direct current (DC) off-board vehicle to grid/building/home chargers and analyses the gaps which prevent the technologies’ wide implementation. These gaps are analysed by considering areas such as the development direction of bidirectional charging technology, battery cost and its degradation, V2G applicable standards, grid codes and charging protocols, deployment of V2G chargers (off-board versus on-board/wireless), market feasibility of V2G services, and the cost of bidirectional off-board chargers. The first survey of twenty-five commercial bidirectional chargers is presented and investigated in relation to the above-mentioned areas. Four key (technical, regulatory, financial, and behavioural) barriers are identified and discussed for the wide implementation of vehicle to grid/building/home charging.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"7 ","pages":"448-467"},"PeriodicalIF":4.8,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11344785","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-12DOI: 10.1109/OJVT.2026.3651808
Joseba Sarabia;Mauricio Marcano;Sergio Diaz;Joshué Pérez Rastelli;Asier Zubizarreta
This article presents an openly documented real-vehicle evaluation of an adaptive shared control system that integrates a nonlinear Model Predictive Controller (NMPC), a Driver Monitoring System (DMS) and a haptic Human Machine Interface (HMI). While similar concepts have been explored by several industrial players, detailed performance data and transparent methodologies remain scarce in the public domain. This work aims to help fill that gap by providing insights into the behavior and integration of such systems under real driving conditions. The system establishes an active safety envelope for manual driving scenarios, employing a shared control strategy that activates during potentially hazardous situations caused by driver misbehavior or external road challenges. A key contribution of this work is the real-world validation of the approach in a vehicle with human drivers, demonstrating how shared control can be effectively deployed beyond simulation. The proposed framework integrates three elements: 1) an NMPC-based shared controller that shifts control authority across three different modes (Electronic Power Steering, Shared Control, and Fully Automated) by adjusting its weights; 2) a DMS that triggers mode switching; and 3) a haptic feedback interface that communicates system state, transitions, and driver intervention requests. The controller enforces a lane-keeping safety envelope and intervenes only when necessary. Results from real-vehicle experiments across two use cases show that the system enhances safety by mitigating lane-departure risks and improving driver attentiveness.
{"title":"Evaluating Shared Control in Real-World Conditions","authors":"Joseba Sarabia;Mauricio Marcano;Sergio Diaz;Joshué Pérez Rastelli;Asier Zubizarreta","doi":"10.1109/OJVT.2026.3651808","DOIUrl":"https://doi.org/10.1109/OJVT.2026.3651808","url":null,"abstract":"This article presents an openly documented real-vehicle evaluation of an adaptive shared control system that integrates a nonlinear Model Predictive Controller (NMPC), a Driver Monitoring System (DMS) and a haptic Human Machine Interface (HMI). While similar concepts have been explored by several industrial players, detailed performance data and transparent methodologies remain scarce in the public domain. This work aims to help fill that gap by providing insights into the behavior and integration of such systems under real driving conditions. The system establishes an active safety envelope for manual driving scenarios, employing a shared control strategy that activates during potentially hazardous situations caused by driver misbehavior or external road challenges. A key contribution of this work is the real-world validation of the approach in a vehicle with human drivers, demonstrating how shared control can be effectively deployed beyond simulation. The proposed framework integrates three elements: 1) an NMPC-based shared controller that shifts control authority across three different modes (Electronic Power Steering, Shared Control, and Fully Automated) by adjusting its weights; 2) a DMS that triggers mode switching; and 3) a haptic feedback interface that communicates system state, transitions, and driver intervention requests. The controller enforces a lane-keeping safety envelope and intervenes only when necessary. Results from real-vehicle experiments across two use cases show that the system enhances safety by mitigating lane-departure risks and improving driver attentiveness.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"7 ","pages":"418-431"},"PeriodicalIF":4.8,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11339954","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-06DOI: 10.1109/OJVT.2025.3646498
