Pub Date : 2025-01-17DOI: 10.1109/TITS.2024.3524582
Hanxuan Dong;Hailong Zhang;Fan Ding;Huachun Tan
Traffic state prediction, a classical task for traffic management, is a central component of intelligent transport systems to maintain safe and efficient operation. While extensive and intensive research has been conducted on traffic state prediction, most studies have concentrated on enhancing the accuracy of specific traffic state parameters. However, traffic state is a co-evolutionary multivariate time series with various parameters such as flow, velocity, occupancy, etc. At the same time, traffic state data will inevitably be lost during collection. So accurate traffic prediction still faces the following challenges: First, how to deal with the complex missing situations in observational data? Second, how to learn the co-evolutionary relationships between different traffic state parameters while mining the high-dimensional spatio-temporal traffic state patterns? In this paper, we propose a mechanism-data blending-driven co-evolving traffic state parameter prediction method: multi-parameter hybrid tensor deep learning networks (MHT-Net), which consists of a multi-parameter tensor graph convolutional network (MTGCN) and a tensor recurrent neural network (T-RNN). MTGCN implements knowledge embedding of synergistic mechanisms between traffic parameters, ensuring that the road network spatial dependency and the synergistic influence relationship of the parameters can be obtained simultaneously; T-RNN is used to learn high-dimensional temporal features of traffic states. Experiment results on a real-world dataset from Jiangsu province outperform the state-of-the-art baselines, demonstrating the efficacy of the proposed method and providing an effective tool for traffic state prediction with missing values. A mechanism-data blending driven co-evolving traffic state parameter prediction method, multi-parameters hybrid tensor deep learning networks (MHT-Net) is proposed, which implements knowledge embedding of synergistic mechanisms between traffic parameters and learn the road network spatial dependency and the synergistic influence relationship of the parameters simultaneously. Experiment results demonstrate the efficacy of the proposed method and provide an effective tool for traffic state prediction with missing values.
{"title":"Co-Evolving Traffic State Parameters Prediction Based on Mechanism-Data Blending Driven Deep Learning","authors":"Hanxuan Dong;Hailong Zhang;Fan Ding;Huachun Tan","doi":"10.1109/TITS.2024.3524582","DOIUrl":"https://doi.org/10.1109/TITS.2024.3524582","url":null,"abstract":"Traffic state prediction, a classical task for traffic management, is a central component of intelligent transport systems to maintain safe and efficient operation. While extensive and intensive research has been conducted on traffic state prediction, most studies have concentrated on enhancing the accuracy of specific traffic state parameters. However, traffic state is a co-evolutionary multivariate time series with various parameters such as flow, velocity, occupancy, etc. At the same time, traffic state data will inevitably be lost during collection. So accurate traffic prediction still faces the following challenges: First, how to deal with the complex missing situations in observational data? Second, how to learn the co-evolutionary relationships between different traffic state parameters while mining the high-dimensional spatio-temporal traffic state patterns? In this paper, we propose a mechanism-data blending-driven co-evolving traffic state parameter prediction method: multi-parameter hybrid tensor deep learning networks (MHT-Net), which consists of a multi-parameter tensor graph convolutional network (MTGCN) and a tensor recurrent neural network (T-RNN). MTGCN implements knowledge embedding of synergistic mechanisms between traffic parameters, ensuring that the road network spatial dependency and the synergistic influence relationship of the parameters can be obtained simultaneously; T-RNN is used to learn high-dimensional temporal features of traffic states. Experiment results on a real-world dataset from Jiangsu province outperform the state-of-the-art baselines, demonstrating the efficacy of the proposed method and providing an effective tool for traffic state prediction with missing values. A mechanism-data blending driven co-evolving traffic state parameter prediction method, multi-parameters hybrid tensor deep learning networks (MHT-Net) is proposed, which implements knowledge embedding of synergistic mechanisms between traffic parameters and learn the road network spatial dependency and the synergistic influence relationship of the parameters simultaneously. Experiment results demonstrate the efficacy of the proposed method and provide an effective tool for traffic state prediction with missing values.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3084-3100"},"PeriodicalIF":7.9,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535569","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}
Vehicle detection based on remote sensing images is widely used in urban traffic management and disaster rescue. RGB images, which are used more, lead to poor detection performance in low light conditions due to the imaging mechanism. At present, the main solution is to improve the detection performance in low light by fusing with infrared images. However, the current methods often overlook the impact of illumination changes on RGB images, and ignore the important role of high-frequency information for object detection, especially for low-light target detection. In this paper, we propose a Cross-modality and Cross-domain Low-light Detector (CCLDet) for low-light vehicle detection, including three improvements. First, an object illumination-aware module (OIAM) is proposed, which can adjust adaptively the weight of different modalities according to the object illumination intensity in the training phase and enables the detector to adapt to different lighting conditions. Second, we propose a visibility loss, which converts the position deviation into the illumination intensity deviation of each point in the object area. Compared with relying only on semantic information for object localization, the illumination makes the information that can be used for localization more abundant. Third, we design a cross-domain feature fusion module (CDFFM), which can enhance high-frequency features and enrich target information when low-frequency features are lost due to low light pollution. Extensive experiments on three challenging RGB-infrared objects detection datasets demonstrated the mAP and the parameter quantities of CCLDet over popular object detectors.
