Telematics devices have transformed driver risk assessment, allowing insurers to tailor premiums based on detailed evaluations of driving habits. However, integrating Advanced Driver Assistance Systems (ADAS) and contextualized geolocation data for predictive improvements remains underexplored due to the recent emergence of these technologies. This article introduces a novel risk assessment methodology that periodically computes weekly insurance premiums by incorporating ADAS risk indicators and contextualized geolocation data. Using a naturalistic dataset from a fleet of 354 commercial drivers over a year, we modeled the relationship between past claims and driving data, and use that to compute weekly premiums that penalize risky driving situations. Risk predictions are modeled through claims frequency using Poisson regression and claims occurrence probability using machine learning models, including XGBoost and TabNet, and interpreted with SHAP. The dataset is divided into weekly profiles containing aggregated driving behavior, ADAS events, and contextual attributes. Results indicate that both modeling approaches show consistent attribute impacts on driver risk. For claims occurrence probability, XGBoost achieved the lowest Log Loss, reducing it from 0.59 to 0.51 with the inclusion of all attributes; for claims frequency, no statistically significant differences were observed when including all attributes. However, adding ADAS and contextual attributes allows for a comprehensive and disaggregated interpretation of the resulting weekly premium. This dynamic pricing can be incorporated into the insurance lifecycle, enabling bespoke risk assessment based on emerging technologies, the driving context, and driver behavior.
{"title":"Predictive Modeling for Driver Insurance Premium Calculation Using Advanced Driver Assistance Systems and Contextual Information","authors":"Leandro Masello;Barry Sheehan;German Castignani;Montserrat Guillen;Finbarr Murphy","doi":"10.1109/TITS.2024.3518572","DOIUrl":"https://doi.org/10.1109/TITS.2024.3518572","url":null,"abstract":"Telematics devices have transformed driver risk assessment, allowing insurers to tailor premiums based on detailed evaluations of driving habits. However, integrating Advanced Driver Assistance Systems (ADAS) and contextualized geolocation data for predictive improvements remains underexplored due to the recent emergence of these technologies. This article introduces a novel risk assessment methodology that periodically computes weekly insurance premiums by incorporating ADAS risk indicators and contextualized geolocation data. Using a naturalistic dataset from a fleet of 354 commercial drivers over a year, we modeled the relationship between past claims and driving data, and use that to compute weekly premiums that penalize risky driving situations. Risk predictions are modeled through claims frequency using Poisson regression and claims occurrence probability using machine learning models, including XGBoost and TabNet, and interpreted with SHAP. The dataset is divided into weekly profiles containing aggregated driving behavior, ADAS events, and contextual attributes. Results indicate that both modeling approaches show consistent attribute impacts on driver risk. For claims occurrence probability, XGBoost achieved the lowest Log Loss, reducing it from 0.59 to 0.51 with the inclusion of all attributes; for claims frequency, no statistically significant differences were observed when including all attributes. However, adding ADAS and contextual attributes allows for a comprehensive and disaggregated interpretation of the resulting weekly premium. This dynamic pricing can be incorporated into the insurance lifecycle, enabling bespoke risk assessment based on emerging technologies, the driving context, and driver behavior.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2202-2211"},"PeriodicalIF":7.9,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10834470","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143184010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-08DOI: 10.1109/TITS.2024.3519199
Taiyu Zhang;Zhengru Ren
Real-time sea state information plays a pivotal role in guiding decisions-making for various marine operations. Utilizing the wave buoy analogy (WBA) enables a cost-effective approach to estimating the wave spectrum through ship motion responses, providing an almost real-time estimation of the sea state. However, non-uniformly distributed response amplitude operators (RAOs) bring about performance deterioration in specific sea states, potentially leading to erroneous estimations that could misguide decision-making and result in severe consequences. Nevertheless, it is possible to combine multiple estimates in a rational manner to improve the robustness and accuracy of the WBA. In this study, the restricted isometry property is introduced to evaluate WBA performance. An RAO-driven assessment criterion is proposed to ascertain the reliability of estimates based solely on RAO input. Building upon this assessment criterion, we propose a multispectral fusion algorithm to amalgamate multiple estimates obtained from ships with different geometries and headings, ultimately generating a comprehensive fused result. Numerical experiments are described to demonstrate the proposed algorithm’s effectiveness.