{"title":"IEEE Open Journal of Vehicular Technology Information for Authors","authors":"","doi":"10.1109/OJVT.2025.3646498","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3646498","url":null,"abstract":"","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"7 ","pages":"C3-C3"},"PeriodicalIF":4.8,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11333909","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Continuous-variable quantum key distribution (CV-QKD) systems face challenges in maintaining efficient reconciliation over long distances due to the time variant signal-to-noise ratio (SNR) imposed by channel quality fluctuations. Hence fixed-rate error-correction schemes using low-density parity-check (LDPC) or Polar codes lead to high block-error rates (BLER) and degraded secret key rates (SKR). To overcome this, we propose an incremental redundancy aided hybrid automatic repeat request (IR-HARQ) protocol using rate-compatible Polar and LDPC codes. Explicitly, by puncturing a mother code and progressively transmitting additional redundant bits, our method dynamically adapts the effective coding rate to the prevalent channel conditions, achieving 2–3 dB SNR gains per retransmission. This adaptive strategy avoids unnecessary redundancy in good channels and strengthens protection in poor channels, thereby improving reconciliation efficiency. Simulation results show that our IR-HARQ scheme significantly enhances the BLER, throughput, and secure transmission distance compared with single-transmission schemes. Moreover, our study highlights that Polar IR-HARQ achieves superior performance in short block-length and low-SNR scenarios, while LDPC IR-HARQ is more competitive for longer codes and higher SNR. These findings confirm IR-HARQ as an attractive and versatile reconciliation solution for real-world CV-QKD deployments.
{"title":"Rate-Compatible Polar- and LDPC-Coded Hybrid ARQ Aided Reverse Reconciliation in CV-QKD","authors":"Dingzhao Wang;Xin Liu;Chao Xu;Soon Xin Ng;Lajos Hanzo","doi":"10.1109/OJVT.2025.3650700","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3650700","url":null,"abstract":"Continuous-variable quantum key distribution (CV-QKD) systems face challenges in maintaining efficient reconciliation over long distances due to the time variant signal-to-noise ratio (SNR) imposed by channel quality fluctuations. Hence fixed-rate error-correction schemes using low-density parity-check (LDPC) or Polar codes lead to high block-error rates (BLER) and degraded secret key rates (SKR). To overcome this, we propose an incremental redundancy aided hybrid automatic repeat request (IR-HARQ) protocol using rate-compatible Polar and LDPC codes. Explicitly, by puncturing a mother code and progressively transmitting additional redundant bits, our method dynamically adapts the effective coding rate to the prevalent channel conditions, achieving 2–3 dB SNR gains per retransmission. This adaptive strategy avoids unnecessary redundancy in good channels and strengthens protection in poor channels, thereby improving reconciliation efficiency. Simulation results show that our IR-HARQ scheme significantly enhances the BLER, throughput, and secure transmission distance compared with single-transmission schemes. Moreover, our study highlights that Polar IR-HARQ achieves superior performance in short block-length and low-SNR scenarios, while LDPC IR-HARQ is more competitive for longer codes and higher SNR. These findings confirm IR-HARQ as an attractive and versatile reconciliation solution for real-world CV-QKD deployments.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"7 ","pages":"432-446"},"PeriodicalIF":4.8,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11328821","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-05DOI: 10.1109/OJVT.2025.3650591
Zoltan Rozsa;Tamas Sziranyi
The frame rates of most 3D LIDAR sensors used in intelligent vehicles are substantially lower than current cameras installed in the same vehicle. This research suggests using a mono camera to virtually enhance the frame rate of LIDARs, allowing the more frequent monitoring of dynamic objects in the surroundings that move quickly. As a first step, dynamic object candidates are identified and tracked in the camera frames. Following that, the LIDAR measurement points of these items are found by clustering in the frustums of 2D bounding boxes. Projecting these to the camera and tracking them to the next camera frame can be used to create 3D-2D correspondences between different timesteps. These correspondences between the last LIDAR frame and the actual camera frame are used to solve the PnP (Perspective-n-Point) problem. Finally, the estimated transformations are applied to the previously measured points to generate virtual measurements. With the proposed estimation, if the ego movement is known, not just static object position can be determined at timesteps where camera measurement is available, but positions of dynamic objects as well. We achieve state-of-the-art performance on large public datasets in terms of accuracy and similarity to real measurements.
