Vision-based Structural Inspection using Multiscale Deep Convolutional Neural Networks

TL;DR

This paper introduces a multiscale deep convolutional neural network for automated, pixel-wise damage detection and classification in civil infrastructure images, significantly improving post-earthquake inspection efficiency.

Contribution

It presents a novel multiscale CNN approach for damage localization and classification, addressing limitations of existing computer vision methods in structural inspections.

Findings

Achieved high pixel accuracy in damage detection

Successfully classified six damage types

Demonstrated effectiveness on real-world images

Abstract

Current methods of practice for inspection of civil infrastructure typically involve visual assessments conducted manually by trained inspectors. For post-earthquake structural inspections, the number of structures to be inspected often far exceeds the capability of the available inspectors. The labor intensive and time consuming natures of manual inspection have engendered research into development of algorithms for automated damage identification using computer vision techniques. In this paper, a novel damage localization and classification technique based on a state of the art computer vision algorithm is presented to address several key limitations of current computer vision techniques. The proposed algorithm carries out a pixel-wise classification of each image at multiple scales using a deep convolutional neural network and can recognize 6 different types of damage. The resulting output is a segmented image where the portion of the image representing damage is outlined and classified as one of the trained damage categories. The proposed method is evaluated in terms of pixel accuracy and the application of the method to real world images is shown.