{"title":"CCLDet: A Cross-Modality and Cross-Domain Low-Light Detector","authors":"Xiping Shang;Nannan Li;Dongjin Li;Jianwei Lv;Wei Zhao;Rufei Zhang;Jingyu Xu","doi":"10.1109/TITS.2024.3522086","DOIUrl":"https://doi.org/10.1109/TITS.2024.3522086","url":null,"abstract":"Vehicle detection based on remote sensing images is widely used in urban traffic management and disaster rescue. RGB images, which are used more, lead to poor detection performance in low light conditions due to the imaging mechanism. At present, the main solution is to improve the detection performance in low light by fusing with infrared images. However, the current methods often overlook the impact of illumination changes on RGB images, and ignore the important role of high-frequency information for object detection, especially for low-light target detection. In this paper, we propose a Cross-modality and Cross-domain Low-light Detector (CCLDet) for low-light vehicle detection, including three improvements. First, an object illumination-aware module (OIAM) is proposed, which can adjust adaptively the weight of different modalities according to the object illumination intensity in the training phase and enables the detector to adapt to different lighting conditions. Second, we propose a visibility loss, which converts the position deviation into the illumination intensity deviation of each point in the object area. Compared with relying only on semantic information for object localization, the illumination makes the information that can be used for localization more abundant. Third, we design a cross-domain feature fusion module (CDFFM), which can enhance high-frequency features and enrich target information when low-frequency features are lost due to low light pollution. Extensive experiments on three challenging RGB-infrared objects detection datasets demonstrated the mAP and the parameter quantities of CCLDet over popular object detectors.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3284-3294"},"PeriodicalIF":7.9,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535538","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}
The safety and efficiency of an Autonomous Vehicle (AV) manoeuvre planning heavily depend on the future trajectories of surrounding vehicles. If an AV can predict its surrounding vehicles’ future trajectories, it can make safe and efficient manoeuvre decisions. In this paper, we present a Deep Spatio-Temporal Context-Aware decision Network (DST-CAN) for predictive manoeuvre decisions for AVs on highways. DST-CAN has two main components, namely spatio-temporal context-aware map generator and predictive manoeuvre decisions engine. DST-CAN employ a memory neuron network to predict the future trajectories of its surrounding vehicles. Using look-ahead prediction and past actual trajectories, a spatio-temporal context-aware probability occupancy map is generated. These context-aware maps as input to a decision engine generate a safe and efficient manoeuvre decision. Here, CNN helps extract feature space, and two fully connected network generates longitudinal and lateral manoeuvre decisions. Performance evaluation of DST-CAN has been carried out using two publicly available NGSIM US-101 and I-80 highway datasets. A traffic rule is defined to generate ground truths for these datasets in addition to human decisions. Two DST-CAN models are trained using imitation learning with human driving decisions from actual traffic data and rule-based ground truth decisions. The performances of the DST-CAN models are compared with the state-of-the-art Convolutional Social-LSTM (CS-LSTM) models for manoeuvre prediction. The results clearly indicate that the context-aware maps help DST-CAN to predict the decision accurately over CS-LSTM. Further, an ablation study has been carried out to understand the effect of prediction horizons of performance and a robustness study to understand the near collision scenarios over actual traffic observations. The context-aware map with a 3 second prediction horizon is robust against near collision.
