Erlong Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Erlong Tan has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Li Li
School of Electronics and Control Engineering, Changan University, Xian, China
2 shared publications - Fei Hui
Chang’an University
1 shared publication - Junfei Zhang
School of Information Engineering, Changan University, Xian, China
1 shared publication Li‐Yong Zheng
Key Laboratory of Road and Traffic Engineering of the State Ministry of Education Tongji University Xi'an China
1 shared publication- Ru-Feng Bu
School of Electronics and Control Engineering, Changan University, Xian, China
1 shared publication - Runmin Wang
The School of Information Engineering, Chang'an University, Xi'an 710018, China
1 shared publication
Latest Publications
- Open Access
- 5 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Intelligent Transportation Systems
- Vol. 7, 759-770
Modeling Passenger Flow Congestion Propagation in Urban Rail Transit Network With an Epidemic Approach
Congestion in urban rail transit (URT) systems resulting from the surge in travel demands affects the safety operation. Understanding the mechanism behind congestion propagation can contribute to improving system safety. Epidemic models have been widely used to describe the spread of congestion within URT networks. This study introduces an enhanced version of the epidemic model, called the susceptible-alert-infected-susceptible (SAIS) model with awareness, which incorporates the alerting state. This addition enables us to describe the preventive response of metro stations to congestion propagation upon receiving warning information. Our model allows stations without congestion to transition to an “alert” state based on the occurrence of congestion in neighboring stations. The alert state signifies that the transit agency will implement congestion control measures to prevent the station from becoming congested. Thus, an alert metro station has a reduced likelihood of transitioning to a congested state. We demonstrate that the SAIS model can decrease the density of congested stations, increase the congestion propagation threshold, and reduce the extent of congestion propagation. We also conduct numerical simulations for a real-world instance on the Beijing URT network to support our analytical findings. Furthermore, we quantitatively assess the influence of different parameter values on congestion propagation.
- 5 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Intelligent Transportation Systems
- Vol. 7, 759-770
Open AccessModeling Passenger Flow Congestion Propagation in Urban Rail Transit Network With an Epidemic Approach
Congestion in urban rail transit (URT) systems resulting from the surge in travel demands affects the safety operation. Understanding the mechanism behind congestion propagation can contribute to improving system safety. Epidemic models have been widely used to describe the spread of congestion within URT networks. This study introduces an enhanced version of the epidemic model, called the susceptible-alert-infected-susceptible (SAIS) model with awareness, which incorporates the alerting state. This addition enables us to describe the preventive response of metro stations to congestion propagation upon receiving warning information. Our model allows stations without congestion to transition to an “alert” state based on the occurrence of congestion in neighboring stations. The alert state signifies that the transit agency will implement congestion control measures to prevent the station from becoming congested. Thus, an alert metro station has a reduced likelihood of transitioning to a congested state. We demonstrate that the SAIS model can decrease the density of congested stations, increase the congestion propagation threshold, and reduce the extent of congestion propagation. We also conduct numerical simulations for a real-world instance on the Beijing URT network to support our analytical findings. Furthermore, we quantitatively assess the influence of different parameter values on congestion propagation.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (3) , 3812-3819
Hierarchical Pairwise and Group-Wise Interaction Modeling for Efficient Pedestrian Trajectory Prediction
Accurate trajectory prediction in multi-agent environments is fundamental to understanding and forecasting collective motion in complex scenes. However, existing methods often struggle to capture the dynamic nature of interactions and higher-order group relationships. To address these challenges, we propose a novel framework that seamlessly integrates pairwise and group-wise interaction modeling. Our approach introduces a Step-wise Pairwise Interaction Modeling (SPIM) module to effectively capture dynamic interaction features over time, and a Hypergraph-based Global Interaction Modeling (HGIM) module to effectively model higher-order group relationships using adaptive hypergraph structures. Through the integration of these complementary modules within a unified multimodal decoder architecture, our method achieves competitive performance on the SDD and ETH-UCY datasets while significantly reducing model complexity. These results highlight the superior efficiency and effectiveness of our proposed approach.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (3) , 3812-3819
Hierarchical Pairwise and Group-Wise Interaction Modeling for Efficient Pedestrian Trajectory Prediction
Accurate trajectory prediction in multi-agent environments is fundamental to understanding and forecasting collective motion in complex scenes. However, existing methods often struggle to capture the dynamic nature of interactions and higher-order group relationships. To address these challenges, we propose a novel framework that seamlessly integrates pairwise and group-wise interaction modeling. Our approach introduces a Step-wise Pairwise Interaction Modeling (SPIM) module to effectively capture dynamic interaction features over time, and a Hypergraph-based Global Interaction Modeling (HGIM) module to effectively model higher-order group relationships using adaptive hypergraph structures. Through the integration of these complementary modules within a unified multimodal decoder architecture, our method achieves competitive performance on the SDD and ETH-UCY datasets while significantly reducing model complexity. These results highlight the superior efficiency and effectiveness of our proposed approach.
