WHU-PCPR: A cross-platform heterogeneous point cloud dataset for place recognition in complex urban scenes

2026-01-10

arXiv.org

AI Summary

Existing place recognition datasets are limited in scene complexity, platform diversity, and sensor heterogeneity, hindering research on cross-platform point cloud place recognition in complex urban environments. To address this gap, this work introduces the WHU-PCPR dataset, which uniquely integrates vehicle-mounted high-precision mobile laser scanning (MLS) and head-worn portable laser scanning (PLS) systems, combining both mechanical and solid-state LiDARs. The dataset spans 82.3 kilometers of trajectories and 60 months of temporal coverage, encompassing dynamically evolving urban and campus road scenes. Accompanying the release, the authors provide benchmark code and conduct a systematic evaluation of state-of-the-art methods, revealing significant performance bottlenecks under cross-platform and sensor-heterogeneous conditions, thereby establishing a foundational resource and identifying key challenges for future research.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Point Cloud-based Place Recognition (PCPR) demonstrates considerable potential in applications such as autonomous driving, robot localization and navigation, and map update. In practical applications, point clouds used for place recognition are often acquired from different platforms and LiDARs across varying scene. However, existing PCPR datasets lack diversity in scenes, platforms, and sensors, which limits the effective development of related research. To address this gap, we establish WHU-PCPR, a cross-platform heterogeneous point cloud dataset designed for place recognition. The dataset differentiates itself from existing datasets through its distinctive characteristics: 1) cross-platform heterogeneous point clouds: collected from survey-grade vehicle-mounted Mobile Laser Scanning (MLS) systems and low-cost Portable helmet-mounted Laser Scanning (PLS) systems, each equipped with distinct mechanical and solid-state LiDAR sensors. 2) Complex localization scenes: encompassing real-time and long-term changes in both urban and campus road scenes. 3) Large-scale spatial coverage: featuring 82.3 km of trajectory over a 60-month period and an unrepeated route of approximately 30 km. Based on WHU-PCPR, we conduct extensive evaluation and in-depth analysis of several representative PCPR methods, and provide a concise discussion of key challenges and future research directions. The dataset and benchmark code are available at https://github.com/zouxianghong/WHU-PCPR.

Problem

• Point Cloud-based Place Recognition
• cross-platform
• heterogeneous LiDAR
• urban scenes
• dataset diversity

Innovation

• cross-platform
• heterogeneous point cloud
• place recognition
• LiDAR
• urban scene