{"title":"An Efficient Deep Spatio-Temporal Context Aware Decision Network (DST-CAN) for Predictive Manoeuvre Planning on Highways","authors":"Jayabrata Chowdhury;Suresh Sundaram;Nishanth Rao;Narasimman Sundararajan","doi":"10.1109/TITS.2024.3522971","DOIUrl":"https://doi.org/10.1109/TITS.2024.3522971","url":null,"abstract":"The safety and efficiency of an Autonomous Vehicle (AV) manoeuvre planning heavily depend on the future trajectories of surrounding vehicles. If an AV can predict its surrounding vehicles’ future trajectories, it can make safe and efficient manoeuvre decisions. In this paper, we present a Deep Spatio-Temporal Context-Aware decision Network (DST-CAN) for predictive manoeuvre decisions for AVs on highways. DST-CAN has two main components, namely spatio-temporal context-aware map generator and predictive manoeuvre decisions engine. DST-CAN employ a memory neuron network to predict the future trajectories of its surrounding vehicles. Using look-ahead prediction and past actual trajectories, a spatio-temporal context-aware probability occupancy map is generated. These context-aware maps as input to a decision engine generate a safe and efficient manoeuvre decision. Here, CNN helps extract feature space, and two fully connected network generates longitudinal and lateral manoeuvre decisions. Performance evaluation of DST-CAN has been carried out using two publicly available NGSIM US-101 and I-80 highway datasets. A traffic rule is defined to generate ground truths for these datasets in addition to human decisions. Two DST-CAN models are trained using imitation learning with human driving decisions from actual traffic data and rule-based ground truth decisions. The performances of the DST-CAN models are compared with the state-of-the-art Convolutional Social-LSTM (CS-LSTM) models for manoeuvre prediction. The results clearly indicate that the context-aware maps help DST-CAN to predict the decision accurately over CS-LSTM. Further, an ablation study has been carried out to understand the effect of prediction horizons of performance and a robustness study to understand the near collision scenarios over actual traffic observations. The context-aware map with a 3 second prediction horizon is robust against near collision.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"2944-2954"},"PeriodicalIF":7.9,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535416","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 : 2025-01-16DOI: 10.1109/TITS.2024.3521974
Yuhao Wang;Pingping Zhang;Xuehu Liu;Zhengzheng Tu;Huchuan Lu
Person Re-identification (ReID) aims to retrieve the specific person across non-overlapping cameras, which greatly helps intelligent transportation systems. As we all know, Convolutional Neural Networks (CNNs) and Transformers have the unique strengths to extract local and global features, respectively. Considering this fact, we focus on the mutual fusion between them to learn more comprehensive representations for persons. In particular, we utilize the complementary integration of deep features from different model structures. We propose a novel fusion framework called FusionReID to unify the strengths of CNNs and Transformers for image-based person ReID. More specifically, we first deploy a Dual-branch Feature Extraction (DFE) to extract features through CNNs and Transformers from a single image. Moreover, we design a novel Dual-attention Mutual Fusion (DMF) to achieve sufficient feature fusions. The DMF comprises Local Refinement Units (LRU) and Heterogenous Transmission Modules (HTM). LRU utilizes depth-separable convolutions to align deep features in channel dimensions and spatial sizes. HTM consists of a Shared Encoding Unit (SEU) and two Mutual Fusion Units (MFU). Through the continuous stacking of HTM, deep features after LRU are repeatedly utilized to generate more discriminative features. Extensive experiments on three public ReID benchmarks demonstrate that our method can attain superior performances than most state-of-the-arts. The source code is available at https://github.com/924973292/FusionReID.