{"title":"Restricted Isometry Property in Wave Buoy Analogy and Application to Multispectral Fusion","authors":"Taiyu Zhang;Zhengru Ren","doi":"10.1109/TITS.2024.3519199","DOIUrl":"https://doi.org/10.1109/TITS.2024.3519199","url":null,"abstract":"Real-time sea state information plays a pivotal role in guiding decisions-making for various marine operations. Utilizing the wave buoy analogy (WBA) enables a cost-effective approach to estimating the wave spectrum through ship motion responses, providing an almost real-time estimation of the sea state. However, non-uniformly distributed response amplitude operators (RAOs) bring about performance deterioration in specific sea states, potentially leading to erroneous estimations that could misguide decision-making and result in severe consequences. Nevertheless, it is possible to combine multiple estimates in a rational manner to improve the robustness and accuracy of the WBA. In this study, the restricted isometry property is introduced to evaluate WBA performance. An RAO-driven assessment criterion is proposed to ascertain the reliability of estimates based solely on RAO input. Building upon this assessment criterion, we propose a multispectral fusion algorithm to amalgamate multiple estimates obtained from ships with different geometries and headings, ultimately generating a comprehensive fused result. Numerical experiments are described to demonstrate the proposed algorithm’s effectiveness.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"1999-2010"},"PeriodicalIF":7.9,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183984","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}
For scalable autonomous driving, a robust map-based localization system, independent of GPS, is fundamental. To achieve such map-based localization, online high-definition (HD) map construction plays a significant role in accurate estimation of the pose. Although recent advancements in online HD map construction have predominantly investigated on vectorized representation due to its effectiveness, they suffer from computational cost and fixed parametric model, which limit scalability. To alleviate these limitations, we propose a novel HD map learning framework that leverages graph modeling. This framework is designed to learn the construction of diverse geometric shapes, thereby enhancing the scalability of HD map construction. Our approach involves representing the map elements as an instance-level graph by decomposing them into vertices and edges to facilitate accurate and efficient end-to-end vectorized HD map learning. Furthermore, we introduce an association strategy using a Graph Neural Network to efficiently handle the complex geometry of various map elements, while maintaining scalability. Comprehensive experiments on public open dataset show that our proposed network outperforms state-of-the-art model by 1.6 mAP. We further showcase the superior scalability of our approach compared to state-of-the-art methods, achieving a 4.8 mAP improvement in long range configuration. Our code is available at https://github.com/juyebshin/InstaGraM.
