Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset

Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity. Large variation in appearance of the concrete material, changing illumination and weather conditions, a variety of possible surfa...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-04
Main Authors: Mundt, Martin, Majumder, Sagnik, Sreenivas Murali, Panetsos, Panagiotis, Visvanathan Ramesh
Format: Article
Language:English
Subjects:
Artificial neural networks
Concrete
Concrete bridges
Defects
Image classification
Machine learning
Neural networks
Object recognition
Structural integrity
Weather
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity. Large variation in appearance of the concrete material, changing illumination and weather conditions, a variety of possible surface markings as well as the possibility for different types of defects to overlap, make it a challenging real-world task. In this work we introduce the novel COncrete DEfect BRidge IMage dataset (CODEBRIM) for multi-target classification of five commonly appearing concrete defects. We investigate and compare two reinforcement learning based meta-learning approaches, MetaQNN and efficient neural architecture search, to find suitable convolutional neural network architectures for this challenging multi-class multi-target task. We show that learned architectures have fewer overall parameters in addition to yielding better multi-target accuracy in comparison to popular neural architectures from the literature evaluated in the context of our application.
ISSN:2331-8422