EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Occlusion-Aware Trajectory Discontinuity Correction for Roadside LiDAR Using Time–Space Analysis

Mingshu Dong iD, Hao Xu iD, Muchen Tian iD, Fei Guan iD, Ziru Wang iD, Renjuan Sun iD, Yanhua Guan

Sensors · 12.06.2026 · 26 (12) · 3755

DOI: 10.3390/s26123755 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.06.2026. Verfasst von Mingshu Dong und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil and Environmental Engineering, University of Nevada, Reno, Reno, NV 89557, USA. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in roadside sensing technologies, including camera-based systems, radar, and LiDAR, have enabled high-resolution sampling of vehicle trajectories, overcoming the temporal and spatial limitations of traditional data collection methods. Among these, LiDAR sensing has been widely adopted for traffic monitoring and surrogate safety analysis due to its high spatial accuracy and temporal resolution. However, sensor noise and occlusion in roadside LiDAR frequently introduce tracking point offsets and trajectory discontinuities, reducing the reliability of vehicle counts, traffic state estimation, and conflict analysis. To address these challenges, this study proposes a post-processing method based on time–space analysis to detect and correct occlusion-induced trajectory discontinuities. By exploiting the inherent spatiotemporal consistency of vehicle movements, the proposed approach identifies fragmented trajectories, reconstructs continuous vehicle paths, and recovers realistic traffic patterns. Validated on real-world LiDAR data collected at an urban intersection in Reno, Nevada, across four 30 min traffic periods covering AM and PM peak conditions on weekdays and weekends, the proposed method achieves an average precision of 0.989 and an average F1-score of 0.948, outperforming IMM, GNN-RM, and HMM + Viterbi benchmark methods. Count accuracy improved from 85.5% to 97.4% across all evaluated periods, confirming the method’s effectiveness under occlusion conditions.

Schlagwörter

Stichwörter der Autor:innen

occlusionpost-processingroadside LiDARtime–space analysistraffic monitoringtrajectory discontinuityvehicle trajectory

Autor:innen und Institutionen

  • Department of Civil and Environmental Engineering, University of Nevada, Reno, Reno, NV 89557, USA.
  • School of Qilu Transportation, Shandong University, Jinan 250002, China.

ORCID-Profile: Mingshu Dong, Hao Xu, Muchen Tian, Fei Guan, Ziru Wang, Renjuan Sun

Zitieren

APA

Dong, M., Xu, H., Tian, M., Guan, F., Wang, Z., Sun, R., & Guan, Y. (2026). Occlusion-Aware Trajectory Discontinuity Correction for Roadside LiDAR Using Time–Space Analysis. Sensors, 26(12), 3755. https://doi.org/10.3390/s26123755

Vancouver

Dong M, Xu H, Tian M, Guan F, Wang Z, Sun R, et al. Occlusion-Aware Trajectory Discontinuity Correction for Roadside LiDAR Using Time–Space Analysis. Sensors. 2026;26(12):3755. doi:10.3390/s26123755

BibTeX
@article{Dong2026,
  author = {Dong, Mingshu and Xu, Hao and Tian, Muchen and Guan, Fei and Wang, Ziru and Sun, Renjuan and Guan, Yanhua},
  title = {Occlusion-Aware Trajectory Discontinuity Correction for Roadside LiDAR Using Time–Space Analysis},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3755},
  doi = {10.3390/s26123755}
}
Kostenlos starten →