Vehicle-Scene Interaction: A Text-Driven 3-D Lidar Place Recognition Method for Autonomous Driving
IEEE Transactions on Intelligent Transportation Systems · 2026-08 · 27 (8) · 9563-9575
DOI: 10.1109/tits.2026.3676077 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-08. Verfasst von Tianyi Shang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: Natural Science Foundation of Shandong Province, National Natural Science Foundation of China, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Environment description-based vehicle-scene interaction for vehicle localization in large-scale point cloud maps constructed through multi-sensor systems is critically significant for the advancement of large-scale intelligent transportation systems, such as delivery vehicles operating in the ‘last mile’. However, current vehicle-scene interaction encounter challenges due to the inability of point cloud encoders to effectively capture local details and long-range spatial relationships and a significant modality gap between text and point cloud representations. To address these challenges, we present Des4Pos, a novel two-stage text-driven 3D Lidar place recognition framework. In the coarse stage, the point-cloud encoder utilizes the Multi-scale Fusion Attention Mechanism (MFAM) to enhance local geometric features, followed by a bidirectional Long Short-Term Memory (LSTM) module to strengthen global spatial relationships. Concurrently, the Stepped Text Encoder (STE) integrates cross-modal prior knowledge from CLIP and aligns text and point-cloud features using this prior knowledge, effectively bridging modality discrepancies. In the fine stage, we introduce a Cascaded Residual Attention (CRA) module to fuse cross-modal features and predict relative localization offsets, thereby achieving greater localization precision. Experiments on the KITTI360Pose test set demonstrate that Des4Pos achieves state-of-the-art performance in text-to-point-cloud place recognition at the expense of a slight increase in the runtime. Specifically, it attains a top-1 accuracy of 40% and a top-10 accuracy of 77% under a 5-meter radius threshold, surpassing the best previous sota method Text2Loc by 8% and 7%, respectively. Our code and datasets are publicly available at https://github.com/nuozimiaowu/Des4Pos
Förderung
- Natural Science Foundation of Shandong Province
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Major Innovation Project of Qilu University of Technology
- Science and Technology Support Plan for Youth Innovation of Colleges and Universities in Shandong Province
Zitieren
APA
Shang, T., Li, Z., Xu, P., & Deng, Z. (2026). Vehicle-Scene Interaction: A Text-Driven 3-D Lidar Place Recognition Method for Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems, 27(8), 9563-9575. https://doi.org/10.1109/tits.2026.3676077
Vancouver
Shang T, Li Z, Xu P, Deng Z. Vehicle-Scene Interaction: A Text-Driven 3-D Lidar Place Recognition Method for Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems. 2026;27(8):9563-9575. doi:10.1109/tits.2026.3676077
BibTeX
@article{Shang2026,
author = {Shang, Tianyi and Li, Zhenyu and Xu, Pengjie and Deng, Zhaojun},
title = {Vehicle-Scene Interaction: A Text-Driven 3-D Lidar Place Recognition Method for Autonomous Driving},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2026},
volume = {27},
number = {8},
pages = {9563--9575},
doi = {10.1109/tits.2026.3676077}
}
EUVIMED