Speak the Same Language: Global LiDAR Registration on BIM Using Pose Hough Transform

2024-05-07

IEEE Transactions on Automation Science and Engineering

AI Summary

This paper addresses the geometric and semantic misalignment between LiDAR point clouds and BIM models—arising from heterogeneous data sources and inconsistent coordinate systems—by proposing a cross-modal precise registration method. Methodologically, it introduces a novel triangular mesh descriptor based on wall and corner extraction, integrated with a hierarchical Hough voting scheme and occupancy-aware scoring validation to achieve scale-invariant matching and robust multi-hypothesis pose estimation. Evaluated on large-scale campus buildings across multiple LiDAR scanning sessions, the method achieves sub-decimeter (<0.1 m) global coordinate system registration accuracy for both terrestrial and mobile LiDAR data. The paper also releases the first benchmark dataset and open-source implementation specifically designed for LiDAR–BIM registration, establishing a reproducible technical pipeline and practical toolkit for cross-modal collaborative modeling.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Light detection and ranging (LiDAR) point clouds and building information modeling (BIM) represent two distinct data modalities in the fields of robot perception and construction. These modalities originate from different sources and are associated with unique reference frames. The primary goal of this study is to align these modalities within a shared reference frame using a global registration approach, effectively enabling them to ``speak the same language''. To achieve this, we propose a cross-modality registration method, spanning from the front end to the back end. At the front end, we extract triangle descriptors by identifying walls and intersected corners, enabling the matching of corner triplets with a complexity independent of the BIM's size. For the back-end transformation estimation, we utilize the Hough transform to map the matched triplets to the transformation space and introduce a hierarchical voting mechanism to hypothesize multiple pose candidates. The final transformation is then verified using our designed occupancy-aware scoring method. To assess the effectiveness of our approach, we conducted real-world multi-session experiments in a large-scale university building, employing two different types of LiDAR sensors. We make the collected datasets and codes publicly available to benefit the community.

Problem

• Align LiDAR point clouds and BIM in a shared reference frame.
• Propose a cross-modality registration method using Hough transform.
• Enable global registration of LiDAR and BIM data efficiently.

Innovation

• Cross-modality registration using triangle descriptors
• Hough transform for pose estimation
• Occupancy-aware scoring for transformation verification