EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SGMR-LPR: A Semantic-Guided Network Robust to Movable Objects for LiDAR-Based Place Recognition

Weizhong Jiang iD, Zhipeng Xiao, Lilin Qian, Erke Shang, Dawei Zhao, Qi Zhu, Liang Xiao iD

Sensors · 12.05.2026 · 26 (10) · 3050

DOI: 10.3390/s26103050 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.05.2026. Verfasst von Weizhong Jiang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Defense Innovation Institute, Beijing 100071, China. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Defense Innovation Institution.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Robust LiDAR point cloud processing in dynamic outdoor environments, where movable objects such as vehicles and pedestrians introduce significant structural uncertainty, remains a key challenge for remote sensing and autonomous systems. This work addresses LiDAR-based place recognition (LPR), a critical component for loop closure and re-localization that is highly susceptible to such dynamics. While semantic information is beneficial, existing methods often require external segmentation models at inference or lack explicit mechanisms to suppress movable objects under uncertain predictions. To address these limitations, we propose SGMR-LPR, an end-to-end semantic-guided framework designed to explicitly counteract movable-object interference during feature encoding. Building on the “segmentation-while-describing” paradigm, SGMR-LPR incorporates an internal semantic segmentation branch and two novel modules: a probabilistic movable object masking (PMOM) module, which transforms semantic logits into continuous, uncertainty-aware masks of movable regions; and a movable-suppressed channel–spatial attention (MSCS) module, which uses these masks to adaptively modulate high-level BEV features—suppressing responses from movable-object regions while enhancing stable structural elements. By embedding explicit movable-awareness into feature modulation, SGMR-LPR achieves enhanced robustness without external semantic models at inference. Extensive experiments on multiple benchmarks demonstrate consistent performance gains, particularly in scenes with dense movable objects, advancing reliable point cloud-based scene understanding in dynamic environments.

Schlagwörter

Stichwörter der Autor:innen

3D point cloud processingBEV feature modulationLiDAR-based place recognitionattention mechanismmovable objects robustnessscene understandingsemantic guidance

Autor:innen und Institutionen

  • Defense Innovation Institute, Beijing 100071, China.

ORCID-Profile: Weizhong Jiang, Liang Xiao

Förderung

  • Defense Innovation Institution

Zitieren

APA

Jiang, W., Xiao, Z., Qian, L., Shang, E., Zhao, D., Zhu, Q., & Xiao, L. (2026). SGMR-LPR: A Semantic-Guided Network Robust to Movable Objects for LiDAR-Based Place Recognition. Sensors, 26(10), 3050. https://doi.org/10.3390/s26103050

Vancouver

Jiang W, Xiao Z, Qian L, Shang E, Zhao D, Zhu Q, et al. SGMR-LPR: A Semantic-Guided Network Robust to Movable Objects for LiDAR-Based Place Recognition. Sensors. 2026;26(10):3050. doi:10.3390/s26103050

BibTeX
@article{Jiang2026,
  author = {Jiang, Weizhong and Xiao, Zhipeng and Qian, Lilin and Shang, Erke and Zhao, Dawei and Zhu, Qi and Xiao, Liang},
  title = {SGMR-LPR: A Semantic-Guided Network Robust to Movable Objects for LiDAR-Based Place Recognition},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3050},
  doi = {10.3390/s26103050}
}
Kostenlos starten →