- 7 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-22
An Illumination-Adaptive Visual SLAM Algorithm With Lightweight Object Detection for Complex Dynamic Environments
Existing visual simultaneous localization and mapping (SLAM) algorithms excel in stable illumination variation and static environments, but struggle in dynamic environments with varying illumination. Object detection, an essential component for dynamic feature removal, imposes substantial computational burdens due to model architectural complexity. This study proposed a robust visual SLAM framework that fuses an illumination-adaptive thresholding feature point extraction module with a lightweight object detection network (YOLO+ShuffleNetV2+ EMA) to effectively separate dynamic and static features by improving feature point extraction and matching accuracy. The fusion module is deployed at the SLAM front-end and utilizes an independent threading mechanism to decouple the dynamic feature point removal process from the main pipeline. Furthermore, a back-end point cloud mapping module is introduced into the SLAM framework, which collaborates with an RGB-D camera and the YOLO+ShuffleNetV2+EMA network to eliminate dynamic object point clouds. Experimental results on indoor and outdoor datasets demonstrate that the proposed SLAM framework significantly enhances feature point processing capability and localization accuracy under varying illumination and dynamic environments. Under illumination conditions varying from 30% to 130% within the same scene, the adaptive thresholding method consistently maintains an average feature point count exceeding 1700, with an average variation of 784 feature points across different environments. The lightweight object detection network achieves a 70.72% reduction in parameter count and a 71.33% decrease in model size. In terms of localization accuracy, the framework achieves a maximum absolute trajectory error reduction of over 95% and a maximum sum of squared errors reduction of over 94%. The trajectories generated by the proposed SLAM algorithm closely align with the ground truth and enable real-time computation using CPU-only processing.