{"title":"Virtually Increasing the Measurement Frequency of LIDAR Sensor Utilizing a Single RGB Camera","authors":"Zoltan Rozsa;Tamas Sziranyi","doi":"10.1109/OJVT.2025.3650591","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3650591","url":null,"abstract":"The frame rates of most 3D LIDAR sensors used in intelligent vehicles are substantially lower than current cameras installed in the same vehicle. This research suggests using a mono camera to virtually enhance the frame rate of LIDARs, allowing the more frequent monitoring of dynamic objects in the surroundings that move quickly. As a first step, dynamic object candidates are identified and tracked in the camera frames. Following that, the LIDAR measurement points of these items are found by clustering in the frustums of 2D bounding boxes. Projecting these to the camera and tracking them to the next camera frame can be used to create 3D-2D correspondences between different timesteps. These correspondences between the last LIDAR frame and the actual camera frame are used to solve the PnP (Perspective-n-Point) problem. Finally, the estimated transformations are applied to the previously measured points to generate virtual measurements. With the proposed estimation, if the ego movement is known, not just static object position can be determined at timesteps where camera measurement is available, but positions of dynamic objects as well. We achieve state-of-the-art performance on large public datasets in terms of accuracy and similarity to real measurements.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"7 ","pages":"552-564"},"PeriodicalIF":4.8,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11328775","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-30DOI: 10.1109/OJVT.2025.3650061
{"title":"2025 Index IEEE Open Journal of Vehicular Technology Vol. 6","authors":"","doi":"10.1109/OJVT.2025.3650061","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3650061","url":null,"abstract":"","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"3017-3065"},"PeriodicalIF":4.8,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11319354","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-26DOI: 10.1109/OJVT.2025.3649122
Khac-Hoang Ngo;Diego Cuevas;Ruben De Miguel Gil;Victor Monzon Baeza;Ana Garcia Armada;Ignacio Santamaria
Noncoherent communication is a promising paradigm for future wireless systems where acquiring accurate channel state information (CSI) is challenging or infeasible. It provides methods to bypass the need for explicit channel estimation in practical scenarios such as high-mobility networks, massive distributed antenna arrays, and energy-constrained Internet-of-Things devices. This survey provides a comprehensive overview of noncoherent communication strategies in multiple-input multiple-output (MIMO) systems. We classify noncoherent communication schemes into three main approaches where CSI-free signal recovery is based on subspace detection (i.e., Grassmannian signaling), differential detection, and energy detection. For each approach, we review the theoretical foundation and design methodologies. We also provide comparative insights into their suitability across different channel models and system constraints, highlighting application scenarios where noncoherent methods offer performance and scalability advantages. Furthermore, we discuss practical considerations of noncoherent communication, including compatibility with orthogonal frequency division multiplexing (OFDM), resilience to hardware impairments, and scalability with the number of users. Finally, we provide an outlook on future challenges and research directions in designing robust and efficient noncoherent systems for next-generation wireless networks.
