Chunmian Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chunmian Lin has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Daxin Tian
Beijing Advanced Innovation Center for Big Data and Brain Computing, Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control, School of Transportation Science and Engineering, Beihang University, Beijing, China
15 shared publications - Xuting Duan
State Key Lab of Intelligent Transportation System, Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control, School of Transportation Science and Engineering, Beihang University, Beijing, China
15 shared publications - Jianshan Zhou
State Key Lab of Intelligent Transportation System, Beihang University, Beijing, China
14 shared publications - Dezong Zhao
University of Glasgow, Glasgow, United Kingdom
8 shared publications - Dongpu Cao
Tsinghua University
7 shared publications - Kaige Qu
Beihang University
5 shared publications
Latest Publications
- Open Access
- 30 September 2026
- Published by Tsinghua University Press
- Vol. 6 (3)
TWM: Multimodal data generation engine via traffic world model
Generative modeling has emerged as a mainstream paradigm for data synthesis, offering a promising solution to data scarcity and insufficient coverage of long-tail scenarios. Despite remarkable progress in autonomous driving (AD), its potential for traffic data generation from roadside or infrastructure perspectives remains largely underexplored. To this end, we proposed the first traffic-oriented world model termed the traffic world model (TWM) for controllable and high-fidelity multimodal data generation. It was built upon a unified conditional diffusion transformer (cDiT) architecture, which generated a controllable roadside-view image from a structured road-agent layout, and the image was then utilized as the common visual foundation for subsequent multimodal synthesis. TWM jointly supported layout-to-image generation, image-to-video generation, safety-critical event generation, and image-to-light detection and ranging (LiDAR) point-cloud generation, enabling controllable modeling of temporal evolution, traffic participant relationships, and geometric topology in a coherent manner. Extensive experiments on multiple public and proprietary datasets demonstrated that TWM achieves state-of-the-art performance across four traffic scene generation tasks. Relative to the best-performing baseline for each task, TWM reduces FID by 40% for general traffic image generation, Fréchet video distance (FVD) by 42% for traffic video generation, Fréchet inception distance (FID) by 74% for traffic-event image generation, and depth error by 11% for point-cloud generation. The code will be released upon publication.
- 30 September 2026
- Published by Tsinghua University Press
- Vol. 6 (3)
Open AccessTWM: Multimodal data generation engine via traffic world model
Generative modeling has emerged as a mainstream paradigm for data synthesis, offering a promising solution to data scarcity and insufficient coverage of long-tail scenarios. Despite remarkable progress in autonomous driving (AD), its potential for traffic data generation from roadside or infrastructure perspectives remains largely underexplored. To this end, we proposed the first traffic-oriented world model termed the traffic world model (TWM) for controllable and high-fidelity multimodal data generation. It was built upon a unified conditional diffusion transformer (cDiT) architecture, which generated a controllable roadside-view image from a structured road-agent layout, and the image was then utilized as the common visual foundation for subsequent multimodal synthesis. TWM jointly supported layout-to-image generation, image-to-video generation, safety-critical event generation, and image-to-light detection and ranging (LiDAR) point-cloud generation, enabling controllable modeling of temporal evolution, traffic participant relationships, and geometric topology in a coherent manner. Extensive experiments on multiple public and proprietary datasets demonstrated that TWM achieves state-of-the-art performance across four traffic scene generation tasks. Relative to the best-performing baseline for each task, TWM reduces FID by 40% for general traffic image generation, Fréchet video distance (FVD) by 42% for traffic video generation, Fréchet inception distance (FID) by 74% for traffic-event image generation, and depth error by 11% for point-cloud generation. The code will be released upon publication.
