融合强度与几何特征，提升桥梁隧道微小裂缝检测精度。
A 3D Multimodal Feature for Infrastructure Anomaly Detection
- 结合自定义FPFH与强度特征构建3D多模态特征
- 在真实桥隧点云中检测出微小裂缝与渗水异常
- 无需大量数据训练，适合工程现场快速部署
老化结构需定期巡检以发现缺陷。以往研究利用几何畸变定位合成砌体桥点云中的裂缝，但难以检测微小裂缝。本文提出一种新型3D多模态特征3DMulti-FPFHI，将定制的Fast Point Feature Histogram（FPFH）与强度特征融合，并集成至PatchCore异常检测算法中，通过统计与参数分析进行评估。该方法在真实砌体拱桥与全尺寸混凝土隧道实验模型的点云数据上验证。结果表明，3D强度特征显著提升检测质量，可有效识别因渗水引起的强度异常；3DMulti-FPFHI优于FPFH及当前先进多模态异常检测方法。该方法仅需极少数据，展现出应对多种基础设施异常检测场景的潜力。代码与数据集已开源：https://github.com/Jingyixiong/3D-Multi-FPFHI。
原文摘要 · Abstract (English)
Ageing structures require periodic inspections to identify structural defects. Previous work has used geometric distortions to locate cracks in synthetic masonry bridge point clouds but has struggled to detect small cracks. To address this limitation, this study proposes a novel 3D multimodal feature, 3DMulti-FPFHI, that combines a customized Fast Point Feature Histogram (FPFH) with an intensity feature. This feature is integrated into the PatchCore anomaly detection algorithm and evaluated through statistical and parametric analyses. The method is further evaluated using point clouds of a real masonry arch bridge and a full-scale experimental model of a concrete tunnel. Results show that the 3D intensity feature enhances inspection quality by improving crack detection; it also enables the identification of water ingress which introduces intensity anomalies. The 3DMulti-FPFHI outperforms FPFH and a state-of-the-art multimodal anomaly detection method. The potential of the method to address diverse infrastructure anomaly detection scenarios is highlighted by the minimal requirements for data compared to learning-based methods. The code and related point cloud dataset are available at https://github.com/Jingyixiong/3D-Multi-FPFHI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。