{"title":"InstaGraM: Instance-Level Graph Modeling for Vectorized HD Map Learning","authors":"Juyeb Shin;Hyeonjun Jeong;Francois Rameau;Dongsuk Kum","doi":"10.1109/TITS.2024.3518537","DOIUrl":"https://doi.org/10.1109/TITS.2024.3518537","url":null,"abstract":"For scalable autonomous driving, a robust map-based localization system, independent of GPS, is fundamental. To achieve such map-based localization, online high-definition (HD) map construction plays a significant role in accurate estimation of the pose. Although recent advancements in online HD map construction have predominantly investigated on vectorized representation due to its effectiveness, they suffer from computational cost and fixed parametric model, which limit scalability. To alleviate these limitations, we propose a novel HD map learning framework that leverages graph modeling. This framework is designed to learn the construction of diverse geometric shapes, thereby enhancing the scalability of HD map construction. Our approach involves representing the map elements as an instance-level graph by decomposing them into vertices and edges to facilitate accurate and efficient end-to-end vectorized HD map learning. Furthermore, we introduce an association strategy using a Graph Neural Network to efficiently handle the complex geometry of various map elements, while maintaining scalability. Comprehensive experiments on public open dataset show that our proposed network outperforms state-of-the-art model by 1.6 mAP. We further showcase the superior scalability of our approach compared to state-of-the-art methods, achieving a 4.8 mAP improvement in long range configuration. Our code is available at <uri>https://github.com/juyebshin/InstaGraM</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"1889-1899"},"PeriodicalIF":7.9,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183981","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}
Pub Date : 2025-01-06DOI: 10.1109/TITS.2024.3521514
Hong Zhu;Jialong Feng;Fengmei Sun;Keshuang Tang;Di Zang;Qi Kang
Treating each intersection as basic agent, multi-agent reinforcement learning (MARL) methods have emerged as the predominant approach for distributed adaptive traffic signal control (ATSC) in multi-intersection scenarios, such as arterial coordination. MARL-based ATSC currently faces two challenges: disturbances from the control policies of other intersections may impair the learning and control stability of the agents; and the heterogeneous features across intersections may complicate coordination efforts. To address these challenges, this study proposes a novel MARL method for distributed ATSC in arterials, termed the Distributed Controller for Heterogeneous Intersections (DCHI). The DCHI method introduces a Neighborhood Experience Sharing (NES) framework, wherein each agent utilizes both local data and shared experiences from adjacent intersections to improve its control policy. Within this framework, the neural networks of each agent are partitioned into two parts following the Knowledge Homogenizing Encapsulation (KHE) mechanism. The first part manages heterogeneous intersection features and transforms the control experiences, while the second part optimizes homogeneous control logic. Experimental results demonstrate that the proposed DCHI achieves efficiency improvements in average travel time of over 30% compared to traditional methods and yields similar performance to the centralized sharing method. Furthermore, vehicle trajectories reveal that DCHI can adaptively establish green wave bands in a distributed manner. Given its superior control performance, accommodation of heterogeneous intersections, and low reliance on information networks, DCHI could significantly advance the application of MARL-based ATSC methods in practice.
{"title":"Sharing Control Knowledge Among Heterogeneous Intersections: A Distributed Arterial Traffic Signal Coordination Method Using Multi-Agent Reinforcement Learning","authors":"Hong Zhu;Jialong Feng;Fengmei Sun;Keshuang Tang;Di Zang;Qi Kang","doi":"10.1109/TITS.2024.3521514","DOIUrl":"https://doi.org/10.1109/TITS.2024.3521514","url":null,"abstract":"Treating each intersection as basic agent, multi-agent reinforcement learning (MARL) methods have emerged as the predominant approach for distributed adaptive traffic signal control (ATSC) in multi-intersection scenarios, such as arterial coordination. MARL-based ATSC currently faces two challenges: disturbances from the control policies of other intersections may impair the learning and control stability of the agents; and the heterogeneous features across intersections may complicate coordination efforts. To address these challenges, this study proposes a novel MARL method for distributed ATSC in arterials, termed the Distributed Controller for Heterogeneous Intersections (DCHI). The DCHI method introduces a Neighborhood Experience Sharing (NES) framework, wherein each agent utilizes both local data and shared experiences from adjacent intersections to improve its control policy. Within this framework, the neural networks of each agent are partitioned into two parts following the Knowledge Homogenizing Encapsulation (KHE) mechanism. The first part manages heterogeneous intersection features and transforms the control experiences, while the second part optimizes homogeneous control logic. Experimental results demonstrate that the proposed DCHI achieves efficiency improvements in average travel time of over 30% compared to traditional methods and yields similar performance to the centralized sharing method. Furthermore, vehicle trajectories reveal that DCHI can adaptively establish green wave bands in a distributed manner. Given its superior control performance, accommodation of heterogeneous intersections, and low reliance on information networks, DCHI could significantly advance the application of MARL-based ATSC methods in practice.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2760-2776"},"PeriodicalIF":7.9,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183767","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}
