It is of great significance to quickly detect underwater cracks as they can seriously threaten the safety of underwater structures.Research to date has mainly focused on the detection of above-water-level cracks and hasn't considered the large scale cracks.In this paper,a large-scale underwater crack examination method is proposed based on image stitching and segmentation.In addition,a purpose of this paper is to design a new convolution method to segment underwater images.An improved As-Projective-As-Possible(APAP)algorithm was designed to extract and stitch keyframes from videos.The graph convolutional neural network(GCN)was used to segment the stitched image.The GCN's m-IOU is 24.02％higher than Fully convolutional networks(FCN),proving that GCN has great potential of application in image segmentation and underwater image processing.The result shows that the improved APAP algorithm and GCN can adapt to complex underwater environments and perform well in different study areas.

Wenxuan CAO;Junjie LI

Faculty of Infrastructure Engineering,Dalian University of Technology,Dalian 116024,China;College of Water Conservancy and Hydropower Engineering,Hohai University,Nanjing 210098,China

结构与土木工程前沿

[1]Wenxuan CAO;Junjie LI-.Detecting large-scale underwater cracks based on remote operated vehicle and graph convolutional neural network)[J].结构与土木工程前沿,2022(11):1378-1396

keyframes

Detecting,large,scale,underwater,cracks,remote,operated,vehicle,graph,convolutional,neural,It,great,significance,quickly,they,seriously,threaten,safety,structures,Research,date,mainly,focused,detection,above,level,hasn,considered,In,this,paper,examination,method,proposed,stitching,segmentation,addition,purpose,new,images,An,improved,Projective,Possible,APAP,algorithm,was,designed,extract,from,videos,GCN,stitched,IOU,higher,than,Fully,networks,FCN,proving,that,potential,application,processing,result,shows,adapt,complex,environments,perform,well,different,study,areas

0.515032