- 7 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-22
An Illumination-Adaptive Visual SLAM Algorithm With Lightweight Object Detection for Complex Dynamic Environments
Existing visual simultaneous localization and mapping (SLAM) algorithms excel in stable illumination variation and static environments, but struggle in dynamic environments with varying illumination. Object detection, an essential component for dynamic feature removal, imposes substantial computational burdens due to model architectural complexity. This study proposed a robust visual SLAM framework that fuses an illumination-adaptive thresholding feature point extraction module with a lightweight object detection network (YOLO+ShuffleNetV2+ EMA) to effectively separate dynamic and static features by improving feature point extraction and matching accuracy. The fusion module is deployed at the SLAM front-end and utilizes an independent threading mechanism to decouple the dynamic feature point removal process from the main pipeline. Furthermore, a back-end point cloud mapping module is introduced into the SLAM framework, which collaborates with an RGB-D camera and the YOLO+ShuffleNetV2+EMA network to eliminate dynamic object point clouds. Experimental results on indoor and outdoor datasets demonstrate that the proposed SLAM framework significantly enhances feature point processing capability and localization accuracy under varying illumination and dynamic environments. Under illumination conditions varying from 30% to 130% within the same scene, the adaptive thresholding method consistently maintains an average feature point count exceeding 1700, with an average variation of 784 feature points across different environments. The lightweight object detection network achieves a 70.72% reduction in parameter count and a 71.33% decrease in model size. In terms of localization accuracy, the framework achieves a maximum absolute trajectory error reduction of over 95% and a maximum sum of squared errors reduction of over 94%. The trajectories generated by the proposed SLAM algorithm closely align with the ground truth and enable real-time computation using CPU-only processing.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Intelligent Transport Systems
- Vol. 19 (1)
Heterogeneous Driver‐Aware Vehicle Trajectory Reconstruction and Fusion for Multiple Long‐Range Traffic Detectors
Traditional methods of vehicle trajectory reconstruction heavily rely on the data of cross‐sectional traffic detectors, but the effectiveness of existing methods is limited by insufficient information of the cross‐sectional data. In response to this, this study proposes a novel trajectory reconstruction method based on long‐range traffic detectors. It builds upon Newell's car‐following model and its derived inverse following model. By taking driver heterogeneity into account through individualised calibration of the key parameter, namely the spatial shift, which is optimised by the whale optimisation algorithm, the accuracy of trajectory reconstruction is enhanced. Furthermore, to connect trajectories of the same vehicle in the same area that are reconstructed by adjacent long‐range detectors, a particle filter‐based trajectory fusion method is developed. It can fuse overlapped reconstructed trajectories and smoothly connect sectional trajectories into a complete and seamlessly connected one. The performance of the trajectory reconstruction method is evaluated on the NGSIM I‐80 dataset, while the trajectory fusion method was tested on both the I‐80 and the TRJD TS datasets. Results show that the reconstruction method generates complete vehicle trajectories across various traffic flow conditions, achieving an average of 28.65% reduction in mean absolute error compared to methods that do not account for driver heterogeneity. The mean absolute error of the fused trajectories was reduced by 49.23% and 59.69% on average for two datasets, respectively, compared to reconstructed trajectories using a single detector. The trajectory reconstruction accuracy of the proposed method also outperforms that of a deep convolutional neural network and an improved adaptive smoothing method.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Intelligent Transport Systems
- Vol. 19 (1)
Open AccessHeterogeneous Driver‐Aware Vehicle Trajectory Reconstruction and Fusion for Multiple Long‐Range Traffic Detectors
Traditional methods of vehicle trajectory reconstruction heavily rely on the data of cross‐sectional traffic detectors, but the effectiveness of existing methods is limited by insufficient information of the cross‐sectional data. In response to this, this study proposes a novel trajectory reconstruction method based on long‐range traffic detectors. It builds upon Newell's car‐following model and its derived inverse following model. By taking driver heterogeneity into account through individualised calibration of the key parameter, namely the spatial shift, which is optimised by the whale optimisation algorithm, the accuracy of trajectory reconstruction is enhanced. Furthermore, to connect trajectories of the same vehicle in the same area that are reconstructed by adjacent long‐range detectors, a particle filter‐based trajectory fusion method is developed. It can fuse overlapped reconstructed trajectories and smoothly connect sectional trajectories into a complete and seamlessly connected one. The performance of the trajectory reconstruction method is evaluated on the NGSIM I‐80 dataset, while the trajectory fusion method was tested on both the I‐80 and the TRJD TS datasets. Results show that the reconstruction method generates complete vehicle trajectories across various traffic flow conditions, achieving an average of 28.65% reduction in mean absolute error compared to methods that do not account for driver heterogeneity. The mean absolute error of the fused trajectories was reduced by 49.23% and 59.69% on average for two datasets, respectively, compared to reconstructed trajectories using a single detector. The trajectory reconstruction accuracy of the proposed method also outperforms that of a deep convolutional neural network and an improved adaptive smoothing method.