Pub Date : 2025-01-06DOI: 10.1109/TITS.2024.3510515
Wenhao Ding;Haohong Lin;Bo Li;Ding Zhao
Generating adversarial scenes that potentially fail autonomous driving systems provides an effective way to improve their robustness. Extending purely data-driven generative models, recent specialized models satisfy additional controllable requirements such as embedding a traffic sign in a driving scene by manipulating patterns implicitly at the neuron level. In this paper, we introduce a method to incorporate domain knowledge explicitly in the generation process to achieve Semantically Adversarial Generation (SAG). To be consistent with the composition of driving scenes, we first categorize the knowledge into two types, the property of objects and the relationship among objects. We then propose a tree-structured variational auto-encoder (T-VAE) to learn hierarchical scene representation. By imposing semantic rules on the properties of nodes and edges into the tree structure, explicit knowledge integration enables controllable generation. To demonstrate the advantage of structural representation, we construct a synthetic example to illustrate the controllability and explainability of our method in a succinct setting. We further extend to realistic environments for autonomous vehicles, showing that our method efficiently identifies adversarial driving scenes against different state-of-the-art 3D point cloud segmentation models and satisfies the constraints specified as explicit knowledge.
{"title":"Semantically Adversarial Scene Generation With Explicit Knowledge Guidance","authors":"Wenhao Ding;Haohong Lin;Bo Li;Ding Zhao","doi":"10.1109/TITS.2024.3510515","DOIUrl":"https://doi.org/10.1109/TITS.2024.3510515","url":null,"abstract":"Generating adversarial scenes that potentially fail autonomous driving systems provides an effective way to improve their robustness. Extending purely data-driven generative models, recent specialized models satisfy additional controllable requirements such as embedding a traffic sign in a driving scene by manipulating patterns implicitly at the neuron level. In this paper, we introduce a method to incorporate domain knowledge explicitly in the generation process to achieve Semantically Adversarial Generation (SAG). To be consistent with the composition of driving scenes, we first categorize the knowledge into two types, the property of objects and the relationship among objects. We then propose a tree-structured variational auto-encoder (T-VAE) to learn hierarchical scene representation. By imposing semantic rules on the properties of nodes and edges into the tree structure, explicit knowledge integration enables controllable generation. To demonstrate the advantage of structural representation, we construct a synthetic example to illustrate the controllability and explainability of our method in a succinct setting. We further extend to realistic environments for autonomous vehicles, showing that our method efficiently identifies adversarial driving scenes against different state-of-the-art 3D point cloud segmentation models and satisfies the constraints specified as explicit knowledge.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"1510-1521"},"PeriodicalIF":7.9,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183814","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}
Pub Date : 2025-01-03DOI: 10.1109/TITS.2024.3509140
Feng Xue;Yicong Chang;Wenzhuang Xu;Wenteng Liang;Fei Sheng;Anlong Ming
Despite significant progress in RGB-D based road segmentation in recent years, the latest methods cannot achieve both state-of-the-art accuracy and real time due to the high-performance reliance on heavy structures. We argue that this reliance is due to unsuitable multimodal fusion. To be specific, RGB and depth data in road scenes are each sensitive to different regions, but current RGB-D based road segmentation methods generally combine features within sensitive regions which preserves false road representation from one of the data. Based on such findings, we design an Evidence-based Road Segmentation Method (Evi-RoadSeg), which incorporates prior knowledge of the modal-specific characteristics. Firstly, we abandon the cross-modal fusion operation commonly used in existing multimodal based methods. Instead, we collect the road evidence from RGB and depth inputs separately via two low-latency subnetworks, and fuse the road representation of the two subnetworks by taking both modalities’ evidence as a measure of confidence. Secondly, we propose an RGB-D data augmentation scheme tailored to road scenes to enhance the unique properties of RGB and depth data. It facilitates learning by adding more sensitive regions to the samples. Finally, the proposed method is evaluated on the widely used KITTI-road, ORFD, and R2D datasets. Our method achieves state-of-the-art accuracy at over 70 FPS, $5times $ faster than comparable RGB-D methods. Furthermore, extensive experiments illustrate that our method can be deployed on a Jetson Nano 2GB with a speed of 8+ FPS. The code will be released in https://github.com/xuefeng-cvr/Evi-RoadSeg.
