Automatic Pavement Crack Detection Based on Octave Convolution Neural Network with Hierarchical Feature Learning

作     者：Minggang Xu Chong Li Ying Chen Wu Wei Minggang Xu;Chong Li;Ying Chen;Wu Wei

作者机构：Department of Civil Engineering of Nanjing Technical Vocational CollegeNanjing 210019China School of Artificial Intelligence and Advanced Computing(AIAC)Xi’an Jiaotong-Liverpool UniversitySuzhou 215400China Department of Electronic EngineeringShantou UniversityShantou 515063China School of Automation Science and EngineeringSouth China University of TechnologyGuangzhou 510006China 

出 版 物：《Journal of Beijing Institute of Technology》 (北京理工大学学报（英文版）)

年 卷 期：2024年第33卷第5期

页      面：422-435页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0814[工学-土木工程] 0811[工学-控制科学与工程] 082301[工学-道路与铁道工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 0823[工学-交通运输工程] 

基　　金：supported in part by the National Natural Foundation of China(No.62176147) 

主　　题：automated pavement crack detection octave convolutional network hierarchical feature multiscale multifrequency 

摘      要：Automatic pavement crack detection plays an important role in ensuring road *** images of cracks,information about the cracks can be conveyed through high-frequency and low-fre-quency signals that focus on fine details and global structures,*** output features obtained from different convolutional layers can be combined to represent information about both high-frequency and low-frequency *** this paper,we propose an encoder-decoder framework called octave hierarchical network(Octave-H),which is based on the U-Network(U-Net)architec-ture and utilizes an octave convolutional neural network and a hierarchical feature learning module for performing crack *** proposed octave convolution is capable of extracting multi-fre-quency feature maps,capturing both fine details and global *** propose a hierarchical feature learning module that merges multi-frequency-scale feature maps with different levels(high and low)of octave convolutional *** verify the superiority of the proposed Octave-H,we employed the CrackForest dataset(CFD)and AigleRN databases to evaluate this *** experimental results demonstrate that Octave-H outperforms other algorithms with satisfactory performance.