{"title":"Noncoherent MIMO Communications: Theoretical Foundation, Design Approaches, and Future Challenges","authors":"Khac-Hoang Ngo;Diego Cuevas;Ruben De Miguel Gil;Victor Monzon Baeza;Ana Garcia Armada;Ignacio Santamaria","doi":"10.1109/OJVT.2025.3649122","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3649122","url":null,"abstract":"Noncoherent communication is a promising paradigm for future wireless systems where acquiring accurate channel state information (CSI) is challenging or infeasible. It provides methods to bypass the need for explicit channel estimation in practical scenarios such as high-mobility networks, massive distributed antenna arrays, and energy-constrained Internet-of-Things devices. This survey provides a comprehensive overview of noncoherent communication strategies in multiple-input multiple-output (MIMO) systems. We classify noncoherent communication schemes into three main approaches where CSI-free signal recovery is based on subspace detection (i.e., Grassmannian signaling), differential detection, and energy detection. For each approach, we review the theoretical foundation and design methodologies. We also provide comparative insights into their suitability across different channel models and system constraints, highlighting application scenarios where noncoherent methods offer performance and scalability advantages. Furthermore, we discuss practical considerations of noncoherent communication, including compatibility with orthogonal frequency division multiplexing (OFDM), resilience to hardware impairments, and scalability with the number of users. Finally, we provide an outlook on future challenges and research directions in designing robust and efficient noncoherent systems for next-generation wireless networks.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"7 ","pages":"381-401"},"PeriodicalIF":4.8,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11316609","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Autonomous and semi-autonomous vehicles require accurate perception of their surrounding environment to ensure safe operation, yet onboard sensors frequently encounter occlusion challenges that result in incomplete dynamic environmental maps. Infrastructure-to-vehicle cooperative perception addresses this by deploying infrastructure nodes that monitor scenes and share reliable environmental maps with nearby vehicles via technologies like C-V2X. However, existing infrastructure perspective datasets lack diverse multi-modal data and aerial footage, which are crucial to determine effectively the necessary sensors for safety-critical infrastructure node applications. This paper introduces G-MIND, a multimodal infrastructure node dataset supporting research into sensor suitability for infrastructure-assisted safety-critical applications. G-MIND is the first dataset to incorporate this comprehensive range of sensing modalities for infrastructure-based perception: RGB, FIR, and neuromorphic cameras, LiDARs, RADAR, and aerial drone footage. With 91,500 annotated frames, G-MIND offers a larger scale than existing infrastructure perception datasets such as Ko-PER (10 k frames), CoopScenes (40 K frames), and DAIR-V2X (71 k frames), enabling more comprehensive training and evaluation. The dataset captures day and night scenarios featuring cars, pedestrians, and cyclists across diverse traffic scenarios. Beyond standard perception benchmarking, G-MIND includes specialized collections designed to test perception system boundaries: maximum detection distance scenarios, far and occluded object scenarios, and pedestrian action prediction scenarios that challenge current algorithms. Additionally, this paper analyzes what constitutes effective ITS infrastructure node sensors from a practical perspective, comparing modalities against technical criteria (field of view, spatial resolution, low light performance, adverse weather resilience) and pragmatic criteria (cost, durability).
{"title":"G-MIND: Galway Multimodal Infrastructure Node Dataset for Intelligent Transportation Systems","authors":"Dara Molloy;Roshan George;Tim Brophy;Brian Deegan;Darragh Mullins;Enda Ward;Jonathan Horgan;Ciaran Eising;Patrick Denny;Edward Jones;Martin Glavin","doi":"10.1109/OJVT.2025.3648251","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3648251","url":null,"abstract":"Autonomous and semi-autonomous vehicles require accurate perception of their surrounding environment to ensure safe operation, yet onboard sensors frequently encounter occlusion challenges that result in incomplete dynamic environmental maps. Infrastructure-to-vehicle cooperative perception addresses this by deploying infrastructure nodes that monitor scenes and share reliable environmental maps with nearby vehicles via technologies like C-V2X. However, existing infrastructure perspective datasets lack diverse multi-modal data and aerial footage, which are crucial to determine effectively the necessary sensors for safety-critical infrastructure node applications. This paper introduces G-MIND, a multimodal infrastructure node dataset supporting research into sensor suitability for infrastructure-assisted safety-critical applications. G-MIND is the first dataset to incorporate this comprehensive range of sensing modalities