- Open Access
- 31 July 2026
- Published by Tsinghua University Press
TWM: Multimodal data generation engine via Traffic World Model
- 31 July 2026
- Published by Tsinghua University Press
Open AccessTWM: Multimodal data generation engine via Traffic World Model
- 21 July 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
DCGM: Synergizing Differential Cross-Modal Fusion and Graph-Mamba for Referring Multi-Object Tracking
- 21 July 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
DCGM: Synergizing Differential Cross-Modal Fusion and Graph-Mamba for Referring Multi-Object Tracking
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 42, 3841-3860
LECTP: Lightweight and Efficient Cooperative Trajectory Planning for Multi-CAV at Unsignalized Intersections
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 42, 3841-3860
LECTP: Lightweight and Efficient Cooperative Trajectory Planning for Multi-CAV at Unsignalized Intersections
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (17) , 1
R-PERL: Resilience-Oriented Mixed Platoon Control under Traffic Oscillations and Communication Delays
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (17) , 1
R-PERL: Resilience-Oriented Mixed Platoon Control under Traffic Oscillations and Communication Delays
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (4) , 4587-4597
SSM-Det: State Space Model-Based Object Detector for Intelligent Transportation System
The State Space Model (SSM) has been a growth of interest in computer vision due to its long-term dependency modeling with linear complexity. Despite massive endeavor, it has not been extensively explored in intelligent transportation system (ITS) yet. In this paper, we propose State Space Model-based object Detector (SSM-Det), that is meticulously curated with Direction-aware Visual State Space Encoder (D-VSSE). Specifically, it customizes multi-path pixel exchange and patch re-arrangement via four-direction scanning mechanism, promoting for information communication. To bridge the information bottleneck across high-low level, we further design Split-Fusion (SF) and Skip-Connection (SC) modules for contextual feature propagation before decoding: SF performs multi-channel semantic separation and re-weighting in global-local scope, while SC is responsible for cross-layer feature interaction in a cascaded manner. Empirical studies is conducted on both VisDrone2019-DET and SEU_PML benchmarks, and our proposed SSM-Det reports the state-of-the-art performance against all counterparts by a substantial margin, while maintaining the real-time inference speed. We hope this work contributes to the in-depth investigation of SSM-based detector for intelligent transportation applications. The code is available at https://buaawjq.github.io/SSM-Det/.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (4) , 4587-4597
SSM-Det: State Space Model-Based Object Detector for Intelligent Transportation System
The State Space Model (SSM) has been a growth of interest in computer vision due to its long-term dependency modeling with linear complexity. Despite massive endeavor, it has not been extensively explored in intelligent transportation system (ITS) yet. In this paper, we propose State Space Model-based object Detector (SSM-Det), that is meticulously curated with Direction-aware Visual State Space Encoder (D-VSSE). Specifically, it customizes multi-path pixel exchange and patch re-arrangement via four-direction scanning mechanism, promoting for information communication. To bridge the information bottleneck across high-low level, we further design Split-Fusion (SF) and Skip-Connection (SC) modules for contextual feature propagation before decoding: SF performs multi-channel semantic separation and re-weighting in global-local scope, while SC is responsible for cross-layer feature interaction in a cascaded manner. Empirical studies is conducted on both VisDrone2019-DET and SEU_PML benchmarks, and our proposed SSM-Det reports the state-of-the-art performance against all counterparts by a substantial margin, while maintaining the real-time inference speed. We hope this work contributes to the in-depth investigation of SSM-based detector for intelligent transportation applications. The code is available at https://buaawjq.github.io/SSM-Det/.
- 18 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP, 1
Cooperative Coverage Mission Planning for Multi-UAV Based on the Dualring Dynamic Scheduler
Unmanned aerial vehicles (UAVs) have rapidly advanced in applications such as disaster response, infrastructure inspection, and smart city systems. However, cooperative coverage mission planning in dynamic environments poses a persistent challenge in balancing global optimization with real-time responsiveness. To address this, we propose a two-stage task allocation framework based on a dual-ring dynamic scheduler. In the centralized planning phase, an enhanced NSGA-II algorithm is developed, incorporating dual-population initialization, path-exchange crossover, and multi-strategy mutation. Experimental results demonstrate a 49% improvement in the hypervolume indicator over the baseline NSGA-II, with average reductions of 13.33% and 23.71% in total and maximum execution times, respectively. In the dynamic scheduling phase, we design a distributed auction mechanism leveraging a dual-ring communication topology, capable of handling six types of events: UAV failure, UAV addition, node cancel exploration, node urgent exploration, node re-exploration and node in-depth exploration. Through event-driven auctions and group-based bidding, the system maintains a load imbalance under 28% and achieves effective rebalancing even under scenarios with over 50% UAV loss. These results validate the robustness and adaptability of the dual-ring dynamic scheduler in real-time collaborative coverage missions. The proposed method demonstrates significant potential in dynamic, large-scale UAV applications. Source code will be available at: https://github.com/GradualScholar/CoverageMissionPlannin.git
- 18 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP, 1
Cooperative Coverage Mission Planning for Multi-UAV Based on the Dualring Dynamic Scheduler
Unmanned aerial vehicles (UAVs) have rapidly advanced in applications such as disaster response, infrastructure inspection, and smart city systems. However, cooperative coverage mission planning in dynamic environments poses a persistent challenge in balancing global optimization with real-time responsiveness. To address this, we propose a two-stage task allocation framework based on a dual-ring dynamic scheduler. In the centralized planning phase, an enhanced NSGA-II algorithm is developed, incorporating dual-population initialization, path-exchange crossover, and multi-strategy mutation. Experimental results demonstrate a 49% improvement in the hypervolume indicator over the baseline NSGA-II, with average reductions of 13.33% and 23.71% in total and maximum execution times, respectively. In the dynamic scheduling phase, we design a distributed auction mechanism leveraging a dual-ring communication topology, capable of handling six types of events: UAV failure, UAV addition, node cancel exploration, node urgent exploration, node re-exploration and node in-depth exploration. Through event-driven auctions and group-based bidding, the system maintains a load imbalance under 28% and achieves effective rebalancing even under scenarios with over 50% UAV loss. These results validate the robustness and adaptability of the dual-ring dynamic scheduler in real-time collaborative coverage missions. The proposed method demonstrates significant potential in dynamic, large-scale UAV applications. Source code will be available at: https://github.com/GradualScholar/CoverageMissionPlannin.git