{"title":"Unity Is Strength: Unifying Convolutional and Transformeral Features for Better Person Re-Identification","authors":"Yuhao Wang;Pingping Zhang;Xuehu Liu;Zhengzheng Tu;Huchuan Lu","doi":"10.1109/TITS.2024.3521974","DOIUrl":"https://doi.org/10.1109/TITS.2024.3521974","url":null,"abstract":"Person Re-identification (ReID) aims to retrieve the specific person across non-overlapping cameras, which greatly helps intelligent transportation systems. As we all know, Convolutional Neural Networks (CNNs) and Transformers have the unique strengths to extract local and global features, respectively. Considering this fact, we focus on the mutual fusion between them to learn more comprehensive representations for persons. In particular, we utilize the complementary integration of deep features from different model structures. We propose a novel fusion framework called FusionReID to unify the strengths of CNNs and Transformers for image-based person ReID. More specifically, we first deploy a Dual-branch Feature Extraction (DFE) to extract features through CNNs and Transformers from a single image. Moreover, we design a novel Dual-attention Mutual Fusion (DMF) to achieve sufficient feature fusions. The DMF comprises Local Refinement Units (LRU) and Heterogenous Transmission Modules (HTM). LRU utilizes depth-separable convolutions to align deep features in channel dimensions and spatial sizes. HTM consists of a Shared Encoding Unit (SEU) and two Mutual Fusion Units (MFU). Through the continuous stacking of HTM, deep features after LRU are repeatedly utilized to generate more discriminative features. Extensive experiments on three public ReID benchmarks demonstrate that our method can attain superior performances than most state-of-the-arts. The source code is available at <uri>https://github.com/924973292/FusionReID</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3713-3723"},"PeriodicalIF":7.9,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563910","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 : 2025-01-16DOI: 10.1109/TITS.2024.3524673
Bo Zhang;Zhihua Chen;Linlin Zang;Peng Guo;Rui Miao
Intelligent and efficient energy supply management lays an essential foundation for urban governance and electric vehicle (EV) industry. Specifically, battery swapping is a novel mode of power supply for EVs. However, the new way of energy supply complicates the action policies of EVs, especially when the number of power supply facilities is limited. To address this issue, this paper proposes a multilevel deep reinforcement learning (DRL) method to coordinate the action of EVs within the battery charging and swapping station (BCSS) environment. Firstly, an action-driven simulation framework is developed to simulate the BCSS environment and obtain the EVs’ attributes. Then the multilevel algorithm is proposed to drive the EVs to obtain charging strategies. In the multilevel algorithm, the initial decision for EVs is provided by a DRL-based model. Then the advantage value function is utilized to adjust the initial decision of EVs to meet the constraints of limited charging and swapping equipment. Besides, unlike traditional DRL-based methods, the proposed model is driven by the rewards obtained from EV actions. Finally, extensive experiments have shown that the proposed multilevel DRL-based method has superior performance over existing methods in resolving coordinated battery charging and swapping actions. In particular, the proposed model can provide a suggested and reasonable price range for the practical battery swapping mode operation.
{"title":"Coordinated Battery Charging and Swapping Scheduling of EVs Based on Multilevel Deep Reinforcement Learning for Urban Governance","authors":"Bo Zhang;Zhihua Chen;Linlin Zang;Peng Guo;Rui Miao","doi":"10.1109/TITS.2024.3524673","DOIUrl":"https://doi.org/10.1109/TITS.2024.3524673","url":null,"abstract":"Intelligent and efficient energy supply management lays an essential foundation for urban governance and electric vehicle (EV) industry. Specifically, battery swapping is a novel mode of power supply for EVs. However, the new way of energy supply complicates the action policies of EVs, especially when the number of power supply facilities is limited. To address this issue, this paper proposes a multilevel deep reinforcement learning (DRL) method to coordinate the action of EVs within the battery charging and swapping station (BCSS) environment. Firstly, an action-driven simulation framework is developed to simulate the BCSS environment and obtain the EVs’ attributes. Then the multilevel algorithm is proposed to drive the EVs to obtain charging strategies. In the multilevel algorithm, the initial decision for EVs is provided by a DRL-based model. Then the advantage value function is utilized to adjust the initial decision of EVs to meet the constraints of limited charging and swapping equipment. Besides, unlike traditional DRL-based methods, the proposed model is driven by the rewards obtained from EV actions. Finally, extensive experiments have shown that the proposed multilevel DRL-based method has superior performance over existing methods in resolving coordinated battery charging and swapping actions. In particular, the proposed model can provide a suggested and reasonable price range for the practical battery swapping mode operation.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3784-3798"},"PeriodicalIF":7.9,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564242","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 : 2025-01-16DOI: 10.1109/TITS.2025.3525765
Dan Bao;Ronghua Guo
A novel intelligent reflecting surface (IRS) aided dual-function radar-communication (DFRC) system is proposed in this paper. IRSs are not only used to improve communication channels, but also employed as cooperative intelligent targets to enhance some objects of interest, such as vehicles and pedestrians in an intelligent transportation system. The optimal design objective function is to maximize the radar performance, while keeping the communication rate constant. The measure of radar performance is the Cramér-Rao bound (CRB) of the direction of departure (DOD), which is a special capability of a collocated antenna array multiple input multiple output (MIMO) radar. The joint optimization process comprises two steps, namely the passive optimization of IRSs and the active transmit beamforming. Due to the non-convexity of the optimization problem, a solver based on semidefinite relaxation (SDR) is proposed. Simulation experiments show the ability of the proposed optimization algorithm to balance the radar performance and the communication rate.
