Vision-based Automated Bridge Component Recognition Integrated With High-level Scene Understanding

TL;DR

This paper presents a method that combines pixel-level bridge component recognition with high-level scene understanding using multi-scale CNNs and scene classifiers to improve accuracy and reduce false positives in urban scene images.

Contribution

It introduces an integrated approach that combines bridge component detection with scene classification to enhance reliability and reduce false positives in structural image analysis.

Findings

Integrated approach improves detection accuracy.

Reduces false positives compared to naive methods.

Enhances consistency in component classification.

Abstract

Image data has a great potential of helping conventional visual inspections of civil engineering structures due to the ease of data acquisition and the advantages in capturing visual information. A variety of techniques have been proposed to detect damages, such as cracks and spalling on a close-up image of a single component (columns and road surfaces etc.). However, these techniques commonly suffer from severe false-positives especially when the image includes multiple components of different structures. To reduce the false-positives and extract reliable information about the structures' conditions, detection and localization of critical structural components are important first steps preceding the damage assessment. This study aims at recognizing bridge structural and non-structural components from images of urban scenes. During the bridge component recognition, every image pixel is classified into one of the five classes (non-bridge, columns, beams and slabs, other structural, other nonstructural) by multi-scale convolutional neural networks (multi-scale CNNs). To reduce false-positives and get consistent labels, the component classifications are integrated with scene understanding by an additional classifier with 10 higher-level scene classes (building, greenery, person, pavement, signs and poles, vehicles, bridges, water, sky, and others). The bridge component recognition integrated with the scene understanding is compared with the naive approach without scene classification in terms of accuracy, false-positives and consistencies to demonstrate the effectiveness of the integrated approach.