Comparison of deep convolutional neural network classifiers and the effect of scale encoding for automated pavement assessment

作     者：Elham Eslami Hae-Bum Yun Elham Eslami;Hae-Bum Yun

作者机构：Department of CivilEnvironmental and Construction EngineeringUniversity of Central FloridaOrlandoFL 32816USA 

出 版 物：《Journal of Traffic and Transportation Engineering(English Edition)》 (交通运输工程学报（英文版）)

年 卷 期：2023年第10卷第2期

页      面：258-275页

核心收录：

学科分类：0710[理学-生物学] 08[工学] 081104[工学-模式识别与智能系统] 0814[工学-土木工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by Data Transfer Solutions,a company located in Orlando,Florida,U.S.A. Korea Institute of Civil Engineering and Building Technology(KICT)。 

主　　题：Road damage detection Automated pavement condition assessment Convolutional neural networks Deep learning Multi-class classification 

摘      要：Deep learning has received a growing interest in recent years for detecting different types of pavement distresses and automating pavement condition assessment.A proper choice of deep learning models is key for successful pavement assessment applications.In this study,we first present a comprehensive experimental comparison of state-of-the-art image classification models to evaluate their performances on 11 pavement objects classification.Our experiments are conducted in different dimensions of comparison,including deep classifier architecture,effects of network depth,and computational costs.Five convolutional neural network(CNN)classifiers widely used in transportation applications,including VGG16,VGG19,ResNet50,DenseNet121,and a generic CNN(as the control model),are tested with a comprehensive pixel-level annotated dataset for 11 different distress and non-distress classes(UCF-PAVE 2017).In addition,we investigate a simple yet effective approach of encoding contextual information with multi-scale input tiles to classify highly random pavement objects in size,shape,intensity,texture,and direction.Our comparison results show that the multi-scale approach significantly improves the classification accuracy for all compared deep classifiers at a negligible extra computational cost.Finally,we provide recommendations of how to improve the classification performance of deep CNNs for automated pavement condition assessment based on the comparison results.