{"title":"Evidence-Based Real-Time Road Segmentation With RGB-D Data Augmentation","authors":"Feng Xue;Yicong Chang;Wenzhuang Xu;Wenteng Liang;Fei Sheng;Anlong Ming","doi":"10.1109/TITS.2024.3509140","DOIUrl":"https://doi.org/10.1109/TITS.2024.3509140","url":null,"abstract":"Despite significant progress in RGB-D based road segmentation in recent years, the latest methods cannot achieve both state-of-the-art accuracy and real time due to the high-performance reliance on heavy structures. We argue that this reliance is due to unsuitable multimodal fusion. To be specific, RGB and depth data in road scenes are each sensitive to different regions, but current RGB-D based road segmentation methods generally combine features within sensitive regions which preserves false road representation from one of the data. Based on such findings, we design an Evidence-based Road Segmentation Method (Evi-RoadSeg), which incorporates prior knowledge of the modal-specific characteristics. Firstly, we abandon the cross-modal fusion operation commonly used in existing multimodal based methods. Instead, we collect the road evidence from RGB and depth inputs separately via two low-latency subnetworks, and fuse the road representation of the two subnetworks by taking both modalities’ evidence as a measure of confidence. Secondly, we propose an RGB-D data augmentation scheme tailored to road scenes to enhance the unique properties of RGB and depth data. It facilitates learning by adding more sensitive regions to the samples. Finally, the proposed method is evaluated on the widely used KITTI-road, ORFD, and R2D datasets. Our method achieves state-of-the-art accuracy at over 70 FPS, <inline-formula> <tex-math>$5times $ </tex-math></inline-formula> faster than comparable RGB-D methods. Furthermore, extensive experiments illustrate that our method can be deployed on a Jetson Nano 2GB with a speed of 8+ FPS. The code will be released in <uri>https://github.com/xuefeng-cvr/Evi-RoadSeg</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"1482-1493"},"PeriodicalIF":7.9,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183810","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}
Pub Date : 2025-01-03DOI: 10.1109/TITS.2024.3507639
Miguel Costa;Manuel Marques;Carlos Lima Azevedo;Felix Wilhelm Siebert;Filipe Moura
Cycling is critical for cities to transition to more sustainable transport modes. Yet, safety concerns remain a critical deterrent for individuals to cycle. If individuals perceive an environment as unsafe for cycling, it is likely that they will prefer other means of transportation. Yet, capturing and understanding how individuals perceive cycling risk is complex and often slow, with researchers defaulting to traditional surveys and in-loco interviews. In this study, we tackle this problem. We base our approach on using pairwise comparisons of real-world images, repeatedly presenting respondents with pairs of road environments and asking them to select the one they perceive as safer for cycling, if any. Using the collected data, we train a siamese-convolutional neural network using a multi-loss framework that learns from individuals’ responses, learns preferences directly from images, and includes ties (often discarded in the literature). Effectively, this model learns to predict human-style perceptions, evaluating which cycling environments are perceived as safer. Our model achieves good results, showcasing this approach has a real-life impact, such as improving interventions’ effectiveness. Furthermore, it facilitates the continuous assessment of changing cycling environments, permitting short-term evaluations of measures to enhance perceived cycling safety. Finally, our method can be efficiently deployed in different locations with a growing number of openly available street-view images.
