Detection of surface cracks
Cracking is often recognized as the first sign of damage in infrastructure.For example,crack distresses are common failure types of pavement,usually caused by heavy vehicle traffic and severe weather condition.Cracking leads to deterioration of the serviceability,and may induce further deterioration of the structure by allowing corrosive agents(e.g.,water)to infiltrate,and eventually causes total failure.Manual inspection is the traditional assessment method of cracking distresses,which is extremely time consuming,lacking of objectivity,prone to human errors,and risky to the inspection personnel due to traffic at high speed.In recent decades,rapid development in computing technology has provided great opportunities for implementation of image-based inspection on cracking distresses.In this paper,a novel image-based crack identification technique is presented.Laser scanned image data is used for analysis,which eliminates the influence of changing lighting condition and image noises such as blemishes.Image filtering techniques are applied during pre-processing,to remove the high frequency noises and low frequency surface shape from the range data.Subsequently,an efficient image contouring analysis is performed to extract crack shapes from the filtered surface.
crack detection feature extraction image processing image filtering
Shanglian Zhou Wei Song
Department of Civil,Construction and Environmental Engineering,University of Alabama,Tuscaloosa,USA
国际会议
The 7th World Conference on Structural Control and Monitoring(7WCSCM)(第七届结构控制与监测世界大会)
青岛
英文
1521-1529
2018-07-22（万方平台首次上网日期，不代表论文的发表时间）