{"title":"A Dual Function Intelligent Reflecting Surface in Integrated Radar Communication System","authors":"Dan Bao;Ronghua Guo","doi":"10.1109/TITS.2025.3525765","DOIUrl":"https://doi.org/10.1109/TITS.2025.3525765","url":null,"abstract":"A novel intelligent reflecting surface (IRS) aided dual-function radar-communication (DFRC) system is proposed in this paper. IRSs are not only used to improve communication channels, but also employed as cooperative intelligent targets to enhance some objects of interest, such as vehicles and pedestrians in an intelligent transportation system. The optimal design objective function is to maximize the radar performance, while keeping the communication rate constant. The measure of radar performance is the Cramér-Rao bound (CRB) of the direction of departure (DOD), which is a special capability of a collocated antenna array multiple input multiple output (MIMO) radar. The joint optimization process comprises two steps, namely the passive optimization of IRSs and the active transmit beamforming. Due to the non-convexity of the optimization problem, a solver based on semidefinite relaxation (SDR) is proposed. Simulation experiments show the ability of the proposed optimization algorithm to balance the radar performance and the communication rate.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3471-3481"},"PeriodicalIF":7.9,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535425","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 : 2025-01-16DOI: 10.1109/TITS.2025.3525772
Huihui Pan;Yisong Jia;Jue Wang;Weichao Sun
Monocular 3D object detection finds applications in various fields, notably in intelligent driving, due to its cost-effectiveness and ease of deployment. However, its accuracy significantly lags behind LiDAR-based methods, primarily because the monocular depth estimation problem is inherently challenging. While some methods leverage additional information to aid in network training and enhance performance, they are hindered by their reliance on specific datasets. We contend that many components of monocular 3D object detection lack the necessary adaptability, impeding the performance of the detector. In this paper, we propose six adaptive methods addressing issues related to network structure, loss function, and optimizer. These methods specifically target the rigid components within the detector that hinder adaptability. Simultaneously, we provide theoretical insights into the network output and propose two novel regression methods. These methods facilitate more straightforward learning for the network. Importantly, our approach does not depend on supplementary information, allowing for end-to-end training. In comparison with existing methods, our proposed approach demonstrates competitive speed and accuracy. On the KITTI dataset, our method achieves a 17.72% AP3D(IOU =0.7, Car, Moderate), outperforming all previous monocular methods. Additionally, our approach prioritizes speed, achieving a runtime of up to 52 FPS on an RTX 2080Ti GPU, surpassing all previous monocular methods. The source codes are at: https://github.com/jiayisong/AMNet.