{"title":"Which Cycling Environment Appears Safer? Learning Cycling Safety Perceptions From Pairwise Image Comparisons","authors":"Miguel Costa;Manuel Marques;Carlos Lima Azevedo;Felix Wilhelm Siebert;Filipe Moura","doi":"10.1109/TITS.2024.3507639","DOIUrl":"https://doi.org/10.1109/TITS.2024.3507639","url":null,"abstract":"Cycling is critical for cities to transition to more sustainable transport modes. Yet, safety concerns remain a critical deterrent for individuals to cycle. If individuals perceive an environment as unsafe for cycling, it is likely that they will prefer other means of transportation. Yet, capturing and understanding how individuals perceive cycling risk is complex and often slow, with researchers defaulting to traditional surveys and in-loco interviews. In this study, we tackle this problem. We base our approach on using pairwise comparisons of real-world images, repeatedly presenting respondents with pairs of road environments and asking them to select the one they perceive as safer for cycling, if any. Using the collected data, we train a siamese-convolutional neural network using a multi-loss framework that learns from individuals’ responses, learns preferences directly from images, and includes ties (often discarded in the literature). Effectively, this model learns to predict human-style perceptions, evaluating which cycling environments are perceived as safer. Our model achieves good results, showcasing this approach has a real-life impact, such as improving interventions’ effectiveness. Furthermore, it facilitates the continuous assessment of changing cycling environments, permitting short-term evaluations of measures to enhance perceived cycling safety. Finally, our method can be efficiently deployed in different locations with a growing number of openly available street-view images.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"1689-1700"},"PeriodicalIF":7.9,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183860","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}
Pub Date : 2024-12-31DOI: 10.1109/TITS.2024.3520393
Flávio Tonioli Mariotto;Néstor Becerra Yoma;Madson Cortes de Almeida
To make the proper planning of bus public transportation systems, especially with the introduction of electric buses to the fleets, it is essential to characterize the routes, patterns of traffic, speed, constraints, and presence of high slopes. Currently, GPS (Global Position System) is available worldwide in the fleet. However, they often produce datasets of poor quality, with low data rates, loss of information, noisy samples, and eventual paths not belonging to regular bus routes. Therefore, extracting useful information from these poor data is a challenging task. The current paper proposes a novel method based on an unsupervised competitive density clustering algorithm to obtain hot spot clusters of any density. The clusters are a result of their competition for the GPS samples. Each cluster attracts GPS samples until a maximum radius from its centroid and thereafter moves toward the most density areas. The winning clusters are sorted using a novel distance metric with the support of a visual interface, forming a sequence of points that outline the bus trajectory. Finally, indicators are correlated to the clusters making a trajectory characterization and allowing extensive assessments. According to the actual case studies, the method performs well with noisy GPS samples and the loss of information. The proposed method presents quite a fixed parameter, allowing fair performance for most GPS datasets without needing custom adjustments. It also proposes a framework for preparing the input GPS dataset, clustering, sorting the clusters to outline the trajectory, and making the trajectory characterization.
