Unified Few-shot Crack Segmentation and its Precise 3D Automatic Measurement in Concrete Structures

2025-01-15

AI Summary

To address key bottlenecks in concrete crack detection—including poor scene generalization, 2D measurement distortion, and difficulty modeling complex curved surfaces—this paper proposes an integrated framework combining few-shot segmentation with automated 3D metrology. We innovatively design a Segment Anything Model (SAM)-enhanced few-shot crack segmentation network and, for the first time, integrate LiDAR-image dual-modal SLAM with multimodal point cloud registration and color transfer to enable direct, full-parameter 3D measurement of crack length, width, and depth on curved structural elements. Extensive validation across diverse real-world concrete structures demonstrates a 12.6% improvement in 2D segmentation mIoU and sub-1.8 mm 3D measurement error—significantly outperforming conventional 2D projection methods. The framework enables high-accuracy, calibration-free 3D metrology on arbitrarily curved surfaces.

Technology Category

• Computer Vision: Segmentation
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Visual-Spatial Systems has become increasingly essential in concrete crack inspection. However, existing methods often lacks adaptability to diverse scenarios, exhibits limited robustness in image-based approaches, and struggles with curved or complex geometries. To address these limitations, an innovative framework for two-dimensional (2D) crack detection, three-dimensional (3D) reconstruction, and 3D automatic crack measurement was proposed by integrating computer vision technologies and multi-modal Simultaneous localization and mapping (SLAM) in this study. Firstly, building on a base DeepLabv3+ segmentation model, and incorporating specific refinements utilizing foundation model Segment Anything Model (SAM), we developed a crack segmentation method with strong generalization across unfamiliar scenarios, enabling the generation of precise 2D crack masks. To enhance the accuracy and robustness of 3D reconstruction, Light Detection and Ranging (LiDAR) point clouds were utilized together with image data and segmentation masks. By leveraging both image- and LiDAR-SLAM, we developed a multi-frame and multi-modal fusion framework that produces dense, colorized point clouds, effectively capturing crack semantics at a 3D real-world scale. Furthermore, the crack geometric attributions were measured automatically and directly within 3D dense point cloud space, surpassing the limitations of conventional 2D image-based measurements. This advancement makes the method suitable for structural components with curved and complex 3D geometries. Experimental results across various concrete structures highlight the significant improvements and unique advantages of the proposed method, demonstrating its effectiveness, accuracy, and robustness in real-world applications.

Problem

• Concrete crack detection
• Flexibility limitations
• 3D crack measurement

Innovation

• Computer Vision
• SLAM Technology
• Crack Detection and Measurement