{"title":"MonoAMNet: Three-Stage Real-Time Monocular 3D Object Detection With Adaptive Methods","authors":"Huihui Pan;Yisong Jia;Jue Wang;Weichao Sun","doi":"10.1109/TITS.2025.3525772","DOIUrl":"https://doi.org/10.1109/TITS.2025.3525772","url":null,"abstract":"Monocular 3D object detection finds applications in various fields, notably in intelligent driving, due to its cost-effectiveness and ease of deployment. However, its accuracy significantly lags behind LiDAR-based methods, primarily because the monocular depth estimation problem is inherently challenging. While some methods leverage additional information to aid in network training and enhance performance, they are hindered by their reliance on specific datasets. We contend that many components of monocular 3D object detection lack the necessary adaptability, impeding the performance of the detector. In this paper, we propose six adaptive methods addressing issues related to network structure, loss function, and optimizer. These methods specifically target the rigid components within the detector that hinder adaptability. Simultaneously, we provide theoretical insights into the network output and propose two novel regression methods. These methods facilitate more straightforward learning for the network. Importantly, our approach does not depend on supplementary information, allowing for end-to-end training. In comparison with existing methods, our proposed approach demonstrates competitive speed and accuracy. On the KITTI dataset, our method achieves a 17.72% AP3D(IOU =0.7, Car, Moderate), outperforming all previous monocular methods. Additionally, our approach prioritizes speed, achieving a runtime of up to 52 FPS on an RTX 2080Ti GPU, surpassing all previous monocular methods. The source codes are at: <uri>https://github.com/jiayisong/AMNet</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3574-3587"},"PeriodicalIF":7.9,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564212","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 : 2025-01-16DOI: 10.1109/TITS.2025.3526318
Jiwan Jiang;Yang Zhou;Ghazaleh Jafarsalehi;Xin Wang;Soyoung Ahn;John D. Lee
This paper presents a stochastic calibration method based on Approximate Bayesian Computation (ABC). This method is applied to calibrate two car-following control models: linear control and model predictive control (MPC). The method is likelihood-function-free, where the likelihood function is replaced by simulation to approximate the posterior distribution of model parameters. This structure affords flexibility to calibrate posterior joint distributions of complex models, even those without analytical closed forms such as MPC. Two experiments were conducted to evaluate how well the proposed method reproduces: (i) marginal and joint distributions of model parameters, using synthetic data and (ii) vehicle trajectories (acceleration, speed, and position), using field data involving two commercial adaptive cruise control (ACC) systems. The results showed that the ABC method can reproduce marginal and joint distributions reasonably well for the linear controller as well as the non-analytical MPC-based controller, which was previously infeasible. The method can also robustly characterize the commercial ACC behavior at the trajectory level, which suggests that the simple linear controller better describes their behavior.
{"title":"Stochastic Calibration of Automated Vehicle Car-Following Control: An Approximate Bayesian Computation Approach","authors":"Jiwan Jiang;Yang Zhou;Ghazaleh Jafarsalehi;Xin Wang;Soyoung Ahn;John D. Lee","doi":"10.1109/TITS.2025.3526318","DOIUrl":"https://doi.org/10.1109/TITS.2025.3526318","url":null,"abstract":"This paper presents a stochastic calibration method based on Approximate Bayesian Computation (ABC). This method is applied to calibrate two car-following control models: linear control and model predictive control (MPC). The method is likelihood-function-free, where the likelihood function is replaced by simulation to approximate the posterior distribution of model parameters. This structure affords flexibility to calibrate posterior joint distributions of complex models, even those without analytical closed forms such as MPC. Two experiments were conducted to evaluate how well the proposed method reproduces: (i) marginal and joint distributions of model parameters, using synthetic data and (ii) vehicle trajectories (acceleration, speed, and position), using field data involving two commercial adaptive cruise control (ACC) systems. The results showed that the ABC method can reproduce marginal and joint distributions reasonably well for the linear controller as well as the non-analytical MPC-based controller, which was previously infeasible. The method can also robustly characterize the commercial ACC behavior at the trajectory level, which suggests that the simple linear controller better describes their behavior.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3115-3127"},"PeriodicalIF":7.9,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535541","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 : 2025-01-16DOI: 10.1109/TITS.2024.3515074
Joseph Paul;Krishna Murthy Gurumurthy;Taner Cokyasar;Haotian Su;Nazmul Khan;Josh Auld;Yunyi Jia
This study analyzes various human factors considerations in estimating discounts for pooled rideshare trips. The discounts are utilized in an optimization-based rideshare assignment strategy (proactive strategy) and compared against each other, as well as a heuristic strategy attempting to replicate current real-world pooling rates. Simulations within Austin, Texas and Greenville, South Carolina, reveal the proactive strategy’s ability to increase average vehicle occupancy by 0.23 persons/mile in Austin and 0.52 persons/mile in Greenville. A significant ability to decrease trip rejections and increase profitability is also observed. Finally, the strengths of particular combinations of factors are discussed relative to their effectiveness in each region.