{"title":"Unsupervised Competitive Learning Clustering and Visual Method to Obtain Accurate Trajectories From Noisy Repetitive GPS Data","authors":"Flávio Tonioli Mariotto;Néstor Becerra Yoma;Madson Cortes de Almeida","doi":"10.1109/TITS.2024.3520393","DOIUrl":"https://doi.org/10.1109/TITS.2024.3520393","url":null,"abstract":"To make the proper planning of bus public transportation systems, especially with the introduction of electric buses to the fleets, it is essential to characterize the routes, patterns of traffic, speed, constraints, and presence of high slopes. Currently, GPS (Global Position System) is available worldwide in the fleet. However, they often produce datasets of poor quality, with low data rates, loss of information, noisy samples, and eventual paths not belonging to regular bus routes. Therefore, extracting useful information from these poor data is a challenging task. The current paper proposes a novel method based on an unsupervised competitive density clustering algorithm to obtain hot spot clusters of any density. The clusters are a result of their competition for the GPS samples. Each cluster attracts GPS samples until a maximum radius from its centroid and thereafter moves toward the most density areas. The winning clusters are sorted using a novel distance metric with the support of a visual interface, forming a sequence of points that outline the bus trajectory. Finally, indicators are correlated to the clusters making a trajectory characterization and allowing extensive assessments. According to the actual case studies, the method performs well with noisy GPS samples and the loss of information. The proposed method presents quite a fixed parameter, allowing fair performance for most GPS datasets without needing custom adjustments. It also proposes a framework for preparing the input GPS dataset, clustering, sorting the clusters to outline the trajectory, and making the trajectory characterization.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"1562-1572"},"PeriodicalIF":7.9,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143184007","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}
Pub Date : 2024-12-31DOI: 10.1109/TITS.2024.3504605
Kunyoung Lee;Hyunsoo Seo;Seunghyun Kim;Byeong Seon An;Shinwi Park;Yonggwon Jeon;Eui Chul Lee
Remote photoplethysmography (rPPG) is a method for monitoring pulse signal by utilizing a camera sensor to capture a facial video including variations in blood flow beneath the skin. Recently, rPPG advancements have enabled the measurement of an individual’s heart rate with a Root Mean Square Error (RMSE) of approximately 1.0 in controlled indoor environments. However, when applied in car dataset including driving environments, the RMSE of rPPG measurements significantly increases to over 9.07. This limitation, caused by motion-related artifacts and fluctuations in ambient illumination, becomes particularly noticeable while driving, resulting in a Percentage of Time that Error is less than 6 beats per minute (PTE6) of up to 65.1%. To address these limitations, we focus on the assessment of rPPG noise, with an emphasis on evaluating noise components within facial video and quantifying quality of the rPPG measurement. In this paper, we propose a deep learning framework that infers rPPG signal and quality based on video vision transformer. the proposed method demonstrates that the top 10% quality measurements yield PTE6 of 91.98% and 99.59% in driving and garage environments, respectively. Additionally, we introduce a quality-based rPPG compensation method that improves accuracy in driving environments by predicting rPPG quality based on noise assessment. This compensation method demonstrates superior accuracy compared to the current state-of-the-art, achieving a PTE6 of 68.24% in driving scenarios.
{"title":"Quality-Based rPPG Compensation With Temporal Difference Transformer for Camera-Based Driver Monitoring","authors":"Kunyoung Lee;Hyunsoo Seo;Seunghyun Kim;Byeong Seon An;Shinwi Park;Yonggwon Jeon;Eui Chul Lee","doi":"10.1109/TITS.2024.3504605","DOIUrl":"https://doi.org/10.1109/TITS.2024.3504605","url":null,"abstract":"Remote photoplethysmography (rPPG) is a method for monitoring pulse signal by utilizing a camera sensor to capture a facial video including variations in blood flow beneath the skin. Recently, rPPG advancements have enabled the measurement of an individual’s heart rate with a Root Mean Square Error (RMSE) of approximately 1.0 in controlled indoor environments. However, when applied in car dataset including driving environments, the RMSE of rPPG measurements significantly increases to over 9.07. This limitation, caused by motion-related artifacts and fluctuations in ambient illumination, becomes particularly noticeable while driving, resulting in a Percentage of Time that Error is less than 6 beats per minute (PTE6) of up to 65.1%. To address these limitations, we focus on the assessment of rPPG noise, with an emphasis on evaluating noise components within facial video and quantifying quality of the rPPG measurement. In this paper, we propose a deep learning framework that infers rPPG signal and quality based on video vision transformer. the proposed method demonstrates that the top 10% quality measurements yield PTE6 of 91.98% and 99.59% in driving and garage environments, respectively. Additionally, we introduce a quality-based rPPG compensation method that improves accuracy in driving environments by predicting rPPG quality based on noise assessment. This compensation method demonstrates superior accuracy compared to the current state-of-the-art, achieving a PTE6 of 68.24% in driving scenarios.