Fine-grained truck classification is critical for intelligent transportation systems (ITS), yet current LiDAR-based methods face scalability challenges due to their reliance on supervised deep learning and labor-intensive manual annotation. Vision-Language Models (VLMs) offer promising few-shot generalization, but their application to roadside LiDAR is limited by a modality gap between sparse 3D point clouds and dense 2D imagery. We propose a framework that bridges this gap by adapting off-the-shelf VLMs for fine-grained truck classification without parameter fine-tuning. Our new depth-aware image generation pipeline applies noise removal, spatial and temporal registration, orientation rectification, morphological operations, and anisotropic smoothing to transform sparse, occluded LiDAR scans into depth-encoded 2D visual proxies. Validated on a real-world dataset of 20 vehicle classes, our approach achieves competitive classification accuracy with as few as 16-30 examples per class, offering a scalable alternative to data-intensive supervised baselines. We further observe a "Semantic Anchor" effect: text-based guidance regularizes performance in ultra-low-shot regimes $k < 4$, but degrades accuracy in more-shot settings due to semantic mismatch. Furthermore, we demonstrate the efficacy of this framework as a Cold Start strategy, using VLM-generated labels to bootstrap lightweight supervised models. Notably, the few-shot VLM-based model achieves over correct classification rate of 75 percent for specific drayage categories (20ft, 40ft, and 53ft containers) entirely without the costly training or fine-tuning, significantly reducing the intensive demands of initial manual labeling, thus achieving a method of practical use in ITS applications.
RS2AD-LiDAR: End-to-End Autonomous Driving LiDAR Data Generation from Roadside Sensor Observations
State Key Laboratory of Intelligent Green Vehicle and Mobility(智能绿色车辆与移动国家重点实验室);School of Vehicle and Mobility(车辆与移动学院);College of Artificial Intelligence(人工智能学院);Logic & Silicon AI Studio;School of Instrumentation and Optoelectronic Engineering(仪器科学与光电工程学院)
SVII-3D: Advancing Roadside Infrastructure Inventory with Decimeter-level 3D Localization and Comprehension from Sparse Street Imagery
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan 430079, China(信息工程测绘遥感国家重点实验室(LIESMARS),武汉大学);Research Institute Ltd, Chengdu 610000, China(四川省公路规划设计研究有限公司)
BAAI-VANJEE Roadside Dataset: Towards the Connected Automated Vehicle Highway technologies in Challenging Environments of China
VanJee Technology(万集科技);BeiJing Academy of Artificial Intelligence(北京人工智能研究院)
随着路边感知在互联自动车辆高速公路(CAVH)技术中发挥越来越重要的作用,迫切需要挑战真实世界的路边数据集,用于基准标记和训练各种计算机视觉任务,如2D/3D目标检测和多传感器融合。本文首先介绍了一个具有挑战性的BAAI-VANJEE路边数据集,该数据集由放置在路边约4.5米高的VANJEE智能基站收集的LiDAR数据和RGB图像组成。该数据集包含2500帧LiDAR数据,5000帧RGB图像,其中20%同时采集。它还包含12类对象,74 K 3D对象注释和105 K 2D对象注释。通过提供真实复杂的城市交叉口和高速公路场景,我们期待BAAI-VANJEE路边数据集将积极协助学术界和产业界加速大数据时代智能交通领域的创新研究和成果转化。
Which LiDAR scanning pattern is better for roadside perception: Repetitive or Non-repetitive?
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University(自动化与智能感知学院,上海交通大学);Global College, Shanghai Jiao Tong University(全球学院,上海交通大学)
A Fully Interpretable Statistical Approach for Roadside LiDAR Background Subtraction
Fundación Vicomtech, Basque Research and Technology Alliance (BRTA)(维克森科技基金会、巴斯克研究与技术联盟);University of the Basque Country (UPV/EHU)(巴斯克国家大学);CAFSignalling(CAF信号公司);IKERBASQUE, Basque Foundation for Science(伊基尔巴斯克基金会);Donostia International Physics Center (DIPC)(多诺西亚国际物理中心);Biofisika Institute(生物物理研究所)
Beam-Wise Statistical Background Subtraction for Static Roadside LiDAR: A Cross-Sensor Benchmark Study
University of Applied Sciences Esslingen(埃斯林根应用科学大学);Faculty of Computer Science and Engineering(计算机科学与工程学院);Institute for Intelligent Systems(智能系统研究所)
RS2AD: End-to-End Autonomous Driving Data Generation from Roadside Sensor Observations
School of Vehicle and Mobility, Tsinghua University(清华大学车辆与移动系统学院);State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University(清华大学智能绿色车辆与移动系统国家重点实验室);School of Instrumentation and Optoelectronic Engineering, BeiHang University(北航仪器与光电工程学院);Department of Automation, Tsinghua University(清华大学自动化系)
TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation
SAIVT Group, School of Electrical Engineering and Robotics, Queensland University of Technology(澳大利亚昆士兰科技大学电气工程与机器人学院SAIVT组);CSIRO Robotics, CSIRO(澳大利亚联邦科学与工业研究组织机器人部)
Cross-Modality Gait Recognition: Bridging LiDAR and Camera Modalities for Human Identification
Southern University of Science and Technology(南方科技大学);The University of Hong Kong(香港大学);University of Cordoba(科尔多瓦大学);The Hong Kong Polytechnic University(香港理工大学)
Person Detection and Tracking from an Overhead Crane LiDAR
School of Engineering Aalto University Espoo, Finland(工程学院 阿尔沃大学 埃斯波芬兰);School of Electrical Engineering Aalto University Espoo, Finland(电气工程学院 阿尔沃大学 埃斯波芬兰)