Deep learning for intelligent identification of concrete wind-erosion damage
Authors:
- Xiaoning CuiXCXiaoning Cui
- Qicai WangQWQicai Wang
- Sheng LiSLSheng Li
- Jinpeng DaiJDJinpeng Dai
- Chao XieCXChao Xie
- Yun DuanYDYun Duan
- Jianqiang WangJWJianqiang Wang
- 23 June 2022
- journal article
- research article
- Published by Elsevier in Automation in Construction
- Vol. 141
Abstract
No abstract availableKeywords
This publication has 44 references indexed in Scilit:
- Spatial heterogeneity of surface sediment grain size and aeolian activity in the gobi desert region of northwest ChinaCATENA, 2020
- Computer vision-based concrete crack detection using U-net fully convolutional networksAutomation in Construction, 2019
- Simulations of wind erosion along the Qinghai-Tibet Railway in north-central TibetAeolian Research, 2018
- Autonomous UAVs for Structural Health Monitoring Using Deep Learning and an Ultrasonic Beacon System with Geo‐TaggingComputer-Aided Civil and Infrastructure Engineering, 2018
- Dynamic wind differences in the formation of sand hazards at high- and low-altitude railway sectionsJournal of Wind Engineering and Industrial Aerodynamics, 2017
- Estimation of wind erosion from construction of a railway in arid Northwest ChinaInternational Soil and Water Conservation Research, 2017
- Experimental study into erosion damage mechanism of concrete materials in a wind-blown sand environmentConstruction and Building Materials, 2016
- Characteristics of the disastrous wind-sand environment along railways in the Gobi area of Xinjiang, ChinaAtmospheric Environment, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Wind energy environments and aeolian sand characteristics along the Qinghai–Tibet Railway, ChinaSedimentary Geology, 2012