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"1951-1963"},"PeriodicalIF":7.9,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183983","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}
Pub Date : 2024-12-30DOI: 10.1109/TITS.2024.3509381
Zhu Xiao;Bo Liu;Linshan Wu;Hongbo Jiang;Beihao Xia;Tao Li;Cassandra C. Wang
Carbon emissions caused by passenger cars in cities are essentially responsible for severe climate change and serious environmental problems. Exploring carbon emissions from passenger cars helps to control urban pollution and achieve urban sustainability. However, it is a challenging task to foresee the spatio-temporal distribution of carbon emission from passenger cars, as the following technical issues remain. i) Vehicle carbon emissions contain complex spatial interactions and temporal dynamics. How to collaboratively integrate such spatial-temporal correlations for carbon emission prediction is not yet resolved. ii) Given the mobility of passenger cars, the hidden dependencies inherent in traffic density are not properly addressed in predicting carbon emissions from passenger cars. To tackle these issues, we propose a Collaborative Spatial-temporal Network (CSTNet) for implementing carbon emissions prediction by using passenger car trajectory data. Within the proposed method, we devote to extract collaborative properties that stem from a multi-view graph structure together with parallel input of carbon emission and traffic density. Then, we design a spatial-temporal convolutional block for both carbon emission and traffic density, which constitutes of temporal gate convolution, spatial convolution and temporal attention mechanism. Following that, an interaction layer between carbon emission and traffic density is proposed to handle their internal dependencies, and further model spatial relationships between the features. Besides, we identify several global factors and embed them for final prediction with a collaborative fusion. Experimental results on the real-world passenger car trajectory dataset demonstrate that the proposed method outperforms the baselines with a roughly 7%-11% improvement.
{"title":"Exploring Spatio-Temporal Carbon Emission Across Passenger Car Trajectory Data","authors":"Zhu Xiao;Bo Liu;Linshan Wu;Hongbo Jiang;Beihao Xia;Tao Li;Cassandra C. Wang","doi":"10.1109/TITS.2024.3509381","DOIUrl":"https://doi.org/10.1109/TITS.2024.3509381","url":null,"abstract":"Carbon emissions caused by passenger cars in cities are essentially responsible for severe climate change and serious environmental problems. Exploring carbon emissions from passenger cars helps to control urban pollution and achieve urban sustainability. However, it is a challenging task to foresee the spatio-temporal distribution of carbon emission from passenger cars, as the following technical issues remain. i) Vehicle carbon emissions contain complex spatial interactions and temporal dynamics. How to collaboratively integrate such spatial-temporal correlations for carbon emission prediction is not yet resolved. ii) Given the mobility of passenger cars, the hidden dependencies inherent in traffic density are not properly addressed in predicting carbon emissions from passenger cars. To tackle these issues, we propose a Collaborative Spatial-temporal Network (CSTNet) for implementing carbon emissions prediction by using passenger car trajectory data. Within the proposed method, we devote to extract collaborative properties that stem from a multi-view graph structure together with parallel input of carbon emission and traffic density. Then, we design a spatial-temporal convolutional block for both carbon emission and traffic density, which constitutes of temporal gate convolution, spatial convolution and temporal attention mechanism. Following that, an interaction layer between carbon emission and traffic density is proposed to handle their internal dependencies, and further model spatial relationships between the features. Besides, we identify several global factors and embed them for final prediction with a collaborative fusion. Experimental results on the real-world passenger car trajectory dataset demonstrate that the proposed method outperforms the baselines with a roughly 7%-11% improvement.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"1812-1825"},"PeriodicalIF":7.9,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183991","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}
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：