ENSTRECT: A Stage-based Approach to 2.5D Structural Damage Detection

TL;DR

ENSTRECT is a stage-based method for 2.5D structural damage detection that localizes and quantifies damage instances in civil structures using image and point cloud data, achieving high accuracy for cracks and corrosion.

Contribution

It introduces a novel stage-based approach combining image segmentation and point cloud mapping for detailed damage localization and quantification.

Findings

Over 90% IoU for cracks

82% IoU for corrosion

45-56% AP50 detection accuracy

Abstract

To effectively assess structural damage, it is essential to localize the instances of damage in the physical world of a civil structure. ENSTRECT is a stage-based approach designed to accomplish 2.5D structural damage detection. The method requires an image collection, the relative orientation, and a point cloud. Using these inputs, surface damages are segmented at the image level and then mapped into the point cloud space, resulting in a segmented point cloud. To enable further quantitative analyses, the segmented point cloud is transformed into measurable damage instances: cracks are extracted by contracting the clustered point cloud into a corresponding medial axis. For areal damages, such as spalling and corrosion, a procedure is proposed to compute the bounding polygon based on PCA and alpha shapes. With a localization tolerance of 4cm, ENSTRECT can achieve IoUs of over 90% for cracks, 82% for corrosion, and 41% for spalling. Detection at the instance level yields an AP50 of about 45% (cracks, spalling) and 56% (corrosion).