for infrastructure-based perception: RGB, FIR, and neuromorphic cameras, LiDARs, RADAR, and aerial drone footage. With 91,500 annotated frames, G-MIND offers a larger scale than existing infrastructure perception datasets such as Ko-PER (10 k frames), CoopScenes (40 K frames), and DAIR-V2X (71 k frames), enabling more comprehensive training and evaluation. The dataset captures day and night scenarios featuring cars, pedestrians, and cyclists across diverse traffic scenarios. Beyond standard perception benchmarking, G-MIND includes specialized collections designed to test perception system boundaries: maximum detection distance scenarios, far and occluded object scenarios, and pedestrian action prediction scenarios that challenge current algorithms. Additionally, this paper analyzes what constitutes effective ITS infrastructure node sensors from a practical perspective, comparing modalities against technical criteria (field of view, spatial resolution, low light performance, adverse weather resilience) and pragmatic criteria (cost, durability).","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"7 ","pages":"491-509"},"PeriodicalIF":4.8,"publicationDate":"2025-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11316264","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Automotive cameras provide rich visual data to ensure safe function deployment in ADSs (Automated Driving Systems), especially with regard to perception functions. With the increasing demand to accurately perceive the surrounding environment, cameras generate significant volumes of data, causing bandwidth bottlenecks in the automotive wired communication networks. To avoid expensive hardware / cable upgrades, we propose hereby using video compression, and specifically Bayer compression, to reduce the amount of data to be transferred. Bayer compression indicates a special compression scheme utilising the Bayer data pipeline, in contrast to conventional compression schemes using RGB or YCbCr data, mainly for human vision. Bayer is the colour format of raw data captured after camera and before ISP (Image Signal Processing). Bayer data are smaller than RGB data, and recent work demonstrated that it can be directly fed into an automotive perception system. This paper presents novel computational-effective Colour Space Transform (CST) Bayer adaptation techniques, preserving the pixel-correlation by full luma channel, and out-performing other SOTA techniques in terms of image quality and performance when evaluated by downstream perception task. And they can be directly consumable by widely used compression codecs, H.264 and JPEG. The quality of Bayer data compression is evaluated on IQA (Image Quality Assessment) metrics and perception focused downstream tasks, in particularly object detection. With limited colour distortion, the two proposed CSTs achieve the best compression/detection results compared to other SOTA methods at compression ratios of 4.10:1 and 3.86:1 in H.264 with different deep neural network architectures.
{"title":"A Path Toward Bayer Compression for Automotive Applications","authors":"Hetian Wang;Daniel Gummadi;Anthony Huggett;Kurt Debattista;Valentina Donzella","doi":"10.1109/OJVT.2025.3648261","DOIUrl":"https://doi.org/10.1109/OJVT.2025.3648261","url":null,"abstract":"Automotive cameras provide rich visual data to ensure safe function deployment in ADSs (Automated Driving Systems), especially with regard to perception functions. With the increasing demand to accurately perceive the surrounding environment, cameras generate significant volumes of data, causing bandwidth bottlenecks in the automotive wired communication networks. To avoid expensive hardware / cable upgrades, we propose hereby using video compression, and specifically <italic>Bayer compression</i>, to reduce the amount of data to be transferred. Bayer compression indicates a special compression scheme utilising the Bayer data pipeline, in contrast to conventional compression schemes using RGB or YCbCr data, mainly for human vision. Bayer is the colour format of raw data captured after camera and before ISP (Image Signal Processing). Bayer data are smaller than RGB data, and recent work demonstrated that it can be directly fed into an automotive perception system. This paper presents novel computational-effective Colour Space Transform (CST) Bayer adaptation techniques, preserving the pixel-correlation by full luma channel, and out-performing other SOTA techniques in terms of image quality and performance when evaluated by downstream perception task. And they can be directly consumable by widely used compression codecs, H.264 and JPEG. The quality of Bayer data compression is evaluated on IQA (Image Quality Assessment) metrics and perception focused downstream tasks, in particularly object detection. With limited colour distortion, the two proposed CSTs achieve the best compression/detection results compared to other SOTA methods at compression ratios of 4.10:1 and 3.86:1 in H.264 with different deep neural network architectures.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"7 ","pages":"598-611"},"PeriodicalIF":4.8,"publicationDate":"2025-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11316248","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：