A 3D Multimodal Feature for Infrastructure Anomaly Detection

TL;DR

This paper introduces a novel 3D multimodal feature combining geometric and intensity data to improve infrastructure anomaly detection, especially for small cracks and water ingress, outperforming existing methods.

Contribution

The study proposes the 3DMulti-FPFHI feature that enhances anomaly detection in 3D point clouds by integrating intensity with geometric features, improving detection accuracy and robustness.

Findings

Enhanced crack detection in real and experimental point clouds.

Outperforms existing FPFH and multimodal methods.

Enables detection of water ingress anomalies.

Abstract

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.