{"title":"Proactive Assignment Strategy With Human Choice Models for Boosting Pooled Rideshare Service","authors":"Joseph Paul;Krishna Murthy Gurumurthy;Taner Cokyasar;Haotian Su;Nazmul Khan;Josh Auld;Yunyi Jia","doi":"10.1109/TITS.2024.3515074","DOIUrl":"https://doi.org/10.1109/TITS.2024.3515074","url":null,"abstract":"This study analyzes various human factors considerations in estimating discounts for pooled rideshare trips. The discounts are utilized in an optimization-based rideshare assignment strategy (proactive strategy) and compared against each other, as well as a heuristic strategy attempting to replicate current real-world pooling rates. Simulations within Austin, Texas and Greenville, South Carolina, reveal the proactive strategy’s ability to increase average vehicle occupancy by 0.23 persons/mile in Austin and 0.52 persons/mile in Greenville. A significant ability to decrease trip rejections and increase profitability is also observed. Finally, the strengths of particular combinations of factors are discussed relative to their effectiveness in each region.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2351-2365"},"PeriodicalIF":7.9,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183990","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 : 2025-01-16DOI: 10.1109/TITS.2024.3520424
Zhaoying Liu;Yuxiang Zhang;Junran He;Ting Zhang;Sadaqat Ur Rehman;Mohamad Saraee;Changming Sun
Object detection in infrared images poses a considerable challenge due to its small-scale targets, low contrast and poor signal-to-clutter ratio, often resulting in a high false alarm rate. To improve the detection accuracy on infrared small targets, we introduce Light-SGMTLM, a lightweight and saliency-guided multi-task learning model. This model integrates saliency detection into the YOLOv5x framework through a parallel multi-task learning structure and employs a joint loss function during training. Such integration significantly alleviates the impact of complex backgrounds and improves the precision of small target localization. Moreover, we have developed a streamlined module, termed SIWD, to create a more agile backbone, which establishes an optimal balance between precision and efficiency, making the model more suitable for situations with limited computational resources. Comprehensive comparative experiments were conducted on six infrared small target datasets, namely, Small-ExtIRShip, Small-SSDD, IHAST, NUAA-SIRST, IRSTD-1k, and IRDST, and we assessed the model’s performance against ten leading target detection models, such as YOLOv7, YOLOv8, DINO, and Relation-DETR. The findings reveal that our method’s unique joint learning architecture, combining saliency and object detection tasks, significantly improves accuracy for infrared small target detection. Notably, it achieved impressive mean average precision (mAP) values of 92.60% and 75.71% on the NUAA-SIRST and IRSTD-1k datasets, respectively.
{"title":"Enhancing Infrared Small Target Detection: A Saliency-Guided Multi-Task Learning Approach","authors":"Zhaoying Liu;Yuxiang Zhang;Junran He;Ting Zhang;Sadaqat Ur Rehman;Mohamad Saraee;Changming Sun","doi":"10.1109/TITS.2024.3520424","DOIUrl":"https://doi.org/10.1109/TITS.2024.3520424","url":null,"abstract":"Object detection in infrared images poses a considerable challenge due to its small-scale targets, low contrast and poor signal-to-clutter ratio, often resulting in a high false alarm rate. To improve the detection accuracy on infrared small targets, we introduce Light-SGMTLM, a lightweight and saliency-guided multi-task learning model. This model integrates saliency detection into the YOLOv5x framework through a parallel multi-task learning structure and employs a joint loss function during training. Such integration significantly alleviates the impact of complex backgrounds and improves the precision of small target localization. Moreover, we have developed a streamlined module, termed SIWD, to create a more agile backbone, which establishes an optimal balance between precision and efficiency, making the model more suitable for situations with limited computational resources. Comprehensive comparative experiments were conducted on six infrared small target datasets, namely, Small-ExtIRShip, Small-SSDD, IHAST, NUAA-SIRST, IRSTD-1k, and IRDST, and we assessed the model’s performance against ten leading target detection models, such as YOLOv7, YOLOv8, DINO, and Relation-DETR. The findings reveal that our method’s unique joint learning architecture, combining saliency and object detection tasks, significantly improves accuracy for infrared small target detection. Notably, it achieved impressive mean average precision (mAP) values of 92.60% and 75.71% on the NUAA-SIRST and IRSTD-1k datasets, respectively.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3603-3618"},"PeriodicalIF":7.9,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564260","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：